Mirrors_Framework/PX4-Autopilot
1
0
Fork 0
mirror of https://github.com/PX4/PX4-Autopilot.git synced 2026-02-06 03:13:00 +08:00
Code Issues Actions 27 Packages Projects Releases Wiki Activity

New Crowdin translations - zh-CN (#26248)

Browse Source 
Co-authored-by: Crowdin Bot <support+bot@crowdin.com>
This commit is contained in:
PX4 Build Bot
2026-01-28 16:43:18 +11:00
committed by GitHub
parent 65cedc8bf8
commit c90095e8b4
29 changed files with 1186 additions and 213 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docs/zh/SUMMARY.md
View File

@@ -128,6 +128,7 @@
- [LED灯含义](getting_started/led_meanings.md)
- [声调/声音含义](getting_started/tunes.md)
- [QGroundControl Flight-Readiness Status](flying/pre_flight_checks.md)
- [Asset Tracking](debug/asset_tracking.md)
- [Hardware Selection & Setup](hardware/drone_parts.md)
- [飞行控制器(Autopilots)](flight_controller/index.md)
@@ -273,6 +274,8 @@
- [Holybro M8N & M9N GPS](gps_compass/gps_holybro_m8n_m9n.md)
- [Sky-Drones SmartAP GPS](gps_compass/gps_smartap.md)
- [RTK GNSS](gps_compass/rtk_gps.md)
- [ARK G5 RTK GPS](dronecan/ark_g5_rtk_gps.md)
- [ARK G5 RTK HEADING GPS](dronecan/ark_g5_rtk_heading_gps.md)
- [ARK RTK GPS (CAN)](dronecan/ark_rtk_gps.md)
- [ARK RTK GPS L1 L5 (CAN)](dronecan/ark_rtk_gps_l1_l2.md)
- [ARK X20 RTK GPS (CAN)](dronecan/ark_x20_rtk_gps.md)
@@ -840,9 +843,11 @@
- [Camera Integration/Architecture](camera/camera_architecture.md)
- [机器视觉](advanced/computer_vision.md)
- [Motion Capture (VICON, Optitrack, NOKOV)](tutorials/motion-capture.md)
- [Neural Networks](advanced/neural_networks.md)
- [Neural Network Module Utilities](advanced/nn_module_utilities.md)
- [TensorFlow Lite Micro (TFLM)](advanced/tflm.md)
- [Neural Networks](neural_networks/index.md)
- [MC NN Control Module (Generic)](neural_networks/mc_neural_network_control.md)
- [Neural Network Module Utilities](neural_networks/nn_module_utilities.md)
- [TensorFlow Lite Micro (TFLM)](neural_networks/tflm.md)
- [RAPTOR Adaptive RL NN Module](neural_networks/raptor.md)
- [安装英特尔 RealSense R200 的驱动程序](advanced/realsense_intel_driver.md)
- [切换状态估计器](advanced/switching_state_estimators.md)
- [外部模块](advanced/out_of_tree_modules.md)
@@ -925,6 +930,7 @@
- [版本发布](releases/index.md)
- [main (alpha)](releases/main.md)
- [1.17 (alpha)](releases/1.17.md)
- [1.16 (stable)](releases/1.16.md)
- [1.15](releases/1.15.md)
- [1.14](releases/1.14.md)

2
docs/zh/advanced/gimbal_control.md
View File

@@ -74,7 +74,7 @@ The output pins that are used to control the gimbal are set in the [Acuator Conf
![Gimbal Actuator config](../../assets/config/actuators/qgc_actuators_gimbal.png)
The PWM values to use for the disarmed, maximum and minimum values can be determined in the same way as other servo, using the [Actuator Test sliders](../config/actuators.md#actuator-testing) to confirm that each slider moves the appropriate axis, and changing the values so that the gimbal is in the appropriate position at the disarmed, low and high position in the slider.
The PWM values to use for the disarmed, maximum, center and minimum values can be determined in the same way as other servo, using the [Actuator Test sliders](../config/actuators.md#actuator-testing) to confirm that each slider moves the appropriate axis, and changing the values so that the gimbal is in the appropriate position at the disarmed, low, center and high position in the slider.
这些数值也可以在云台文档中提供。
## Gimbal Control in Missions

120
docs/zh/advanced/neural_networks.md
View File

@@ -1,119 +1 @@
# Neural Networks
<Badge type="tip" text="main (planned for: PX4 v1.17)" /> <Badge type="warning" text="Experimental" />
:::warning
This is an experimental module.
Use at your own risk.
:::
The Multicopter Neural Network (NN) module ([mc_nn_control](../modules/modules_controller.md#mc-nn-control)) is an example module that allows you to experiment with using a pre-trained neural network on PX4.
It might be used, for example, to experiment with controllers for non-traditional drone morphologies, computer vision tasks, and so on.
The module integrates a pre-trained neural network based on the [TensorFlow Lite Micro (TFLM)](../advanced/tflm.md) module.
The module is trained for the [X500 V2](../frames_multicopter/holybro_x500v2_pixhawk6c.md) multicopter frame.
While the controller is fairly robust, and might work on other platforms, we recommend [Training your own Network](#training-your-own-network) if you use a different vehicle.
Note that after training the network you will need to update and rebuild PX4.
TLFM is a mature inference library intended for use on embedded devices.
It has support for several architectures, so there is a high likelihood that you can build it for the board you want to use.
If not, there are other possible NN frameworks, such as [Eigen](https://eigen.tuxfamily.org/index.php?title=Main_Page) and [Executorch](https://pytorch.org/executorch-overview).
This document explains how you can include the module in your PX4 build, and provides a broad overview of how it works.
The other documents in the section provide more information about the integration, allowing you to replace the NN with a version trained on different data, or even to replace the TLFM library altogether.
If you are looking for more resources to learn about the module, a website has been created with links to a youtube video and a workshop paper. A full master's thesis will be added later. [A Neural Network Mode for PX4 on Embedded Flight Controllers](https://ntnu-arl.github.io/px4-nns/).
## Neural Network PX4 Firmware
:::warning
This module requires Ubuntu 24.04 or newer (it is not supported in Ubuntu 22.04).
:::
The module has been tested on a number of configurations, which can be build locally using the commands:
```sh
make px4_sitl_neural
```
```sh
make px4_fmu-v6c_neural
```
```sh
make mro_pixracerpro_neural
```
You can add the module to other board configurations by modifying their `default.px4board file` configuration to include these lines:
```sh
CONFIG_LIB_TFLM=y
CONFIG_MODULES_MC_NN_CONTROL=y
```
:::tip
The `mc_nn_control` module takes up roughly 50KB, and many of the `default.px4board file` are already close to filling all the flash on their boards. To make room for the neural control module you can remove the include statements for other modules, such as FW, rover, VTOL and UUV.
:::
## Example Module Overview
The example module replaces the entire controller structure as well as the control allocator, as shown in the diagram below:
![neural_control](../../assets/advanced/neural_control.png)
In the [controller diagram](../flight_stack/controller_diagrams.md) you can see the [uORB message](../middleware/uorb.md) flow.
We hook into this flow by subscribing to messages at particular points, using our neural network to calculate outputs, and then publishing them into the next point in the flow.
We also need to stop the module publishing the topic to be replaced, which is covered in [Neural Network Module: System Integration](nn_module_utilities.md)
### Input
The input can be changed to whatever you want.
Set up the input you want to use during training and then provide the same input in PX4.
In the Neural Control module the input is an array of 15 numbers, and consists of these values in this order:
- [3] Local position error. (goal position - current position)
- [6] The first 2 rows of a 3 dimensional rotation matrix.
- [3] Linear velocity
- [3] Angular velocity
All the input values are collected from uORB topics and transformed into the correct representation in the `PopulateInputTensor()` function.
PX4 uses the NED frame representation, while the Aerial Gym Simulator, in which the NN was trained, uses the ENU representation.
Therefore two rotation matrices are created in the function and all the inputs are transformed from the NED representation to the ENU one.
![ENU-NED](../../assets/advanced/ENU-NED.png)
ENU and NED are just rotation representations, the translational difference is only there so both can be seen in the same figure.
### 输出
The output consists of 4 values, the motor forces, one for each motor.
These are transformed in the `RescaleActions()` function.
This is done because PX4 expects normalized motor commands while the Aerial Gym Simulator uses physical values.
So the output from the network needs to be normalized before they can be sent to the motors in PX4.
The commands are published to the [ActuatorMotors](../msg_docs/ActuatorMotors.md) topic.
The publishing is handled in `PublishOutput(float* command_actions)` function.
:::tip
If the neural control mode is too aggressive or unresponsive the [MC_NN_THRST_COEF](../advanced_config/parameter_reference.md#MC_NN_THRST_COEF) parameter can be tuned.
Decrease it for more thrust.
:::
## Training your own Network
The network is currently trained for the [X500 V2](../frames_multicopter/holybro_x500v2_pixhawk6c.md).
But the controller is somewhat robust, so it could work directly on other platforms, but performing system identification and training a new network is recommended.
Since the Aerial Gym Simulator is open-source you can download it and train your own networks as long as you have access to an NVIDIA GPU.
If you want to train a control network optimized for your platform you can follow the instructions in the [Aerial Gym Documentation](https://ntnu-arl.github.io/aerial_gym_simulator/9_sim2real/).
You should do one system identification flight for this and get an approximate inertia matrix for your platform.
On the `sys-id` flight you need ESC telemetry, you can read more about that in [DSHOT](../peripherals/dshot.md).
Then do the following steps:
- Do a hover flight
- Read of the logs what RPM is required for the drone to hover.
- Use the weight of each motor, length of the motor arms, total weight of the platform with battery to calculate an approximate inertia matrix for the platform.
- Insert these values into the Aerial Gym configuration and train your network.
- Convert the network as explained in [TFLM](tflm.md).
<Redirect to="../neural_networks/mc_neural_network_control" />

4
docs/zh/can/index.md
View File

@@ -10,6 +10,10 @@ CAN it is designed to be democratic and uses differential signaling.
For this reason it is very robust even over longer cable lengths (on large vehicles), and avoids a single point of failure.
CAN 还允许来自外设的状态反馈，并通过总线方便的进行固件升级。
PX4 has the ability to track and log detailed information from CAN devices, including firmware versions, hardware versions, and serial numbers.
This enables unique identification and lifecycle tracking of hardware connected to the flight controller.
See [Asset Tracking](../debug/asset_tracking.md) for more information.
PX4 支持与 CAN 设备通信的两个软件协议：
- [DroneCAN](../dronecan/index.md): PX4 推荐大多数常见的设置。

26
docs/zh/config/safety.md
View File

@@ -121,36 +121,32 @@ PX4 and the receiver may also need to be configured in order to _detect RC loss_
![Safety - RC Loss (QGC)](../../assets/qgc/setup/safety/safety_rc_loss.png)
The QGCroundControl Safety UI allows you to set the [failsafe action](#failsafe-actions) and [RC Loss timeout](#COM_RC_LOSS_T).
Users that want to disable the RC loss failsafe in specific automatic modes (mission, hold, offboard) can do so using the parameter [COM_RCL_EXCEPT](#COM_RCL_EXCEPT).
The QGCroundControl Safety UI allows you to set the [failsafe action](#failsafe-actions) and [manual control loss timeout](#COM_RC_LOSS_T).
Users that want to disable this failsafe in specific modes can do so using the parameter [COM_RCL_EXCEPT](#COM_RCL_EXCEPT).
Additional (and underlying) parameter settings are shown below.
| 参数 | 设置 | 描述 |
| -------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| <a id="COM_RC_LOSS_T"></a>[COM_RC_LOSS_T](../advanced_config/parameter_reference.md#COM_RC_LOSS_T) | Manual Control Loss Timeout | Time after last setpoint received from the selected manual control source after which manual control is considered lost. This must be kept short because the vehicle will continue to fly using the old manual control setpoint until the timeout triggers. |
| <a id="COM_RC_LOSS_T"></a>[COM_RC_LOSS_T](../advanced_config/parameter_reference.md#COM_RC_LOSS_T) | Manual Control Loss Timeout | Time after last setpoint received from the selected manual control source after which manual control is considered lost. This must be kept short because the vehicle will continue to fly using the last known stick position until the timeout triggers. |
| <a id="COM_FAIL_ACT_T"></a>[COM_FAIL_ACT_T](../advanced_config/parameter_reference.md#COM_FAIL_ACT_T) | Failsafe Reaction Delay | Delay in seconds between failsafe condition being triggered (`COM_RC_LOSS_T`) and failsafe action (RTL, Land, Hold). In this state the vehicle waits in hold mode for the manual control source to reconnect. This might be set longer for long-range flights so that intermittent connection loss doesn't immediately invoke the failsafe. It can be to zero so that the failsafe triggers immediately. |
| <a id="NAV_RCL_ACT"></a>[NAV_RCL_ACT](../advanced_config/parameter_reference.md#NAV_RCL_ACT) | 故障保护动作 | Disabled, Loiter, Return, Land, Disarm, Terminate. |
| <a id="COM_RCL_EXCEPT"></a>[COM_RCL_EXCEPT](../advanced_config/parameter_reference.md#COM_RCL_EXCEPT) | RC Loss Exceptions | Set the modes in which manual control loss is ignored: Mission, Hold, Offboard. |
| <a id="COM_RCL_EXCEPT"></a>[COM_RCL_EXCEPT](../advanced_config/parameter_reference.md#COM_RCL_EXCEPT) | RC Loss Exceptions | Set modes in which manual control loss is ignored. |
## 数据链路丢失故障保护
The Data Link Loss failsafe is triggered if a telemetry link (connection to ground station) is lost.
The Data Link Loss failsafe is triggered if the connection to the last MAVLink ground station like QGroundControl is lost.
Users that want to disable this failsafe in specific modes can do so using the parameter [COM_DLL_EXCEPT](#COM_DLL_EXCEPT).
![Safety - Data Link Loss (QGC)](../../assets/qgc/setup/safety/safety_data_link_loss.png)
The settings and underlying parameters are shown below.
| 设置 | 参数 | 描述 |
| -------- | --------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------- |
| 数据链路丢失超时 | [COM_DL_LOSS_T](../advanced_config/parameter_reference.md#COM_DL_LOSS_T) | 数据连接断开后到故障保护触发之前的时间。 |
| 故障保护动作 | [NAV_DLL_ACT](../advanced_config/parameter_reference.md#NAV_DLL_ACT) | Disabled, Hold mode, Return mode, Land mode, Disarm, Terminate. |
The following settings also apply, but are not displayed in the QGC UI.
| 设置 | 参数 | 描述 |
| ----------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------- |
| <a id="COM_DLL_EXCEPT"></a>Mode exceptions for DLL failsafe | [COM_DLL_EXCEPT](../advanced_config/parameter_reference.md#COM_DLL_EXCEPT) | Set modes where DL loss will not trigger a failsafe. |
| 设置 | 参数 | 描述 |
| ----------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------- |
| 数据链路丢失超时 | [COM_DL_LOSS_T](../advanced_config/parameter_reference.md#COM_DL_LOSS_T) | 数据连接断开后到故障保护触发之前的时间。 |
| 故障保护动作 | [NAV_DLL_ACT](../advanced_config/parameter_reference.md#NAV_DLL_ACT) | Disabled, Hold mode, Return mode, Land mode, Disarm, Terminate. |
| <a id="COM_DLL_EXCEPT"></a>Mode exceptions for DLL failsafe | [COM_DLL_EXCEPT](../advanced_config/parameter_reference.md#COM_DLL_EXCEPT) | Set modes in which data link loss is ignored. |
## 地理围栏故障保护

