# AutoTrans

**Repository Path**: wangshengkai111/AutoTrans

## Basic Information

- **Project Name**: AutoTrans
- **Description**: AutoTrans: A Complete Planning and Control Framework for Autonomous UAV Payload Transportation
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-01-14
- **Last Updated**: 2025-03-26

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# AutoTrans: A Complete Planning and Control Framework for Autonomous UAV Payload Transportation

[![AutoTrans](imgs/cover.png)](https://youtu.be/X9g-ivBqy5g)

**Video**: [YouTube](https://youtu.be/X9g-ivBqy5g) | [Bilibili](https://www.bilibili.com/video/BV1aM4y1a7c9)

## Introduction
**AutoTrans** presents a real-time and robust planning and control framework for quadrotor with payload. It can generate the dynamic feasible trajectory considering the time-varying shape and deal with the disturbance while executing trajectory. 

![System](imgs/system.png)

This repo includes a real-time motion planning, a disturbance-aware NMPC and a simple simulation for a quadrotor with a suspended payload.


**Authors**: Haojia Li, Haokun Wang, [Chen Feng](https://chen-albert-feng.github.io/AlbertFeng.github.io/), [Fei Gao*](http://zju-fast.com/fei-gao/), [Boyu Zhou*](http://sysu-star.com/), and [Shaojie Shen](https://uav.hkust.edu.hk/group/). 

**Institutions**: [HKUST Aerial Robotics Group](https://uav.hkust.edu.hk/), [SYSU STAR Group](http://sysu-star.com/), and [ZJU FAST Lab](http://zju-fast.com/).

**Paper**: [AutoTrans: A Complete Planning and Control Framework for Autonomous UAV Payload Transportation](https://doi.org/10.1109/LRA.2023.3313010), IEEE Robotics and Automation Letters (RA-L), 2023. [IEEE Spectrum](https://spectrum.ieee.org/video-friday-reflex-grasping)

```bibtex
@article{li2023autotrans,
  title={AutoTrans: A Complete Planning and Control Framework for Autonomous UAV Payload Transportation}, 
  author={Li, Haojia and Wang, Haokun and Feng, Chen and Gao, Fei and Zhou, Boyu and Shen, Shaojie},
  journal={IEEE Robotics and Automation Letters}, 
  year={2023},
  volume={8},
  number={10},
  pages={6859-6866},
  doi={10.1109/LRA.2023.3313010}}
```

If you find this work useful or interesting, please kindly give us a star ⭐, thanks!😀

## Setup

Compiling tests passed on Ubuntu 20.04/18.04 with ROS installed.
### Prerequisites
- [ROS](http://wiki.ros.org/ROS/Installation) (tested with Noetic)
  
```bash
sudo apt install ros-"${ROS_DISTRO}"-mavros-msgs
```

### Compiling and Running
```bash
# Compile the code
mkdir -p autotrans_ws/src
cd autotrans_ws/src
git clone https://github.com/HKUST-Aerial-Robotics/AutoTrans
cd ..
catkin_make -DCMAKE_BUILD_TYPE=Release

# Run the simulation with planner and controller
source devel/setup.bash
roslaunch payload_planner simple_run.launch
```
You should see the simulation in rviz. You can use the `2D Nav Goal` to set the goal position. The red arrow on the quadrotor represents the estimated disturbance force (like rotor drag).

![Simulation](imgs/simulation.gif)

### Tip: Boost Your Computer
This can make the MPC solve faster in each iteration.
```bash
sudo apt install cpufrequtils
sudo cpufreq-set -g performance
```



## Acknowledgements
We use [MINCO](https://github.com/ZJU-FAST-Lab/GCOPTER) as our trajectory representation.

We borrow the framework from [Fast-Planner](https://github.com/HKUST-Aerial-Robotics/Fast-Planner) and [Ego-Planner-v2](https://github.com/ZJU-FAST-Lab/EGO-Planner-v2)

Thanks to [rpg_mpc](https://github.com/uzh-rpg/rpg_mpc) for a good reference.

## Maintaince
For any technical issues, please contact Haojia Li(hlied@connect.ust.hk).



# AutoTrans：一种用于无人机自主载荷运输的完整规划与控制框架

**AutoTrans**

视频演示：[YouTube](https://youtube.com) | [哔哩哔哩](https://bilibili.com)

---

## 简介  
AutoTrans 为搭载悬挂载荷的四旋翼无人机提供了一套实时、鲁棒的规划与控制框架。该框架能够生成考虑时变形态的动态可行轨迹，并在执行轨迹时有效应对扰动。

---

## 系统概述  
本仓库包含以下组件：  
- **实时运动规划器**  
- **扰动感知非线性模型预测控制器（NMPC）**  
- 四旋翼与悬挂载荷的简易仿真环境  

---

## 作者与机构  
**作者**：李浩佳（Haojia Li）、王浩坤（Haokun Wang）、冯晨（Chen Feng）、高飞（Fei Gao*）、周博宇（Boyu Zhou*）、沈劭劼（Shaojie Shen）  
**机构**：  
- 香港科技大学空中机器人组（HKUST Aerial Robotics Group）  
- 中山大学星航团队（SYSU STAR Group）  
- 浙江大学FAST实验室（ZJU FAST Lab）  

**论文**：  
《AutoTrans: A Complete Planning and Control Framework for Autonomous UAV Payload Transportation》，发表于《IEEE Robotics and Automation Letters (RA-L)》2023年卷，IEEE Spectrum报道。  
```latex
@article{li2023autotrans,
  title={AutoTrans: A Complete Planning and Control Framework for Autonomous UAV Payload Transportation}, 
  author={Li, Haojia and Wang, Haokun and Feng, Chen and Gao, Fei and Zhou, Boyu and Shen, Shaojie},
  journal={IEEE Robotics and Automation Letters}, 
  year={2023},
  volume={8},
  number={10},
  pages={6859-6866},
  doi={10.1109/LRA.2023.3313010}}
```  
如果本项目对您有所帮助或启发，欢迎为仓库点亮⭐星标支持，感谢！😀  

---

## 环境配置  
已在安装ROS的Ubuntu 20.04/18.04系统上通过编译测试。

### 依赖项  
- **ROS**（测试版本为Noetic）  
  ```bash
  sudo apt install ros-"${ROS_DISTRO}"-mavros-msgs
  ```

### 编译与运行  
```bash
# 编译代码
mkdir -p autotrans_ws/src
cd autotrans_ws/src
git clone https://github.com/HKUST-Aerial-Robotics/AutoTrans
cd ..
catkin_make -DCMAKE_BUILD_TYPE=Release

# 运行规划与控制仿真
source devel/setup.bash
roslaunch payload_planner simple_run.launch
```  
启动后可在RViz中查看仿真。使用 **2D Nav Goal** 设置目标位置，四旋翼上的红色箭头表示估计的扰动力（如旋翼阻力）。

---

## 仿真效果  
（此处可添加仿真截图或描述）

---

## 提示：提升计算机性能  
以下命令可加速MPC求解速度：  
```bash
sudo apt install cpufrequtils
sudo cpufreq-set -g performance
```

---

## 致谢  
- 采用 **MINCO** 作为轨迹表示方法。  
- 框架设计参考了 **Fast-Planner** 和 **Ego-Planner-v2**。  
- 感谢 **rpg_mpc** 提供的优秀参考实现。  

---

## 维护支持  
如有任何技术问题，请联系 **李浩佳**（邮箱：hlied@connect.ust.hk）。