68
docs/zh/debug/asset_tracking.md Normal file
View File

@@ -0,0 +1,68 @@
# Asset Tracking
<Badge type="tip" text="main (planned for: PX4 v1.18)" />
PX4 can track and log detailed information about external hardware devices connected to the flight controller.
This enables unique identification of vehicle parts throughout their operational lifetime using device IDs, serial numbers, and version information.
:::info
Asset tracking is currently implemented for [DroneCAN](../dronecan/index.md) devices only.
:::
## 综述
Asset tracking allows you to determine exactly which hardware is installed on a vehicle, providing serial number, version, and other information.
This makes it easier to track and maintain specific vehicle parts across multiple vehicles, to quickly see what versions you're running when debugging, and log component information for regulatory audits.
Asset tracking automatically collects and logs the following metadata from external devices:
- **Device identification**: Vendor name, model name, device type
- **Version information**: Firmware version, hardware version
- **Unique identifiers**: Serial number, device ID
- **Device capabilities**: ESC, GPS, magnetometer, barometer, etc.
This information is published via the [`device_information`](../msg_docs/DeviceInformation.md) uORB topic and logged to flight logs.
This enables fleet management, maintenance tracking, and troubleshooting.
## Viewing Device Information
### Real-Time Monitoring
You can view device information in real-time using the [MAVLink Shell](../debug/mavlink_shell.md) or console:
```sh
listener device_information
```
Example output for a CAN GPS module:
```plain
TOPIC: device_information
device_information
timestamp: 16258961403 (0.216525 seconds ago)
device_id: 8944643 (Type: 0x88, UAVCAN:0 (0x7C))
device_type: 5
vendor_name: "cubepilot"
model_name: "here4"
firmware_version: "1.14.3006590"
hardware_version: "4.19"
serial_number: "1c00410018513331"
```
Device information is published in a round-robin fashion for each detected device, at a rate of approximately 1 Hz.
### Multi-Capability Devices
Devices with multiple sensors (e.g., a CAN GPS/magnetometer combo module like the HERE4) register separate device information entries for each capability.
Each entry shares the same serial number and base metadata but has a different `device_id` corresponding to the specific sensor capability.
## 飞行日志分析
Device information is automatically logged to flight logs.
You can extract it using [pyulog](../log/flight_log_analysis.md#pyulog), though note that fields like vendor name, model name, and serial number are stored as `char` arrays and require additional parsing.
## 另见
- [CAN (DroneCAN & Cyphal)](../can/index.md) — CAN bus configuration and setup
- [DroneCAN](../dronecan/index.md) — DroneCAN-specific documentation
- [Flight Log Analysis](../log/flight_log_analysis.md) — Flight log analysis

112
docs/zh/dronecan/ark_g5_rtk_gps.md Normal file
View File

@@ -0,0 +1,112 @@
# ARK G5 RTK GPS
:::info
This GPS module is made in the USA and NDAA compliant.
:::
[ARK G5 RTK GPS](https://arkelectron.com/product/ark-g5-rtk-gps/) is a [DroneCAN](index.md) quad-band [RTK GPS](../gps_compass/rtk_gps.md).
The module incorporates the [Septentrio mosaic-G5 P3 Ultra-compact high-precision GPS/GNSS receiver module](https://www.u-blox.com/en/product/zed-x20p-module), magnetometer, barometer, IMU, and buzzer module.
![ARK G5 RTK GPS](../../assets/hardware/gps/ark/ark_g5_rtk_gps.png)
## 购买渠道
Order this module from:
- [ARK Electronics](https://arkelectron.com/product/ark-g5-rtk-gps/) (US)
## Hardware Specifications
- [DroneCAN](index.md) RTK GNSS, Magnetometer, Barometer, IMU, and Buzzer Module
- [Dronecan Firmware Updating](../dronecan/index.md#firmware-update)
- 传感器
- [Septentrio mosaic-G5 P3 Ultra-compact high-precision GPS/GNSS receiver module](https://www.septentrio.com/en/products/gnss-receivers/gnss-receiver-modules/mosaic-G5-P3)
- All-band all constellation GNSS receiver
- All-in-view satellite tracking: multi-constellation, quad-band GNSS module receiver
- Full raw data with positioning measurements and Galileo HAS positioning service compatibility
- Best-in-class RTK cm-level positioning accuracy
- Advanced GNSS+ algorithms
- 20Hz update rate
- [ST IIS2MDC Magnetometer](https://www.st.com/en/mems-and-sensors/iis2mdc.html)
- [Bosch BMP390 Barometer](https://www.bosch-sensortec.com/products/environmental-sensors/pressure-sensors/bmp390/)
- [Invensense ICM-42688-P 6-Axis IMU](https://invensense.tdk.com/products/motion-tracking/6-axis/icm-42688-p/)
- STM32F412VGH6 MCU
- Safety Button
- 蜂鸣器
- Two CAN Connectors (Pixhawk Connector Standard 4-pin JST GH)
- G5 "UART 2" Connector
- 4-pin JST GH
- TX, RX, PPS, GND
- G5 USB C
- Debug Connector (Pixhawk Connector Standard 6-pin JST SH)
- LED Indicators
- GPS Fix
- RTK Status
- RGB system status
- USA Built
- NDAA Compliant
- Power Requirements
- 5V
- 270mA
- 尺寸
- Without Antenna
- 48.0mm x 40.0mm x 15.4mm
- 13.0g
- With Antenna
- 48.0mm x 40.0mm x 51.0mm
- 43.5g
- Includes
- CAN Cable (Pixhawk Connector Standard 4-pin)
- Full-Frequency Helical GPS Antenna
## 硬件安装
### 布线
The ARK G5 RTK GPS is connected to the CAN bus using a [Pixhawk connector standard](https://github.com/pixhawk/Pixhawk-Standards/blob/master/DS-009%20Pixhawk%20Connector%20Standard.pdf) 4-pin JST GH cable.
For more information, refer to the [CAN Wiring](../can/index.md#wiring) instructions.
### Mounting
The recommended mounting orientation is with the connectors on the board pointing towards the **back of vehicle**.
The sensor can be mounted anywhere on the frame, but you will need to specify its position, relative to vehicle centre of gravity, during [PX4 Configuration](#px4-configuration).
## Firmware Setup
The Septentrio G5 module firmware can be updated using the Septentrio [RxTools](https://www.septentrio.com/en/products/gps-gnss-receiver-software/rxtools) application.
## Flight Controller Setup
### Enabling DroneCAN
In order to use the ARK G5 RTK GPS, connect it to the Pixhawk CAN bus and enable the DroneCAN driver by setting parameter [UAVCAN_ENABLE](../advanced_config/parameter_reference.md#UAVCAN_ENABLE) to `2` for dynamic node allocation (or `3` if using [DroneCAN ESCs](../dronecan/escs.md)).
步骤如下：
- In _QGroundControl_ set the parameter [UAVCAN_ENABLE](../advanced_config/parameter_reference.md#UAVCAN_ENABLE) to `2` or `3` and reboot (see [Finding/Updating Parameters](../advanced_config/parameters.md)).
- Connect ARK G5 RTK GPS CAN to the Pixhawk CAN.
Once enabled, the module will be detected on boot.
There is also CAN built-in bus termination via [CANNODE_TERM](../advanced_config/parameter_reference.md#CANNODE_TERM)
### PX4 配置
You need to set necessary [DroneCAN](index.md) parameters and define offsets if the sensor is not centred within the vehicle:
- Enable [UAVCAN_SUB_GPS](../advanced_config/parameter_reference.md#UAVCAN_SUB_GPS), [UAVCAN_SUB_MAG](../advanced_config/parameter_reference.md#UAVCAN_SUB_MAG), and [UAVCAN_SUB_BARO](../advanced_config/parameter_reference.md#UAVCAN_SUB_BARO).
- The parameters [EKF2_GPS_POS_X](../advanced_config/parameter_reference.md#EKF2_GPS_POS_X), [EKF2_GPS_POS_Y](../advanced_config/parameter_reference.md#EKF2_GPS_POS_Y) and [EKF2_GPS_POS_Z](../advanced_config/parameter_reference.md#EKF2_GPS_POS_Z) can be set to account for the offset of the ARK G5 RTK GPS from the vehicle's centre of gravity.
## LED含义
The GPS status lights are located to the right of the connectors:
- Blinking green is GPS fix
- Blinking blue is received corrections and RTK Float
- Solid blue is RTK Fixed
## 另见
- [ARK G5 RTK GPS Documentation](https://docs.arkelectron.com/gps/ark-g5-rtk-gps) (ARK Docs)

150
docs/zh/dronecan/ark_g5_rtk_heading_gps.md Normal file
View File

@@ -0,0 +1,150 @@
# ARK G5 RTK HEADING GPS
:::info
This GPS module is made in the USA and NDAA compliant.
:::
[ARK G5 RTK HEADING GPS](https://arkelectron.com/product/ark-g5-rtk-gps/) is a [DroneCAN](index.md) quad-band dual antenna [RTK GPS](../gps_compass/rtk_gps.md) that additionally provides vehicle yaw information from GPS.
The module incorporates the [Septentrio mosaic-G5 P3H Ultra-compact high-precision GPS/GNSS receiver module with heading capability](https://www.septentrio.com/en/products/gnss-receivers/gnss-receiver-modules/mosaic-G5-P3H), magnetometer, barometer, IMU, and buzzer module.
![ARK G5 RTK HEADING GPS](../../assets/hardware/gps/ark/ark_g5_rtk_gps.png)
## 购买渠道
Order this module from:
- [ARK Electronics](https://arkelectron.com/product/ark-g5-rtk-heading-gps/) (US)
## Hardware Specifications
- [DroneCAN](index.md) RTK GNSS, Magnetometer, Barometer, IMU, and Buzzer Module
- [Dronecan Firmware Updating](../dronecan/index.md#firmware-update)
- 传感器
- [Septentrio mosaic-G5 P3H Ultra-compact high-precision GPS/GNSS receiver module with heading capability](https://www.septentrio.com/en/products/gnss-receivers/gnss-receiver-modules/mosaic-G5-P3H)
- All-band all constellation GNSS receiver
- All-in-view satellite tracking: multi-constellation, quad-band GNSS module receiver
- Full raw data with positioning measurements and Galileo HAS positioning service compatibility
- Best-in-class RTK cm-level positioning accuracy
- Advanced GNSS+ algorithms
- 20Hz update rate
- [ST IIS2MDC Magnetometer](https://www.st.com/en/mems-and-sensors/iis2mdc.html)
- [Bosch BMP390 Barometer](https://www.bosch-sensortec.com/products/environmental-sensors/pressure-sensors/bmp390/)
- [Invensense ICM-42688-P 6-Axis IMU](https://invensense.tdk.com/products/motion-tracking/6-axis/icm-42688-p/)
- STM32F412VGH6 MCU
- Safety Button
- 蜂鸣器
- Two CAN Connectors (Pixhawk Connector Standard 4-pin JST GH)
- G5 "UART 2" Connector
- 4-pin JST GH
- TX, RX, PPS, GND
- G5 USB C
- Debug Connector (Pixhawk Connector Standard 6-pin JST SH)
- LED Indicators
- GPS Fix
- RTK Status
- RGB system status
- USA Built
- NDAA Compliant
- Power Requirements
- 5V
- 270mA
- 尺寸
- Without Antenna
- 48.0mm x 40.0mm x 15.4mm
- 13.0g
- With Antenna
- 48.0mm x 40.0mm x 51.0mm
- 43.5g
- Includes
- CAN Cable (Pixhawk Connector Standard 4-pin)
- Full-Frequency Helical GPS Antenna
## 硬件安装
### 布线
The ARK G5 RTK HEADING GPS is connected to the CAN bus using a [Pixhawk connector standard](https://github.com/pixhawk/Pixhawk-Standards/blob/master/DS-009%20Pixhawk%20Connector%20Standard.pdf) 4-pin JST GH cable.
For more information, refer to the [CAN Wiring](../can/index.md#wiring) instructions.
### Mounting
The recommended mounting orientation is with the connectors on the board pointing towards the **back of vehicle**.
The sensor can be mounted anywhere on the frame, but you will need to specify its position, relative to vehicle centre of gravity, during [PX4 configuration](#px4-configuration).
## Firmware Setup
The Septentrio G5 module firmware can be updated using the Septentrio [RxTools](https://www.septentrio.com/en/products/gps-gnss-receiver-software/rxtools) application.
## Flight Controller Setup
### Enabling DroneCAN
In order to use the ARK G5 RTK HEADING GPS, connect it to the Pixhawk CAN bus and enable the DroneCAN driver by setting parameter [UAVCAN_ENABLE](../advanced_config/parameter_reference.md#UAVCAN_ENABLE) to `2` for dynamic node allocation (or `3` if using [DroneCAN ESCs](../dronecan/escs.md)).
步骤如下：
- In _QGroundControl_ set the parameter [UAVCAN_ENABLE](../advanced_config/parameter_reference.md#UAVCAN_ENABLE) to `2` or `3` and reboot (see [Finding/Updating Parameters](../advanced_config/parameters.md)).
- Connect ARK G5 RTK HEADING GPS CAN to the Pixhawk CAN.
Once enabled, the module will be detected on boot.
There is also CAN built-in bus termination via [CANNODE_TERM](../advanced_config/parameter_reference.md#CANNODE_TERM)
### PX4 配置
You need to set necessary [DroneCAN](index.md) parameters and define offsets if the sensor is not centred within the vehicle:
- Enable GPS yaw fusion by setting bit 3 of [EKF2_GPS_CTRL](../advanced_config/parameter_reference.md#EKF2_GPS_CTRL) to true.
- Enable GPS blending to ensure the heading is always published by setting [SENS_GPS_MASK](../advanced_config/parameter_reference.md#SENS_GPS_MASK) to 7 (all three bits checked).
- Enable [UAVCAN_SUB_GPS](../advanced_config/parameter_reference.md#UAVCAN_SUB_GPS), [UAVCAN_SUB_MAG](../advanced_config/parameter_reference.md#UAVCAN_SUB_MAG), and [UAVCAN_SUB_BARO](../advanced_config/parameter_reference.md#UAVCAN_SUB_BARO).
- The parameters [EKF2_GPS_POS_X](../advanced_config/parameter_reference.md#EKF2_GPS_POS_X), [EKF2_GPS_POS_Y](../advanced_config/parameter_reference.md#EKF2_GPS_POS_Y) and [EKF2_GPS_POS_Z](../advanced_config/parameter_reference.md#EKF2_GPS_POS_Z) can be set to account for the offset of the ARK G5 RTK HEADING GPS from the vehicle's centre of gravity.
### Parameter references
This GPS is using ARK's private driver, the prameters below only exist on the firmware we ship the GPS with. You can set these params either in QGC or using the DroneCAN GUI Tool.
#### SEP_OFFS_YAW (float)
Heading offset angle for dual antenna GPS setups that support heading estimation.
Set this to 0 if the antennas are parallel to the forward-facing direction of the vehicle and the Rover/ANT2 antenna is in front.
The offset angle increases clockwise.
Set this to 90 if the ANT2 antenna is placed on the right side of the vehicle and the Moving Base/MAIN antenna is on the left side.
- Default: 0
- Min: -360
- Max: 360
- Unit: degree
#### SEP_OFFS_PITCH (float)
Vertical offsets can be compensated for by adjusting the Pitch offset.
Note that this can be interpreted as the "roll" angle in case the antennas are aligned along the perpendicular axis. This occurs in situations where the two antenna ARPs may not be exactly at the same height in the vehicle reference frame. Since pitch is defined as the right-handed rotation about the vehicle Y axis, a situation where the main antenna is mounted lower than the aux antenna (assuming the default antenna setup) will result in a positive pitch.
- Default: 0
- Min: -90
- Max: 90
- Unit: degree
#### SEP_OUT_RATE (enum)
Configures the output rate for GNSS data messages.
- -1: OnChange (Default)
- 50: 50 ms
- 100: 100 ms
- 200: 200 ms
- 500: 500 ms
## LED含义
The GPS status lights are located to the right of the connectors:
- Blinking green is GPS fix
- Blinking blue is received corrections and RTK Float
- Solid blue is RTK Fixed
## 另见
- [ARK G5 RTK HEADING GPS Documentation](https://docs.arkelectron.com/gps/ark-g5-rtk-gps) (ARK Docs)

2
docs/zh/dronecan/index.md
View File

@@ -27,6 +27,8 @@ Connecting peripherals over DroneCAN has many benefits:
- Wiring is less complicated as you can have a single bus for connecting all your ESCs and other DroneCAN peripherals.
- Setup is easier as you configure ESC numbering by manually spinning each motor.
- It allows users to configure and update the firmware of all CAN-connected devices centrally through PX4.
- PX4 automatically tracks device information (vendor, model, versions, serial numbers) for maintenance and fleet management.
See [Asset Tracking](../debug/asset_tracking.md).
## 支持的硬件

2
docs/zh/features_fw/gain_compression.md
View File

@@ -1,6 +1,6 @@
# Gain compression
<Badge type="tip" text="main (planned for: PX4 v1.17)" />
<Badge type="tip" text="PX4 v1.17" />
Automatic gain compression reduces the gains of the angular-rate PID whenever oscillations are detected.
It monitors the angular-rate controller output through a band-pass filter to identify these oscillations.

2
docs/zh/flight_controller/micoair743-lite.md
View File

@@ -1,6 +1,6 @@
# MicoAir743-Lite
<Badge type="tip" text="main (planned for: PX4 v1.17)" />
<Badge type="tip" text="PX4 v1.17" />
:::warning
PX4 does not manufacture this (or any) autopilot.

2
docs/zh/flight_controller/radiolink_pix6.md
View File

@@ -1,6 +1,6 @@
# RadiolinkPIX6 Flight Controller
<Badge type="tip" text="main (planned for: PX4 v1.17)" />
<Badge type="tip" text="PX4 v1.17" />
:::warning
PX4 does not manufacture this (or any) autopilot.

4
docs/zh/flight_controller/x-mav_ap-h743r1.md
View File

@@ -1,6 +1,6 @@
# AP-H743-R1
# AP-H743-R1 Flight Controller
<Badge type="tip" text="main (planned for: PX4 v1.17)" />
<Badge type="tip" text="PX4 v1.17" />
:::warning
PX4 does not manufacture this (or any) autopilot.

77
docs/zh/flight_modes_fw/hold.md
View File

@@ -2,11 +2,14 @@
<img src="../../assets/site/position_fixed.svg" title="Position fix required (e.g. GPS)" width="30px" />
The _Hold_ flight mode causes the vehicle to loiter (circle) around its current GPS position and maintain its current altitude.
The _Hold_ flight mode causes the vehicle to loiter around its current GPS position and maintain its current altitude.
The mode supports a [number of distinct loiter modes](#loiter-modes), which are triggered using different QGC controls or MAVLink commands.
These allow loitering with circular and figure 8 flight paths.
:::tip
_Hold mode_ can be used to pause a mission or to help you regain control of a vehicle in an emergency.
It is usually activated with a pre-programmed switch.
It is usually activated with a pre-programmed RC switch.
:::
::: info
@@ -24,24 +27,80 @@ It is usually activated with a pre-programmed switch.
:::
## 技术总结
## Loiter modes
The aircraft circles around the GPS hold position at the current altitude.
The vehicle will first ascend to [NAV_MIN_LTR_ALT](#NAV_MIN_LTR_ALT) if the mode is engaged below this altitude.
### Default Loiter
RC stick movement is ignored.
The aircraft circles around the position at which the mode was triggered and maintain its current altitude.
The loiter radius is set by the parameter [NAV_LOITER_RAD](#NAV_LOITER_RAD).
Note that if the vehicle altitude is below [NAV_MIN_LTR_ALT](#NAV_MIN_LTR_ALT), it will ascend to that minimum altitude before circling.
### 参数
The default loiter mode is entered when you switch to Hold mode without explicitly specifying any loiter behaviour.
For example, if you switch to Hold mode using an RC switch, select **Hold** on the QGC flight mode selector, or activate the mode using the MAVLink [MAV_CMD_DO_SET_MODE](https://mavlink.io/en/messages/common.html#MAV_CMD_DO_SET_MODE) command.
### Orbit Loiter Mode
<Badge type="tip" text="PX4 v1.12" />
The aircraft travels towards a _specified_ orbit center position, then circles it with a given direction and radius.
This behaviour can be accessed in QGroundControl by clicking on the map in Fly view, selecting **Orbit at Location**, and configuring the radius.
The behavior can be triggered using the MAVLink [MAV_CMD_DO_ORBIT](https://mavlink.io/en/messages/common.html#MAV_CMD_DO_ORBIT) command.
Note that PX4 respects the specified centre point (`param5`, `param6`, `param7`), and the radius and direction (`param1`).
PX4 ignores `param3` (Yaw behaviour) and `param4` (Orbits).
The value of `param2` (velocity) is also ignored, but the speed can be controlled using the [MAV_CMD_DO_CHANGE_SPEED](https://mavlink.io/en/messages/common.html#MAV_CMD_DO_CHANGE_SPEED) command (constrained between `FW_AIRSPD_MAX` and `FW_AIRSPD_MIN`).
PX4 outputs orbit status using the [ORBIT_EXECUTION_STATUS](https://mavlink.io/en/messages/common.html#ORBIT_EXECUTION_STATUS) message.
### Figure 8 Loiter Mode
<Badge type="tip" text="PX4 v1.15" /> <Badge type="warning" text="Experimental" />
The aircraft flys towards the closest point on a specified figure 8 path and then follows it.
The path is defined by the figure 8 centre position, orientation, and radius of two circles.
The feature is experimental, and is not present in PX4 firmware by default (on most flight controller boards).
It can be included by setting the `CONFIG_FIGURE_OF_EIGHT` key in the [PX4 board configuration](../hardware/porting_guide_config.md#px4-board-configuration-kconfig) for your board and rebuilding.
For example, this is enabled on the [default.px4board](https://github.com/PX4/PX4-Autopilot/blob/main/boards/auterion/fmu-v6s/default.px4board#L46) file for the `auterion/fmu-v6s` board.
The behavior can be triggered using the MAVLink [MAV_CMD_DO_FIGURE_EIGHT](https://mavlink.io/en/messages/common.html#MAV_CMD_DO_FIGURE_EIGHT) command (PX4 respects all the parameters).
PX4 outputs the figure 8 status using the [FIGURE_EIGHT_EXECUTION_STATUS](https://mavlink.io/en/messages/common.html#FIGURE_EIGHT_EXECUTION_STATUS) message.
:::info
Figure 8 loitering is not currently supported by QGC: [QGC#12778: Need Support Figure of eight (8 figure) loitering by QGC](https://github.com/mavlink/qgroundcontrol/issues/12778).
:::
Figure 8 loitering is also available in the simulator.
You can test it in [Gazebo](../sim_gazebo_gz/index.md) using a fixed wing frame:
```sh
make px4_sitl gz_rc_cessna
```
## 参数
Hold mode behaviour can be configured using the parameters below.
| 参数 | 描述 |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
| [NAV_LOITER_RAD](../advanced_config/parameter_reference.md#NAV_LOITER_RAD) | The radius of the loiter circle. |
| <a id="NAV_LOITER_RAD"></a>[NAV_LOITER_RAD](../advanced_config/parameter_reference.md#NAV_LOITER_RAD) | The radius of the loiter circle. |
| <a id="NAV_MIN_LTR_ALT"></a>[NAV_MIN_LTR_ALT](../advanced_config/parameter_reference.md#NAV_MIN_LTR_ALT) | Minimum height for loiter mode (vehicle will ascend to this altitude if mode is engaged at a lower altitude). |
## MAVLink Commands
The following commands are relevant to this mode:
- [MAV_CMD_DO_ORBIT](https://mavlink.io/en/messages/common.html#MAV_CMD_DO_ORBIT) - Switch to Hold mode and start the specified [Orbit loiter](#orbit-loiter-mode).
Params 2 (velocity), 3 (yaw), 4 (orbits) are ignored.
[ORBIT_EXECUTION_STATUS](https://mavlink.io/en/messages/common.html#ORBIT_EXECUTION_STATUS) is emitted.
- [MAV_CMD_DO_FIGURE_EIGHT](https://mavlink.io/en/messages/common.html#MAV_CMD_DO_FIGURE_EIGHT) - Switch to Hold mode and start the specified [Figure 8 loiter](#figure-8-loiter-mode).
All params are respected.
[FIGURE_EIGHT_EXECUTION_STATUS](https://mavlink.io/en/messages/common.html#FIGURE_EIGHT_EXECUTION_STATUS) is emitted.
Note, other commands may be supported.
## 另见
[Hold Mode (MC)](../flight_modes_mc/hold.md)
- [Hold Mode (MC)](../flight_modes_mc/hold.md)
<!-- this maps to AUTO_LOITER in flight mode state machine -->

4
docs/zh/flight_modes_fw/takeoff.md
View File

@@ -49,8 +49,8 @@ If the local position is invalid or becomes invalid while executing the takeoff,
::: info
- Takeoff towards a target position was added in <Badge type="tip" text="main (planned for: PX4 v1.17)" />.
- Holding wings level and ascending to clearance attitude when local position is invalid during takeoff was added in <Badge type="tip" text="main (planned for: PX4 v1.17)" />.
- Takeoff towards a target position was added in <Badge type="tip" text="PX4 v1.17" />.
- Holding wings level and ascending to clearance attitude when local position is invalid during takeoff was added in <Badge type="tip" text="PX4 v1.17" />.
- QGroundControl does not support `MAV_CMD_NAV_TAKEOFF` (at time of writing).
:::

88
docs/zh/gps_compass/rtk_gps.md
View File

@@ -20,52 +20,59 @@ The RTK compatible devices below that are expected to work with PX4 (it omits di
The table indicates devices that also output yaw, and that can provide yaw when two on-vehicle units are used.
It also highlights devices that connect via the CAN bus, and those which support PPK (Post-Processing Kinematic).
| 设备 | GPS | 罗盘 | [DroneCAN](../dronecan/index.md) | [GPS Yaw](#configuring-gps-as-yaw-heading-source) | PPK |
| :------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------: | :-------------------------: | :------------------------------: | :-----------------------------------------------: | :-------------------------: |
| [ARK RTK GPS](../dronecan/ark_rtk_gps.md) | F9P | BMM150 | &check; | [Dual F9P][DualF9P] | |
| [ARK RTK GPS L1 L5](../dronecan/ark_rtk_gps_l1_l2.md) | F9P | BMM150 | &check; | | |
| [ARK MOSAIC-X5 RTK GPS](../dronecan/ark_mosaic__rtk_gps.md) | Mosaic-X5 | IIS2MDC | &check; | [Septentrio Dual Antenna][SeptDualAnt] | |
| [ARK X20 RTK GPS](../dronecan/ark_x20_rtk_gps.md) | X20P | BMP390 | &check; | | |
| [CUAV C-RTK GPS](../gps_compass/rtk_gps_cuav_c-rtk.md) | M8P/M8N | &check; | | | |
| [CUAV C-RTK2](../gps_compass/rtk_gps_cuav_c-rtk2.md) | F9P | &check; | | [Dual F9P][DualF9P] | |
| [CUAV C-RTK 9Ps GPS](../gps_compass/rtk_gps_cuav_c-rtk-9ps.md) | F9P | RM3100 | | [Dual F9P][DualF9P] | |
| [CUAV C-RTK2 PPK/RTK GNSS](../gps_compass/rtk_gps_cuav_c-rtk.md) | F9P | RM3100 | | | &check; |
| [CubePilot Here+ RTK GPS](../gps_compass/rtk_gps_hex_hereplus.md) | M8P | HMC5983 | | | |
| [CubePilot Here3 CAN GNSS GPS (M8N)](https://www.cubepilot.org/#/here/here3) | M8P | ICM20948 | &check; | | |
| [Drotek SIRIUS RTK GNSS ROVER (F9P)](https://store-drotek.com/911-sirius-rtk-gnss-rover-f9p.html) | F9P | RM3100 | | [Dual F9P][DualF9P] | |
| [DATAGNSS NANO HRTK Receiver](../gps_compass/rtk_gps_datagnss_nano_hrtk.md) | [D10P](https://docs.datagnss.com/gnss/gnss_module/D10P_RTK) | IST8310 | | ✘ | |
| [DATAGNSS GEM1305 RTK Receiver](../gps_compass/rtk_gps_gem1305.md) | TAU951M | IST8310 | | ✘ | |
| [Femtones MINI2 Receiver](../gps_compass/rtk_gps_fem_mini2.md) | FB672, FB6A0 | &check; | | | |
| [Freefly RTK GPS](../gps_compass/rtk_gps_freefly.md) | F9P | IST8310 | | | |
| [Holybro H-RTK ZED-F9P RTK Rover (DroneCAN variant)](../dronecan/holybro_h_rtk_zed_f9p_gps.md) | F9P | RM3100 | &check; | [Dual F9P][DualF9P] | |
| [Holybro H-RTK ZED-F9P RTK Rover](https://holybro.com/collections/h-rtk-gps/products/h-rtk-zed-f9p-rover) | F9P | RM3100 | | [Dual F9P][DualF9P] | |
| [Holybro H-RTK F9P Ultralight](https://holybro.com/products/h-rtk-f9p-ultralight) | F9P | IST8310 | | [Dual F9P][DualF9P] | |
| [Holybro H-RTK F9P Helical or Base](../gps_compass/rtk_gps_holybro_h-rtk-f9p.md) | F9P | IST8310 | | [Dual F9P][DualF9P] | |
| [Holybro DroneCAN H-RTK F9P Helical](https://holybro.com/products/dronecan-h-rtk-f9p-helical) | F9P | BMM150 | &check; | [Dual F9P][DualF9P] | |
| [Holybro H-RTK F9P Rover Lite](../gps_compass/rtk_gps_holybro_h-rtk-f9p.md) | F9P | IST8310 | | | |
| [Holybro DroneCAN H-RTK F9P Rover](https://holybro.com/products/dronecan-h-rtk-f9p-rover) | F9P | BMM150 | | [Dual F9P][DualF9P] | |
| [Holybro H-RTK M8P GNSS](../gps_compass/rtk_gps_holybro_h-rtk-m8p.md) | M8P | IST8310 | | | |
| [Holybro H-RTK Unicore UM982 GPS](../gps_compass/rtk_gps_holybro_unicore_um982.md) | UM982 | IST8310 | | [Unicore Dual Antenna][UnicoreDualAnt] | |
| [LOCOSYS Hawk R1](../gps_compass/rtk_gps_locosys_r1.md) | MC-1612-V2b | | | | |
| [LOCOSYS Hawk R2](../gps_compass/rtk_gps_locosys_r2.md) | MC-1612-V2b | IST8310 | | | |
| [mRo u-blox ZED-F9 RTK L1/L2 GPS](https://store.mrobotics.io/product-p/m10020d.htm) | F9P | &check; | | [Dual F9P][DualF9P] | |
| [Navisys L1/L2 ZED-F9P RTK - Base only](https://www.navisys.com.tw/productdetail?name=GR901&class=RTK) | F9P | | | | |
| [RaccoonLab L1/L2 ZED-F9P][RaccoonLab L1/L2 ZED-F9P] | F9P | RM3100 | &check; | | |
| [RaccoonLab L1/L2 ZED-F9P with external antenna][RaccnLabL1L2ZED-F9P ext_ant] | F9P | RM3100 | &check; | | |
| [Septentrio AsteRx-m3 Pro](../gps_compass/septentrio_asterx-rib.md) | AsteRx | &check; | | [Septentrio Dual Antenna][SeptDualAnt] | &check; |
| [Septentrio mosaic-go](../gps_compass/septentrio_mosaic-go.md) | mosaic X5 / mosaic H | &check; | | [Septentrio Dual Antenna][SeptDualAnt] | &check; |
| [SIRIUS RTK GNSS ROVER (F9P)](https://store-drotek.com/911-sirius-rtk-gnss-rover-f9p.html) | F9P | &check; | | [Dual F9P][DualF9P] | |
| [SparkFun GPS-RTK2 Board - ZED-F9P](https://www.sparkfun.com/products/15136) | F9P | &check; | | [Dual F9P][DualF9P] | |
| [Trimble MB-Two](../gps_compass/rtk_gps_trimble_mb_two.md) | F9P | &check; | | &check; | |
| 设备 | GPS | 罗盘 | [DroneCAN] | [GPS Yaw] | PPK |
| :------------------------------------------------------------------------------------------------------------------- | :------------------: | :-------------------------: | :-------------------------: | :---------------------------------: | :-------------------------: |
| [ARK G5 RTK GPS](../dronecan/ark_g5_rtk_gps.md) | [mosaic-G5 P3] | IIS2MDC | &check; | | |
| [ARK G5 RTK HEADING GPS](../dronecan/ark_g5_rtk_heading_gps.md) | [mosaic-G5 P3H] | IIS2MDC | &check; | [Heading Capability][mosaic-G5 P3H] | |
| [ARK RTK GPS](../dronecan/ark_rtk_gps.md) | F9P | BMM150 | &check; | [Dual F9P] | |
| [ARK RTK GPS L1 L5](../dronecan/ark_rtk_gps_l1_l2.md) | F9P | BMM150 | &check; | | |
| [ARK MOSAIC-X5 RTK GPS](../dronecan/ark_mosaic__rtk_gps.md) | Mosaic-X5 | IIS2MDC | &check; | [Septentrio Dual Antenna] | |
| [ARK X20 RTK GPS](../dronecan/ark_x20_rtk_gps.md) | X20P | IIS2MDC | &check; | | |
| [CUAV C-RTK GPS](../gps_compass/rtk_gps_cuav_c-rtk.md) | M8P/M8N | &check; | | | |
| [CUAV C-RTK2](../gps_compass/rtk_gps_cuav_c-rtk2.md) | F9P | &check; | | [Dual F9P] | |
| [CUAV C-RTK 9Ps GPS](../gps_compass/rtk_gps_cuav_c-rtk-9ps.md) | F9P | RM3100 | | [Dual F9P] | |
| [CUAV C-RTK2 PPK/RTK GNSS](../gps_compass/rtk_gps_cuav_c-rtk.md) | F9P | RM3100 | | | &check; |
| [CubePilot Here+ RTK GPS](../gps_compass/rtk_gps_hex_hereplus.md) | M8P | HMC5983 | | | |
| [CubePilot Here3 CAN GNSS GPS (M8N)](https://www.cubepilot.org/#/here/here3) | M8P | ICM20948 | &check; | | |
| [Drotek SIRIUS RTK GNSS ROVER (F9P)](https://store-drotek.com/911-sirius-rtk-gnss-rover-f9p.html) | F9P | RM3100 | | [Dual F9P] | |
| [DATAGNSS NANO HRTK Receiver](../gps_compass/rtk_gps_datagnss_nano_hrtk.md) | [D10P] | IST8310 | | ✘ | |
| [DATAGNSS GEM1305 RTK Receiver](../gps_compass/rtk_gps_gem1305.md) | TAU951M | IST8310 | | ✘ | |
| [Femtones MINI2 Receiver](../gps_compass/rtk_gps_fem_mini2.md) | FB672, FB6A0 | &check; | | | |
| [Freefly RTK GPS](../gps_compass/rtk_gps_freefly.md) | F9P | IST8310 | | | |
| [Holybro H-RTK ZED-F9P RTK Rover (DroneCAN variant)](../dronecan/holybro_h_rtk_zed_f9p_gps.md) | F9P | RM3100 | &check; | [Dual F9P] | |
| [Holybro H-RTK ZED-F9P RTK Rover](https://holybro.com/collections/h-rtk-gps/products/h-rtk-zed-f9p-rover) | F9P | RM3100 | | [Dual F9P] | |
| [Holybro H-RTK F9P Ultralight](https://holybro.com/products/h-rtk-f9p-ultralight) | F9P | IST8310 | | [Dual F9P] | |
| [Holybro H-RTK F9P Helical or Base](../gps_compass/rtk_gps_holybro_h-rtk-f9p.md) | F9P | IST8310 | | [Dual F9P] | |
| [Holybro DroneCAN H-RTK F9P Helical](https://holybro.com/products/dronecan-h-rtk-f9p-helical) | F9P | BMM150 | &check; | [Dual F9P] | |
| [Holybro H-RTK F9P Rover Lite](../gps_compass/rtk_gps_holybro_h-rtk-f9p.md) | F9P | IST8310 | | | |
| [Holybro DroneCAN H-RTK F9P Rover](https://holybro.com/products/dronecan-h-rtk-f9p-rover) | F9P | BMM150 | | [Dual F9P] | |
| [Holybro H-RTK M8P GNSS](../gps_compass/rtk_gps_holybro_h-rtk-m8p.md) | M8P | IST8310 | | | |
| [Holybro H-RTK Unicore UM982 GPS](../gps_compass/rtk_gps_holybro_unicore_um982.md) | UM982 | IST8310 | | [Unicore Dual Antenna] | |
| [LOCOSYS Hawk R1](../gps_compass/rtk_gps_locosys_r1.md) | MC-1612-V2b | | | | |
| [LOCOSYS Hawk R2](../gps_compass/rtk_gps_locosys_r2.md) | MC-1612-V2b | IST8310 | | | |
| [mRo u-blox ZED-F9 RTK L1/L2 GPS](https://store.mrobotics.io/product-p/m10020d.htm) | F9P | &check; | | [Dual F9P] | |
| [Navisys L1/L2 ZED-F9P RTK - Base only](https://www.navisys.com.tw/productdetail?name=GR901&class=RTK) | F9P | | | | |
| [RaccoonLab L1/L2 ZED-F9P][RaccoonLab L1/L2 ZED-F9P] | F9P | RM3100 | &check; | | |
| [RaccoonLab L1/L2 ZED-F9P with external antenna][RaccnLabL1L2ZED-F9P ext_ant] | F9P | RM3100 | &check; | | |
| [Septentrio AsteRx-m3 Pro](../gps_compass/septentrio_asterx-rib.md) | AsteRx | &check; | | [Septentrio Dual Antenna] | &check; |
| [Septentrio mosaic-go](../gps_compass/septentrio_mosaic-go.md) | mosaic X5 / mosaic H | &check; | | [Septentrio Dual Antenna] | &check; |
| [SIRIUS RTK GNSS ROVER (F9P)](https://store-drotek.com/911-sirius-rtk-gnss-rover-f9p.html) | F9P | &check; | | [Dual F9P] | |
| [SparkFun GPS-RTK2 Board - ZED-F9P](https://www.sparkfun.com/products/15136) | F9P | &check; | | [Dual F9P] | |
| [Trimble MB-Two](../gps_compass/rtk_gps_trimble_mb_two.md) | F9P | &check; | | &check; | |
<!-- links used in above table -->
[RaccnLabL1L2ZED-F9P ext_ant]: https://docs.raccoonlab.co/guide/gps_mag_baro/gnss_external_antenna_f9p_v320.html
[RaccoonLab L1/L2 ZED-F9P]: https://docs.raccoonlab.co/guide/gps_mag_baro/gps_l1_l2_zed_f9p.html
[DualF9P]: ../gps_compass/u-blox_f9p_heading.md
[SeptDualAnt]: ../gps_compass/septentrio.md#gnss-based-heading
[UnicoreDualAnt]: ../gps_compass/rtk_gps_holybro_unicore_um982.md#enable-gps-heading-yaw
[Dual F9P]: ../gps_compass/u-blox_f9p_heading.md
[Septentrio Dual Antenna]: ../gps_compass/septentrio.md#gnss-based-heading
[Unicore Dual Antenna]: ../gps_compass/rtk_gps_holybro_unicore_um982.md#enable-gps-heading-yaw
[DATAGNSS GEM1305 RTK]: ../gps_compass/rtk_gps_gem1305.md
[DroneCAN]: ../dronecan/index.md
[GPS Yaw]: #configuring-gps-as-yaw-heading-source
[mosaic-G5 P3]: https://www.septentrio.com/en/products/gnss-receivers/gnss-receiver-modules/mosaic-G5-P3
[mosaic-G5 P3H]: https://www.septentrio.com/en/products/gnss-receivers/gnss-receiver-modules/mosaic-G5-P3H
[D10P]: https://docs.datagnss.com/gnss/gnss_module/D10P_RTK
备注：
@@ -145,6 +152,7 @@ The RTK GPS connection is essentially plug and play:
![survey-in](../../assets/qgc/setup/rtk/qgc_rtk_survey-in.png)
4. 测量完成：
- The RTK GPS icon changes to white and _QGroundControl_ starts to stream position data to the vehicle:
![RTK streaming](../../assets/qgc/setup/rtk/qgc_rtk_streaming.png)

6
docs/zh/hardware/porting_guide.md
View File

@@ -49,7 +49,7 @@ PX4 由两个主要层组成： 基于主机操作系统（NuttX、Linux 或任
## RC UART 接线建议
It is generally recommended to connect RC via separate RX and TX pins to the microcontroller. If however RX and TX are connected together, the UART has to be put into singlewire mode to prevent any contention. This is done via board config and manifest files. One example is <a href="https://github.com/PX4/Firmware/blob/master/src/drivers/boards/px4fmu-v5/manifest.c">px4fmu-v5</a>.
通常建议通过独立的RX和TX引脚将RC连接至微控制器。但若RX和TX引脚连接在一起，则必须将UART置于单线模式以避免竞争冲突。此操作需通过板级配置文件和清单文件实现。示例可参考<a href="https://github.com/PX4/Firmware/blob/master/src/drivers/boards/px4fmu-v5/manifest.c">px4fmu-v5</a>。
如果 RX 和 TX 连在了一起，那么 UART 需要设置为单线模式以防止出现争用。
这可以用过对飞控板的配置文件和 manifest 文件进行更改来实现。
一个例子是 [px4fmu-v5](https://github.com/PX4/PX4-Autopilot/blob/main/boards/px4/fmu-v5/src/manifest.c)。 <!-- NEED px4_version -->
@@ -68,7 +68,7 @@ PX4项目支持并维护[FMU标准参考硬件](../hardware/reference_design.md)
- [飞行测试](../test_and_ci/test_flights.md)
我们鼓励电路板制造商致力于实现与[FMU规范](https://pixhawk.org/)的完全兼容。
We encourage board manufacturers to aim for full compatibility with the <a href="https://pixhawk.org/">FMU spec</a>. With full compatibility you benefit from the ongoing day-to-day development of PX4, but have none of the maintenance costs that come from supporting deviations from the specification.
我们鼓励电路板制造商致力于实现与<a href="https://pixhawk.org/">FMU规范</a>的完全兼容。通过完全兼容，您既能受益于PX4持续的日常开发成果，又无需承担因支持偏离规范而产生的维护成本。
:::tip
制造商在偏离规格时应仔细考虑维护成本（制造商的成本与偏离程度成正比）。
@@ -76,7 +76,7 @@ We encourage board manufacturers to aim for full compatibility with the <a href=
我们欢迎任何个人或公司提交其移植版本，将其纳入我们支持的硬件范围。前提是他们愿意遵守我们的[行为准则](https://github.com/PX4/PX4-Autopilot/blob/main/CODE_OF_CONDUCT.md)，并与开发团队协作，为用户提供安全且令人满意的PX4体验。
如果你想让你的飞控板被 PX4 项目正式支持：
值得注意的是，PX4开发团队有责任发布安全的软件。因此，我们要求所有主板制造商投入必要资源，确保其移植版本保持最新且处于可运行状态。
如果你想让你的飞控板被 PX4 项目正式支持：

6
docs/zh/middleware/uxrce_dds.md
View File

@@ -332,9 +332,11 @@ The configuration can be done using the [UXRCE-DDS parameters](../advanced_confi
- [UXRCE_DDS_SYNCT](../advanced_config/parameter_reference.md#UXRCE_DDS_SYNCT): Bridge time synchronization enable.
The uXRCE-DDS client module can synchronize the timestamp of the messages exchanged over the bridge.
This is the default configuration. In certain situations, for example during [simulations](../ros2/user_guide.md#ros-gazebo-and-px4-time-synchronization), this feature may be disabled.
- <Badge type="tip" text="PX4 v1.17" /> [`UXRCE_DDS_NS_IDX`](../advanced_config/parameter_reference.md#UXRCE_DDS_NS_IDX): Index-based namespace definition
- [UXRCE_DDS_NS_IDX](../advanced_config/parameter_reference.md#UXRCE_DDS_NS_IDX) <Badge type="tip" text="PX4 v1.17" />: Index-based namespace definition.
Setting this parameter to any value other than `-1` creates a namespace with the prefix `uav_` and the specified value, e.g. `uav_0`, `uav_1`, etc.
See [namespace](#customizing-the-namespace) for methods to define richer or arbitrary namespaces.
- [`UXRCE_DDS_FLCTRL`](../advanced_config/parameter_reference.md#UXRCE_DDS_FLCTRL) <Badge type="tip" text="PX4 main" />: Serial port hardware flow control enable.
To use hardware flow control, a custom MicroXRCE Agent needs to be adopted. Please refer to [this PR](https://github.com/eProsima/Micro-XRCE-DDS-Agent/pull/407) for the required changes, cherry-pick them on top of the [agent version](#build-run-within-ros-2-workspace) you need to use and then run the agent with the additional `--flow-control` option.
:::info
Many ports are already have a default configuration.
@@ -439,7 +441,7 @@ PX4_UXRCE_DDS_NS=uav_1 make px4_sitl gz_x500
:::
- A simple index-based namespace can be applied by setting the parameter [`UXRCE_DDS_NS_IDX`](../advanced_config/parameter_reference.md#UXRCE_DDS_NS_IDX) to a value between 0 and 9999.
- A simple index-based namespace can be applied by setting the parameter [`UXRCE_DDS_NS_IDX`](../advanced_config/parameter_reference.md#UXRCE_DDS_NS_IDX) <Badge type="tip" text="PX4 v1.17" /> to a value between 0 and 9999.
This will generate a namespace such as `/uav_0`, `/uav_1`, and so on.
This technique is ideal if vehicles must be persistently associated with namespaces because their clients are automatically started through PX4.

21
docs/zh/neural_networks/index.md Normal file
View File

@@ -0,0 +1,21 @@
# Neural Network Control
PX4 supports the following mechanisms for using neural networks for multirotor control:
- [MC Neural Networks Control](../neural_networks/mc_neural_network_control.md)<Badge type="warning" text="Experimental" /> — A generic neural network module that you can modify to use different underlying neural network and training models and compile into the firmware.
- [RAPTOR: A Neural Network Module for Adaptive Quadrotor Control](../neural_networks/raptor.md)<Badge type="warning" text="Experimental" /> — An adaptive RL NN module that works well with different Quad configurations without additional training.
Generally you will select the former if you wish to experiment with custom neural network architectures and train them using PyTorch or TensorFlow, and the latter if you want to use a pre-trained neural-network controller that works out-of-the-box (without training for your particular platform) or if you train your own policies using [RLtools](https://rl.tools).
Note that both modules are experimental and provided for experimentation.
The table below provides more detail on the differences.
| Use Case | [`mc_raptor`](../neural_networks/raptor.md) | [`mc_nn_control`](../neural_networks/mc_neural_network_control.md) |
| ---------------------------------------------------------------- | ------------------------------------------- | ------------------------------------------------------------------ |
| Pre-trained policy that adapts to any quadrotor without training | ✓ RAPTOR | ✘ |
| Train policy in PyTorch/TF | ✘ | ✓ TF Lite |
| Train policy in RLtools | &check; | ✘ |
| Use manual control (remote) with NN policy | ✘ GPS/MoCap | ✓ Manual attitude commands |
| Load policy checkpoints from SD card | ✓ Upload via MAVLink FTP | ✘ Compiled into firmware |
| Offboard setpoints | ✓ MAVLink | ✘ |
| Internal Trajectory Generator | ✓ (Position, Lissajous) | ✘ |

119
docs/zh/neural_networks/mc_neural_network_control.md Normal file
View File

@@ -0,0 +1,119 @@
# MC Neural Networks Control
<Badge type="tip" text="PX4 v1.17" /> <Badge type="warning" text="Experimental" />
:::warning
This is an experimental module.
Use at your own risk.
:::
The Multicopter Neural Network (NN) module ([mc_nn_control](../modules/modules_controller.md#mc-nn-control)) is an example module that allows you to experiment with using a pre-trained neural network on PX4.
It might be used, for example, to experiment with controllers for non-traditional drone morphologies, computer vision tasks, and so on.
The module integrates a pre-trained neural network based on the [TensorFlow Lite Micro (TFLM)](./tflm.md) module.
The module is trained for the [X500 V2](../frames_multicopter/holybro_x500v2_pixhawk6c.md) multicopter frame.
While the controller is fairly robust, and might work on other platforms, we recommend [Training your own Network](#training-your-own-network) if you use a different vehicle.
Note that after training the network you will need to update and rebuild PX4.
TLFM is a mature inference library intended for use on embedded devices.
It has support for several architectures, so there is a high likelihood that you can build it for the board you want to use.
If not, there are other possible NN frameworks, such as [Eigen](https://eigen.tuxfamily.org/index.php?title=Main_Page) and [Executorch](https://pytorch.org/executorch-overview).
This document explains how you can include the module in your PX4 build, and provides a broad overview of how it works.
The other documents in the section provide more information about the integration, allowing you to replace the NN with a version trained on different data, or even to replace the TLFM library altogether.
If you are looking for more resources to learn about the module, a website has been created with links to a youtube video and a workshop paper. A full master's thesis will be added later. [A Neural Network Mode for PX4 on Embedded Flight Controllers](https://ntnu-arl.github.io/px4-nns/).
## Neural Network PX4 Firmware
:::warning
This module requires Ubuntu 24.04 or newer (it is not supported in Ubuntu 22.04).
:::
The module has been tested on a number of configurations, which can be build locally using the commands:
```sh
make px4_sitl_neural
```
```sh
make px4_fmu-v6c_neural
```
```sh
make mro_pixracerpro_neural
```
You can add the module to other board configurations by modifying their `default.px4board file` configuration to include these lines:
```sh
CONFIG_LIB_TFLM=y
CONFIG_MODULES_MC_NN_CONTROL=y
```
:::tip
The `mc_nn_control` module takes up roughly 50KB, and many of the `default.px4board file` are already close to filling all the flash on their boards. To make room for the neural control module you can remove the include statements for other modules, such as FW, rover, VTOL and UUV.
:::
## Example Module Overview
The example module replaces the entire controller structure as well as the control allocator, as shown in the diagram below:
![neural_control](../../assets/advanced/neural_control.png)
In the [controller diagram](../flight_stack/controller_diagrams.md) you can see the [uORB message](../middleware/uorb.md) flow.
We hook into this flow by subscribing to messages at particular points, using our neural network to calculate outputs, and then publishing them into the next point in the flow.
We also need to stop the module publishing the topic to be replaced, which is covered in [Neural Network Module: System Integration](nn_module_utilities.md)
### Input
The input can be changed to whatever you want.
Set up the input you want to use during training and then provide the same input in PX4.
In the Neural Control module the input is an array of 15 numbers, and consists of these values in this order:
- [3] Local position error. (goal position - current position)
- [6] The first 2 rows of a 3 dimensional rotation matrix.
- [3] Linear velocity
- [3] Angular velocity
All the input values are collected from uORB topics and transformed into the correct representation in the `PopulateInputTensor()` function.
PX4 uses the NED frame representation, while the Aerial Gym Simulator, in which the NN was trained, uses the ENU representation.
Therefore two rotation matrices are created in the function and all the inputs are transformed from the NED representation to the ENU one.
![ENU-NED](../../assets/advanced/ENU-NED.png)
ENU and NED are just rotation representations, the translational difference is only there so both can be seen in the same figure.
### 输出
The output consists of 4 values, the motor forces, one for each motor.
These are transformed in the `RescaleActions()` function.
This is done because PX4 expects normalized motor commands while the Aerial Gym Simulator uses physical values.
So the output from the network needs to be normalized before they can be sent to the motors in PX4.
The commands are published to the [ActuatorMotors](../msg_docs/ActuatorMotors.md) topic.
The publishing is handled in `PublishOutput(float* command_actions)` function.
:::tip
If the neural control mode is too aggressive or unresponsive the [MC_NN_THRST_COEF](../advanced_config/parameter_reference.md#MC_NN_THRST_COEF) parameter can be tuned.
Decrease it for more thrust.
:::
## Training your own Network
The network is currently trained for the [X500 V2](../frames_multicopter/holybro_x500v2_pixhawk6c.md).
But the controller is somewhat robust, so it could work directly on other platforms, but performing system identification and training a new network is recommended.
Since the Aerial Gym Simulator is open-source you can download it and train your own networks as long as you have access to an NVIDIA GPU.
If you want to train a control network optimized for your platform you can follow the instructions in the [Aerial Gym Documentation](https://ntnu-arl.github.io/aerial_gym_simulator/9_sim2real/).
You should do one system identification flight for this and get an approximate inertia matrix for your platform.
On the `sys-id` flight you need ESC telemetry, you can read more about that in [DSHOT](../peripherals/dshot.md).
Then do the following steps:
- Do a hover flight
- Read of the logs what RPM is required for the drone to hover.
- Use the weight of each motor, length of the motor arms, total weight of the platform with battery to calculate an approximate inertia matrix for the platform.
- Insert these values into the Aerial Gym configuration and train your network.
- Convert the network as explained in [TFLM](tflm.md).

86
docs/zh/neural_networks/nn_module_utilities.md Normal file
View File

@@ -0,0 +1,86 @@
# Neural Network Module: System Integration
The neural control module ([mc_nn_control](../modules/modules_controller.md#mc-nn-control)) implements an end-to-end controller utilizing neural networks.
The parts of the module directly concerned with generating the code for the trained neural network and integrating it into the module are covered in [TensorFlow Lite Micro (TFLM)](./tflm.md).
This page covers the changes that were made to integrate the module into PX4, both within the module, and in larger system configuration.
:::tip
This topic should help you to shape the module to your own needs.
You will need some familiarity with PX4 development.
For more information see the developer [Getting Started](../dev_setup/getting_started.md).
:::
## Autostart
A line to autostart the [mc_nn_control](../modules/modules_controller.md#mc-nn-control) module has been added in the [`ROMFS/px4fmu_common/init.d/rc.mc_apps`](https://github.com/PX4/PX4-Autopilot/blob/main/ROMFS/px4fmu_common/init.d/rc.mc_apps) startup script.
It checks whether the module is included by looking for the parameter [MC_NN_EN](../advanced_config/parameter_reference.md#MC_NN_EN).
If this is set to `1` (the default value), the module will be started when booting PX4.
Similarly you could create other parameters in the [`mc_nn_control_params.c`](https://github.com/PX4/PX4-Autopilot/blob/main/src/modules/mc_nn_control/mc_nn_control_params.c) file for other startup script checks.
## Custom Flight Mode
The module creates its own flight mode "Neural Control" which lets you choose it from the flight mode menu in QGC and bind it to a switch on you RC controller.
This is done by using the [ROS 2 Interface Library](../ros2/px4_ros2_interface_lib.md) internally.
This involves several steps and is visualized here:
:::info
The module does not actually use ROS 2, it just uses the API exposed through uORB topics.
:::
:::info
In some QGC versions the flight mode does not show up, so make sure to update to the newest version.
This only works for some flight controllers, so you might have to use an RC controller to switch to the correct external flight mode.
:::
![neural_mode_registration](../../assets/advanced/neural_mode_registration.png)
1. Publish a [RegisterExtComponentRequest](../msg_docs/RegisterExtComponentRequest.md).
This specifies what you want to create, you can read more about this in the [Control Interface](../ros2/px4_ros2_control_interface.md).
In this case we register an arming check and a mode.
2. Wait for a [RegisterExtComponentReply](../msg_docs/RegisterExtComponentReply.md).
This will give feedback on wether the mode registration was successful, and what the mode and arming check id is for the new mode.
3. [Optional] With the mode id, publish a [VehicleControlMode](../msg_docs/VehicleControlMode.md) message on the `config_control_setpoints` topic.
Here you can configure what other modules run in parallel.
The example controller replaces everything, so it turns off allocation.
If you want to replace other parts you can enable or disable the modules accordingly.
4. [Optional] With the mode id, publish a [ConfigOverrides](../msg_docs/ConfigOverrides.md) on the `config_overrides_request` topic.
(This is not done in the example module) This will let you defer failsafes or stop it from automatically disarming.
5. When the mode has been registered a [ArmingCheckRequest](../msg_docs/ArmingCheckRequest.md) will be sent, asking if your mode has everything it needs to run.
This message must be answered with a [ArmingCheckReply](../msg_docs/ArmingCheckReply.md) so the mode is not flagged as unresponsive.
In this response it is possible to set what requirements the mode needs to run, like local position.
If any of these requirements are set the commander will stop you from switching to the mode if they are not fulfilled.
It is also important to set health_component_index and num_events to 0 to not get a segmentation fault.
Unless you have a health component or events.
6. Listen to the [VehicleStatus](../msg_docs/VehicleStatus.md) topic.
If the nav_state equals the assigned `mode_id`, then the Neural Controller is activated.
7. When active the module will run the controller and publish to [ActuatorMotors](../msg_docs/ActuatorMotors.md).
If you want to replace a different part of the controller, you should find the appropriate topic to publish to.
To see how the requests are handled you can check out [src/modules/commander/ModeManagement.cpp](https://github.com/PX4/PX4-Autopilot/blob/main/src/modules/commander/ModeManagement.cpp).
## 日志
To add module-specific logging a new topic has been added to [uORB](../middleware/uorb.md) called [NeuralControl](../msg_docs/NeuralControl.md).
The message definition is also added in `msg/CMakeLists.txt`, and to [`src/modules/logger/logged_topics.cpp`](https://github.com/PX4/PX4-Autopilot/blob/main/src/modules/logger/logged_topics.cpp) under the debug category.
For these messages to be saved in your logs you need to include `debug` in the [SDLOG_PROFILE](../advanced_config/parameter_reference.md#SDLOG_PROFILE) parameter.
## Timing
The module has two includes for measuring the inference times.
The first one is a driver that works on the actual flight controller units, but a second one, `chrono`, is loaded for SITL testing.
Which timing library is included and used is based on wether PX4 is built with NUTTX or not.
## Changing the setpoint
The module uses the [TrajectorySetpoint](../msg_docs/TrajectorySetpoint.md) message's position fields to define its target.
To follow a trajectory, you can send updated setpoints.
For an example of how to do this in a PX4 module, see the [mc_nn_testing](https://github.com/SindreMHegre/PX4-Autopilot-public/tree/main/src/modules/mc_nn_testing) module in this fork.
Note that this is not included in upstream PX4.
To use it, copy the module folder from the linked repository into your workspace, and enable it by adding the following line to your `.px4board` file:
```sh
CONFIG_MODULES_MC_NN_TESTING=y
```

221
docs/zh/neural_networks/raptor.md Normal file
View File

@@ -0,0 +1,221 @@
# RAPTOR: A Neural Network Module for Adaptive Quadrotor Control
<Badge type="tip" text="main (planned for PX4 v1.18)" /> <Badge type="info" text="Multicopter" /> <Badge type="warning" text="Experimental" />
:::warning
This is an experimental module.
Use at your own risk.
:::
RAPTOR is a tiny reinforcement-learning based neural network module for quadrotor control that can be used to control a wide variety of quadrotors without retuning.
This topic provides an overview of the fundamental concepts, and explains how you can use the module in simulation and real hardware.
## 综述
![Visual Abstract](../../assets/advanced/neural_networks/raptor/visual_abstract.jpg)
RAPTOR is an adaptive policy for end-to-end quadrotor control.
It is motivated by the human ability to adapt learned behaviours to similar situations.
For example, while humans may initially require many hours of driving experience to be able to smoothly control the car and blend into traffic, when faced with a new vehicle they do not need to re-learn how to drive — they only need to experience a few rough braking/acceleration/steering responses to adjust their previously learned behavior.
Reinforcement Learning (RL) is a machine learning technique that uses trial and error to learn decision making/control behaviors, which is similar to the way that humans learn to drive.
RL is interesting for controlling robots (and particularly UAVs) because it overcomes some fundamental limitations of classic, modular control architectures (information loss at module boundaries, requirement for expert tuning, etc).
RL has been very successful in [high-performance quadrotor flight](https://doi.org/10.1038/s41586-023-06419-4), but previous designs have not been particularly adaptable to new frames and vehicle types.
RAPTOR fills this gap and demonstrates a single, tiny neural-network control policy that can control a wide variety of quadrotors (tested on real quadrotors from 32 g to 2.4 kg).
For more details please refer to this video:
<lite-youtube videoid="hVzdWRFTX3k" title="RAPTOR: A Foundation Policy for Quadrotor Control"/>
The method we developed for training the RAPTOR policy is called Meta-Imitation Learning:
![Diagram showing the Method Overview](../../assets/advanced/neural_networks/raptor/method.jpg)
You can torture test the RAPTOR policy in your browser at [https://raptor.rl.tools](https://raptor.rl.tools) or in the embedded app here:
<iframe src="https://rl-tools.github.io/raptor.rl.tools?raptor=false" width="100%" height="1000" style="border: none;"></iframe>
For more information please refer to the paper at [https://arxiv.org/abs/2509.11481](https://arxiv.org/abs/2509.11481).
## Structure
The RAPTOR control policy is an end-to-end policy that takes position, orientation, linear velocity and angular velocity as inputs and outputs motor commands (`actuator_motors`).
To integrate it into PX4 we use the external mode registration facilities in PX4 (which also works well for internal modes as demonstrated in `mc_nn_control`).
Because of this architecture the `mc_raptor` module is completely decoupled from all other PX4 logic.
By default, the RAPTOR module expects setpoints via `trajectory_setpoint` messages.
If no `trajectory_setpoint` messages are received or if no `trajectory_setpoint` is received within 200 ms, the current position and orientation (with zero velocity) is used as the setpoint.
Since feeding setpoints reliably via telemetry is still a challenge, we also implement a simple option to generate internal reference trajectories (controlled through the `MC_RAPTOR_INTREF` parameter) for demonstration and benchmarking purposes.
## 特性
- Tiny neural network (just 2084 parameters) => minimal CPU usage
- Easily maintainable
- Simple CMake setup
- Self-contained (no interference with other modules)
- Single, simple and well-maintained dependency (RLtools)
- Loading neural network parameters from SD card
- Minimal flash usage (for possible inclusion into default build configurations)
- Easy development: Train new neural network and just upload it via MAVLink FTP without requiring to re-flash the firmware
- Tested on 10+ different real platforms (including flexible frames, brushed motors)
- Actively developed and maintained
## 用法
### SITL
Build PX4 SITL with Raptor, disable QGC requirement, and adjust the `IMU_GYRO_RATEMAX` to match the simulation IMU rate
```sh
make px4_sitl_raptor gz_x500
param set NAV_DLL_ACT 0
param set COM_DISARM_LAND -1 # When taking off in offboard the landing detector can cause mid-air disarms
param set IMU_GYRO_RATEMAX 250 # Just for SITL. Tested with IMU_GYRO_RATEMAX=400 on real FCUs
param set MC_RAPTOR_ENABLE 1 # Enable the mc_raptor module
param save
```
Upload the RAPTOR checkpoint to the "SD card": Separate terminal
```bash
mavproxy.py --master udp:127.0.0.1:14540
ftp mkdir /raptor # for the real FMU use: /fs/microsd/raptor
ftp put src/modules/mc_raptor/blob/policy.tar /raptor/policy.tar
```
Restart (<kbd>Ctrl+C</kbd>)
```sh
make px4_sitl_raptor gz_x500
commander takeoff
commander status
```
Note the external mode ID of `RAPTOR` in the status report
```sh
commander mode ext{RAPTOR_MODE_ID}
```
#### Internal Reference Trajectory Generation
In our experience, feeding the `trajectory_setpoint` via MAVLink (even via WiFi telemetry) is unreliable.
But we do not want to constrain this module to only platforms that have a companion board.
For this reason we have integrated a simple internal reference trajectory generator for testing and benchmarking purposes.
It supports position (constant position and yaw setpoint) as well as configurable [Lissajous trajectories](https://en.wikipedia.org/wiki/Lissajous_curve).
The Lissajous generator can, for example, generate smooth figure-eight trajectories that contain interesting accelerations for benchmarking and testing purposes.
Please refer to the embedded configurator later in this section to explore the Lissajous parameters and view the resulting trajectories.
To use the internal reference generator, select the mode: `0`: Off/activation position tracking, `1`: Lissajous
```sh
param set MC_RAPTOR_INTREF 1
```
Restart (ctrl+c)
```sh
commander takeoff
commander mode ext{RAPTOR_MODE_ID}
mc_raptor intref lissajous 0.5 1 0 2 1 1 10 3
```
The trajectory is relative to the position and yaw of the vehicle at the point where the RAPTOR mode is activated (or the position and yaw where the parameters are changed if it is already activated).
You can adjust the parameters of the trajectory with the following tool.
Make sure to copy the generated CLI string at the end:
<iframe src="https://rl-tools.github.io/mc-raptor-trajectory-tool" width="100%" height="1700" style="border: none;"></iframe>
### Real-World
#### 设置
The `mc_raptor` module has been mostly tested with the Holybro X500 V2 but it should also work out-of-the-box with other platforms (see the [Other Platforms](#other-platforms) section).
```sh
make px4_fmu-v6c_raptor upload
```
We recommend initially testing the RAPTOR mode using a dead man's switch.
For this we configure the mode selection to be connected to a push button or a switch with a spring that automatically switches back.
In the default position we configure e.g. `Stabilized Mode` and in the pressed configuration we select `External Mode 1` (since the name of the external mode is only transmitted at runtime).
This allows to take off manually and then just trigger the RAPTOR mode for a split-second to see how it behaves.
In our experiments it has been exceptionally stable (zero crashes) but we still think progressively activating it for longer is the safest way to build confidence.
:::warning
Make sure that your platform uses the standard PX4 quadrotor motor layout:
1: front-right, 2: back-left, 3: front-left, 4: back-right
:::
##### Other Platforms
To enable the `mc_raptor` module in other platforms, just add `CONFIG_MODULES_MC_RAPTOR=y` and `CONFIG_LIB_RL_TOOLS=y`
```diff
+++ b/boards/px4/fmu-v6c/raptor.px4board
@@ -35,2 +35,3 @@
CONFIG_DRIVERS_UAVCAN=y
+CONFIG_LIB_RL_TOOLS=y
CONFIG_MODULES_AIRSPEED_SELECTOR=y
@@ -64,2 +65,3 @@
CONFIG_MODULES_MC_POS_CONTROL=y
+CONFIG_MODULES_MC_RAPTOR=y
CONFIG_MODULES_MC_RATE_CONTROL=y
```
#### Results
Even though there were moderate winds (~ 5 m/s) during the test, we found good figure-eight tracking performance at velocities up to 12 m/s:
![Lissajous](../../assets/advanced/neural_networks/raptor/results_figure_eight.svg)
We also tested the linear velocity in a straight line and found that the RAPTOR policy can reliably fly at > 17 m/s (the wind direction was orthogonal to the line):
![Linear Oscillation](../../assets/advanced/neural_networks/raptor/results_line.svg)
### 故障处理
#### 日志
Use this logging configuration to log all relevant topics at maximum rate:
```sh
cat > logger_topics.txt << EOF
raptor_status 0
raptor_input 0
trajectory_setpoint 0
vehicle_local_position 0
vehicle_angular_velocity 0
vehicle_attitude 0
vehicle_status 0
actuator_motors 0
EOF
```
Use mavproxy FTP to upload it:
```sh
mavproxy.py
```
##### Real
```sh
ftp mkdir /fs/microsd/etc
ftp mkdir /fs/microsd/etc/logging
ftp put logger_topics.txt /fs/microsd/etc/logging/logger_topics.txt
```
##### SITL
```sh
ftp mkdir etc
ftp mkdir logging
ftp put logger_topics.txt etc/logging/logger_topics.txt
```

77
docs/zh/neural_networks/tflm.md Normal file
View File

@@ -0,0 +1,77 @@
# TensorFlow Lite Micro (TFLM)
The PX4 [MC Neural Networks Control](../neural_networks/mc_neural_network_control.md) module ([mc_nn_control](../modules/modules_controller.md#mc-nn-control)) integrates a neural network that uses the [TensorFlow Lite Micro (TFLM)](https://github.com/tensorflow/tflite-micro) inference library.
This is a mature inference library intended for use on embedded devices, and is hence a suitable choice for PX4.
This guide explains how the TFLM library is integrated into the [mc_nn_control](../modules/modules_controller.md#mc-nn-control) module, and the changes you would have to make to use it for your own neural network.
:::tip
For more information, see the [TFLM guide](https://ai.google.dev/edge/litert/microcontrollers/get_started).
:::
## TLMF NN Formats
TFLM uses networks in its own [tflite format](https://ai.google.dev/edge/litert/models/convert).
However, since many microcontrollers do not have native filesystem support, a tflite file can be converted to a C++ source and header file.
This is what is done in `mc_nn_control`.
The tflight neural network is represented in code by the files [`control_net.cpp`](https://github.com/PX4/PX4-Autopilot/blob/main/src/modules/mc_nn_control/control_net.cpp) and [`control_net.hpp`](https://github.com/PX4/PX4-Autopilot/blob/main/src/modules/mc_nn_control/control_net.hpp).
### Getting a Network in tflite Format
There are many online resource for generating networks in the `.tflite` format.
For this example we trained the network in the open source [Aerial Gym Simulator](https://ntnu-arl.github.io/aerial_gym_simulator/).
Aerial Gym includes a guide, and supports RL both for control and vision-based navigation tasks.
The project includes conversion code for `PyTorch -> TFLM` in the [resources/conversion](https://github.com/ntnu-arl/aerial_gym_simulator/tree/main/resources/conversion) folder.
### Updating `mc_nn_control` with your own NN
You can convert a `.tflite` network into a `.cc` file in the ubuntu terminal with this command:
```sh
xxd -i converted_model.tflite > model_data.cc
```
You will then have to modify the `control_net.hpp` and `control_net.cpp` to include the data from `model_data.cc`:
- Take the size of the network in the bottom of the `.cc` file and replace the size in `control_net.hpp`.
- Take the data in the model array in the `cc` file, and replace the ones in `control_net.cpp`.
You are now ready to run your own network.
## Code Explanation
This section explains the code used to integrate the NN in `control_net.cpp`.
### Operations and Resolver
Firstly we need to create the resolver and load the needed operators to run inference on the NN.
This is done in the top of `mc_nn_control.cpp`.
The number in `MicroMutableOpResolver<3>` represents how many operations you need to run the inference.
A full list of the operators can be found in the [micro_mutable_op_resolver.h](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/micro_mutable_op_resolver.h) file.
There are quite a few supported operators, but you will not find the most advanced ones.
In the control example the network is fully connected so we use `AddFullyConnected()`.
Then the activation function is ReLU, and we `AddAdd()` for the bias on each neuron.
### Interpreter
In the `InitializeNetwork()` we start by setting up the model that we loaded from the source and header file.
Next is to set up the interpreter, this code is taken from the TFLM documentation and is thoroughly explained there.
The end state is that the `_control_interpreter` is set up to later run inference with the `Invoke()` member function.
The `_input_tensor` is also defined, it is fetched from `_control_interpreter->input(0)`.
### 输入
The `_input_tensor` is filled in the `PopulateInputTensor()` function.
`_input_tensor` works by accessing the `->data.f` member array and fill in the required inputs for your network.
The inputs used in the control network is covered in [MC Neural Networks Control](../neural_networks/mc_neural_network_control.md).
### Outputs
For the outputs the approach is fairly similar to the inputs.
After setting the correct inputs, calling the `Invoke()` function the outputs can be found by getting `_control_interpreter->output(0)`.
And from the output tensor you get the `->data.f` array.

1
docs/zh/releases/1.16.md
View File

@@ -151,6 +151,7 @@ Please continue reading for [upgrade instructions](#upgrade-guide).
### uXRCE-DDS / ROS2
- [PX4-Autopilot#24113](https://github.com/PX4/PX4-Autopilot/pull/24113): <Badge type="warning" text="Experimental"/> [ROS 2 Message Translation Node](../ros2/px4_ros2_msg_translation_node.md) to translate PX4 messages from one definition version to another dynamically
- <Badge type="warning" text="Experimental"/>[PX4 ROS 2 Interface Library](../ros2/px4_ros2_control_interface.md) support for [ROS-based waypoint missions](../ros2/px4_ros2_waypoint_missions.md).
- dds_topics: add vtol_vehicle_status ([PX4-Autopilot#24582](https://github.com/PX4/PX4-Autopilot/pull/24582))
- dds_topics: add home_position ([PX4-Autopilot#24583](https://github.com/PX4/PX4-Autopilot/pull/24583))

134
docs/zh/releases/1.17.md Normal file
View File

@@ -0,0 +1,134 @@
# PX4-Autopilot v1.17.0 Release Notes
<Badge type="danger" text="Alpha/Beta" />
<script setup>
import { useData } from 'vitepress'
const { site } = useData();
</script>
<div v-if="site.title !== 'PX4 Guide (main)'">
<div class="custom-block danger">
<p class="custom-block-title">This page is on a release branch, and hence probably out of date. <a href="https://docs.px4.io/main/en/releases/main.html">See the latest version</a>.</p>
</div>
</div>
This contains changes to PX4 planned for PX4 v1.17 (since the last major release [PX v1.16](../releases/1.16.md)).
:::warning
PX4 v1.17 is in alpha/beta testing.
Update these notes with features that are going to be in PX4 v1.17 release.
New features that are not expected to go into the v1.17 release are in [PX4-Autopilot `main` Release Notes](../releases/main.md).
:::
## Read Before Upgrading
TBD …
Please continue reading for [upgrade instructions](#upgrade-guide).
## Major Changes
- TBD
## Upgrade Guide
## Other changes
### Hardware Support
- **[New Hardware]** boards: [MicoAir743-Lite FC](../flight_controller/micoair743-lite.md) <!-- CHECK is this version and add PR link (or fix up doc version tag and move this) -->
- **[New Hardware]** boards: [RadiolinkPIX6 FC](../flight_controller/radiolink_pix6.md) <!-- CHECK is this version and add PR! -->
- **[New Hardware]** boards: [AP-H743-R1 FC](../flight_controller/x-mav_ap-h743r1.md) <!-- CHECK is this version and add PR! -->
<!--
### Common
- [QGroundControl Bootloader Update](../advanced_config/bootloader_update.md#qgc-bootloader-update-sys-bl-update) via the [SYS_BL_UPDATE](../advanced_config/parameter_reference.md#SYS_BL_UPDATE) parameter has been re-enabled after being broken for a number of releases. ([PX4-Autopilot#25032: build: romf: fix generation of rc.board_bootloader_upgrade](https://github.com/PX4/PX4-Autopilot/pull/25032)).
-->
### Control
<!--
- Added new flight mode(s): [Altitude Cruise (MC)](../flight_modes_mc/altitude_cruise.md), Altitude Cruise (FW).
For fixed-wing the mode behaves the same as Altitude mode but you can disable the manual control loss failsafe. ([PX4-Autopilot#25435: Add new flight mode: Altitude Cruise](https://github.com/PX4/PX4-Autopilot/pull/25435)).
-->
- <Badge type="warning" text="Experimental" /> [MC Neural Network Module](../advanced/neural_networkss.md)
### Estimation
- TBD
<!--
### Sensors
- Add [sbgECom INS driver](../sensor/sbgecom.md) ([PX4-Autopilot#24137](https://github.com/PX4/PX4-Autopilot/pull/24137))
- Quick magnetometer calibration now supports specifying an arbitrary initial heading ([PX4-Autopilot#24637](https://github.com/PX4/PX4-Autopilot/pull/24637))
-->
### 仿真
- Overhaul rover simulation:
- Add synthetic differential rover model: [PX4-gazebo-models#107](https://github.com/PX4/PX4-gazebo-models/pull/107)
- Add synthetic mecanum rover model: [PX4-gazebo-models#113](https://github.com/PX4/PX4-gazebo-models/pull/113)
- Update synthetic ackermann rover model: [PX4-gazebo-models#117](https://github.com/PX4/PX4-gazebo-models/pull/117)
- [Simulation-in-Hardware (SIH)](../sim_sih/index.md#compatibility) <!-- Listed in https://docs.px4.io/main/en/sim_sih/#compatibility : Check the PRs -->
- New simulation: MC Hexacopter X
- New simulation: Ackermann Rover
### Debug & Logging
- TBD
### Ethernet
- TBD
### uXRCE-DDS / Zenoh / ROS2
- [PX4 ROS 2 Interface Library](../ros2/px4_ros2_control_interface.md) support for [Fixed Wing lateral/longitudinal setpoint](../ros2/px4_ros2_control_interface.md#fixed-wing-lateral-and-longitudinal-setpoint-fwlaterallongitudinalsetpointtype) (`FwLateralLongitudinalSetpointType`) and [VTOL transitions](../ros2/px4_ros2_control_interface.md#controlling-a-vtol). ([PX4-Autopilot#24056](https://github.com/PX4/PX4-Autopilot/pull/24056)).
- [UXRCE_DDS: Simple index based namespace (UXRCE_DDS_NS_IDX)](../middleware/uxrce_dds.md#customizing-the-namespace)
- [Zenoh (PX4 ROS 2 rmw_zenoh)](../middleware/zenoh.md)
### MAVLink
- TBD
<!--
### RC
- Parse ELRS Status and Link Statistics TX messages in the CRSF parser.
### Multi-Rotor
- Removed parameters `MPC_{XY/Z/YAW}_MAN_EXPO` and use default value instead, as they were not deemed necessary anymore. ([PX4-Autopilot#25435: Add new flight mode: Altitude Cruise](https://github.com/PX4/PX4-Autopilot/pull/25435)).
- Renamed `MPC_HOLD_DZ` to `MAN_DEADZONE` to have it globally available in modes that allow for a dead zone. ([PX4-Autopilot#25435: Add new flight mode: Altitude Cruise](https://github.com/PX4/PX4-Autopilot/pull/25435)).
-->
### 垂直起降
- TBD
### Fixed-wing
- [Fixed Wing Takeoff mode](../flight_modes_fw/takeoff.md) will now keep climbing with level wings on position loss.
A target takeoff waypoint can be set to control takeoff course and loiter altitude. ([PX4-Autopilot#25083](https://github.com/PX4/PX4-Autopilot/pull/25083)).
- Automatically suppress angular rate oscillations using [Gain compression](../features_fw/gain_compression.md). ([PX4-Autopilot#25840: FW rate control: add gain compression algorithm](https://github.com/PX4/PX4-Autopilot/pull/25840))
### 无人车
- Removed deprecated rover module ([PX4-Autopilot#25054](https://github.com/PX4/PX4-Autopilot/pull/25054)).
- Add support for [Apps & API](../flight_modes_rover/api.md) including [Rover Setpoints](../ros2/px4_ros2_control_interface.md#rover-setpoints) ([PX4-Autopilot#25074](https://github.com/PX4/PX4-Autopilot/pull/25074), [PX4-ROS2-Interface-Lib#140](https://github.com/Auterion/px4-ros2-interface-lib/pull/140)).
- Update [rover simulation](../frames_rover/index.md#simulation) ([PX4-Autopilot#25644](https://github.com/PX4/PX4-Autopilot/pull/25644)) (see [Simulation](#simulation) release note for details).
### ROS 2
- TBD

3
docs/zh/releases/index.md
View File

@@ -2,7 +2,8 @@
这是一份 PX4 发行说明列表，其中包含每次发布所做更改的清单，详细说明了新增功能、漏洞修复、弃用内容以及更新情况。
- [main](../releases/main.md) (changes since v1.16)
- [main](../releases/main.md) (changes planned for v1.18 or later)
- [v1.17](../releases/1.17.md) (changes planned for v1.17, since v1.16)
- [v1.16](../releases/1.16.md)
- [v1.15](../releases/1.15.md)
- [v1.14](../releases/1.14.md)

36
docs/zh/releases/main.md
View File

@@ -16,13 +16,13 @@ const { site } = useData();
This contains changes to PX4 `main` branch since the last major release ([PX v1.16](../releases/1.16.md)).
:::warning
PX4 v1.16 is in candidate-release testing, pending release.
Update these notes with features that are going to be in `main` but not the PX4 v1.16 release.
PX4 v1.17 is in alpha/beta testing.
Update these notes with features that are going to be in `main` (PX4 v1.18 or later) but not the PX4 v1.17 release.
:::
## Read Before Upgrading
TBD …
- TBD …
Please continue reading for [upgrade instructions](#upgrade-guide).
@@ -45,8 +45,7 @@ Please continue reading for [upgrade instructions](#upgrade-guide).
### Control
- Added new flight mode(s): [Altitude Cruise (MC)](../flight_modes_mc/altitude_cruise.md), Altitude Cruise (FW).
For fixed-wing the mode behaves the same as Altitude mode but you can disable the manual control loss failsafe. (PX4-Autopilot#25435: Add new flight mode: Altitude Cruise
).
For fixed-wing the mode behaves the same as Altitude mode but you can disable the manual control loss failsafe. ([PX4-Autopilot#25435: Add new flight mode: Altitude Cruise](https://github.com/PX4/PX4-Autopilot/pull/25435)).
### Estimation
@@ -59,19 +58,34 @@ Please continue reading for [upgrade instructions](#upgrade-guide).
### 仿真
- TBD
<!-- MOVED THIS TO v1.17
- Overhaul rover simulation:
- Add synthetic differential rover model: [PX4-gazebo-models#107](https://github.com/PX4/PX4-gazebo-models/pull/107)
- Add synthetic mecanum rover model: [PX4-gazebo-models#113](https://github.com/PX4/PX4-gazebo-models/pull/113)
- Update synthetic ackermann rover model: [PX4-gazebo-models#117](https://github.com/PX4/PX4-gazebo-models/pull/117)
-->
### Debug & Logging
- [Asset Tracking](../debug/asset_tracking.md): Automatic tracking and logging of external device information including vendor name, firmware and hardware version, serial numbers. Currently supports DroneCAN devices. ([PX4-Autopilot#25617](https://github.com/PX4/PX4-Autopilot/pull/25617))
### Ethernet
- TBD
### uXRCE-DDS / ROS2
### uXRCE-DDS / Zenoh / ROS2
- TBD
<!-- MOVED THIS TO v1.17
- [PX4 ROS 2 Interface Library](../ros2/px4_ros2_control_interface.md) support for [Fixed Wing lateral/longitudinal setpoint](../ros2/px4_ros2_control_interface.md#fixed-wing-lateral-and-longitudinal-setpoint-fwlaterallongitudinalsetpointtype) (`FwLateralLongitudinalSetpointType`) and [VTOL transitions](../ros2/px4_ros2_control_interface.md#controlling-a-vtol). ([PX4-Autopilot#24056](https://github.com/PX4/PX4-Autopilot/pull/24056)).
- [PX4 ROS 2 Interface Library](../ros2/px4_ros2_control_interface.md) support for [ROS-based waypoint missions](../ros2/px4_ros2_waypoint_missions.md).
-->
### MAVLink
@@ -92,16 +106,26 @@ Please continue reading for [upgrade instructions](#upgrade-guide).
### Fixed-wing
- TBD
<!-- MOVED THIS TO v1.17
- [Fixed Wing Takeoff mode](../flight_modes_fw/takeoff.md) will now keep climbing with level wings on position loss.
A target takeoff waypoint can be set to control takeoff course and loiter altitude. ([PX4-Autopilot#25083](https://github.com/PX4/PX4-Autopilot/pull/25083)).
- Automatically suppress angular rate oscillations using [Gain compression](../features_fw/gain_compression.md). ([PX4-Autopilot#25840: FW rate control: add gain compression algorithm](https://github.com/PX4/PX4-Autopilot/pull/25840))
-->
### 无人车
- TBD
<!-- MOVED THIS TO v1.17
- Removed deprecated rover module ([PX4-Autopilot#25054](https://github.com/PX4/PX4-Autopilot/pull/25054)).
- Add support for [Apps & API](../flight_modes_rover/api.md) ([PX4-Autopilot#25074](https://github.com/PX4/PX4-Autopilot/pull/25074), [PX4-ROS2-Interface-Lib#140](https://github.com/Auterion/px4-ros2-interface-lib/pull/140)).
- Update [rover simulation](../frames_rover/index.md#simulation) ([PX4-Autopilot#25644](https://github.com/PX4/PX4-Autopilot/pull/25644)) (see [Simulation](#simulation) release note for details).
-->
### ROS 2
- TBD

10
docs/zh/ros2/px4_ros2_control_interface.md
View File

@@ -345,9 +345,9 @@ private:
以下章节提供了支持的设置点类型列表：
- [MulticopterGotoSetpointType](#go-to-setpoint-multicoptergotosetpointtype): <Badge type="warning" text="MC only" /> 平滑的位置控制以及（可选的）航向控制
- [FwLateralLongitudinalSetpointType](#fixed-wing-lateral-and-longitudinal-setpoint-fwlaterallongitudinalsetpointtype): <Badge type="warning" text="FW only" /> <Badge type="tip" text="main (planned for: PX4 v1.17)" /> 对横向和纵向固定翼动态的直接控制
- [FwLateralLongitudinalSetpointType](#fixed-wing-lateral-and-longitudinal-setpoint-fwlaterallongitudinalsetpointtype): <Badge type="warning" text="FW only" /> <Badge type="tip" text="PX4 v1.17" /> Direct control of lateral and longitudinal fixed wing dynamics
- [DirectActuatorsSetpointType](#direct-actuator-control-setpoint-directactuatorssetpointtype)：直接控制发动机和飞行地面servo setpoints
- [Rover Setpoints](#rover-setpoints): <Badge type="tip" text="main (planned for: PX4 v1.17)" />直接访问火星车控制设定值（位置、速度、姿态、速率、油门和转向）。
- [Rover Setpoints](#rover-setpoints): <Badge type="tip" text="PX4 v1.17" /> Direct access to rover control setpoints (Position, Speed, Attitude, Rate, Throttle and Steering).
:::tip
其他设置点类型目前是实验性的，可在以下网址找到：[px4_ros2/control/setpoint_types/experimental](https://github.com/Auterion/px4-ros2-interface-lib/tree/main/px4_ros2_cpp/include/px4_ros2/control/setpoint_types/experimental)。
@@ -414,7 +414,7 @@ _goto_setpoint->update(
#### 固定翼横向与纵向设定值（FwLateralLongitudinalSetpointType，固定翼横向纵向设定值类型）
<Badge type="warning" text="Fixed wing only" /> <Badge type="tip" text="main (planned for: PX4 v1.17)" />
<Badge type="warning" text="Fixed wing only" /> <Badge type="tip" text="PX4 v1.17" />
:::info
此设定值类型支持固定翼飞行器，以及处于固定翼模式下的垂直起降飞行器（VTOL）。
@@ -556,7 +556,7 @@ _fw_lateral_longitudinal_setpoint->update(setpoint_s, config_s);
#### Rover 设置点
<Badge type="tip" text="main (planned for: PX4 v1.17)" /> <Badge type="warning" text="Experimental" />
<Badge type="tip" text="PX4 v1.17" /> <Badge type="warning" text="Experimental" />
滚动模块使用层次结构来传播设置点：
@@ -590,7 +590,7 @@ _fw_lateral_longitudinal_setpoint->update(setpoint_s, config_s);
### 控制VTOL
<Badge type="tip" text="main (planned for: PX4 v1.17)" /> <Badge type="warning" text="Experimental" />
<Badge type="tip" text="PX4 v1.17" /> <Badge type="warning" text="Experimental" />
要在外部飞行模式下控制VTOL，需确保根据当前飞行配置返回正确的设定值类型：

4
docs/zh/sim_sih/index.md
View File

@@ -27,8 +27,8 @@ The Desktop computer is only used to display the virtual vehicle.
- SIH for FW (airplane) and VTOL tailsitter are supported from PX4 v1.13.
- SIH as SITL (without hardware) from PX4 v1.14.
- SIH for Standard VTOL from PX4 v1.16.
- SIH for MC Hexacopter X from `main` (expected to be PX4 v1.17).
- SIH for Ackermann Rover from `main`.
- SIH for MC Hexacopter X from PX4 v1.17.
- SIH for Ackermann Rover from PX4 v1.17.
### Benefits