KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #typescript #ai-agent #developer-tools #claude-code #codex #deepseek-harness #ai-agents #react #mcp #rust

adaptive_swarm

★ 81 Open GitHub ↗

Multiple robots layered path planning algorithm implemented as a ROS node to control a swarm of nano quadrotors, Crazyflies 2.X, with real-time obstacle avoidance.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Adaptive Swarm
[![ToH](http://img.shields.io/badge/IEEE-ToH2019-blue.svg?style=plastic)](https://ieeexplore.ieee.org/document/8758191)
[![CHI](http://img.shields.io/badge/iHDI2019-workshop-critical.svg?style=plastic)](https://hal.science/hal-02128383/document)
[![Thesis](http://img.shields.io/badge/Msc-Thesis-green.svg?style=plastic)](https://github.com/RuslanAgishev/adaptive_swarm/blob/90d7066fce9917577bab0a8fa40fb93e4ee564f8/MSc_Thesis_Skoltech.pdf)

## Package description

This project is a layered path planner algorithm to solve multiple agents navigation problem in a cluttered environment.
Please, refer to the [Master Thesis](https://github.com/RuslanAgishev/adaptive_swarm/blob/90d7066fce9917577bab0a8fa40fb93e4ee564f8/MSc_Thesis_Skoltech.pdf) for more details.

The general path planning problem is divided into approximate global trajectory construction, which is further smoothed by a local path planning method.
The proposed approach provides a solution based on a leader-followers architecture with a prescribed formation geometry that adapts dynamically to the environment and avoids collisions.

The path generated by the global planner based on rapidly-exploring random tree (RRT) algorithm is corrected with the artificial potential fields (APF) method that ensures robots trajectories to be collision-free, reshaping the geometry of the formation when required by environmental conditions. Take a look at [motion_planning](https://github.com/RuslanAgishev/motion_planning) repository for more examples.

## Getting started

Execute the following command in order to see how the planner algorithm works in simulation:
```bash
python scripts/layered_planner/layered_planner_sim.py 
```

## Real flight

Here I would like to describe how to use the package for autonomous path planning of a group of nano-quadrotors
[Crazyflies](https://www.bitcraze.io/products/old-products/crazyflie-2-0/).

### Dependencies
* [ROS](https://www.ros.org/)
* [crazyflie_ros](https://github.com/whoenig/crazyflie_ros)
* [vicon_bridge](https://github.com/ethz-asl/vicon_bridge)

Install ROS (the package is tested with [kinetic](http://wiki.ros.org/kinetic/Installation/Ubuntu)
version and Ubuntu 16.04),
setup a workspace and build the packages:

```bash
mkdir -p ~/catkin_ws/src
cd ~/catkin_ws/src
git clone --recursive https://github.com/whoenig/crazyflie_ros
git clone https://github.com/ethz-asl/vicon_bridge
git clone https://github.com/RuslanAgishev/adaptive_swarm.git
cd ~/catkin_ws
catkin_make
source devel/setup.bash
```

The path planning algrithm is built with a known map assumption.
You can define obstacles location of your environment in
[`layered_planner.py`](https://github.com/RuslanAgishev/adaptive_swarm/blob/master/scripts/layered_planner/layered_planner.py#L92).

- Launch external position estimator (Vicon motion capture system), and connect to drones:
```bash
roslaunch adaptive_swarm connect123.launch
```

Setup python path to swarmlib:
```bash
export PYTHONPATH=/path/to/catkin_ws/src/adaptive_swarm/scripts:$PYTHONPATH
```

- Command the drones to fly in a formation through a map of obstacles:
```bash
rosrun adaptive_swarm layered_planner.py 
```
<img src="https://github.com/RuslanAgishev/adaptive_swarm/blob/master/figures/layered_planner/narrow_passage/real1.png" width="240"/> <img src="https://github.com/RuslanAgishev/adaptive_swarm/blob/master/figures/layered_planner/narrow_passage/real2.png" width="240"/> <img src="https://github.com/RuslanAgishev/adaptive_swarm/blob/master/figures/layered_planner/narrow_passage/real3.png" width="240"/>

## Citation
Feel free to cite the papers, if you find the package useful for your research.

```bibtex
@article{tsykunov2019swarmtouch,
  title={Swarmtouch: Guiding a swarm of micro-quadrotors with impedance control using a wearable tactile interface},
  author={Tsykunov, Evgeny and Agishev, Ruslan and Ibrahimov, Roman and Labazanova, Luiza and Tleugazy, Akerke and Tsetserukou, Dzmitry},
  journal={IEEE transactions on haptics},
  volume={12},
  number={3},
  pages={363--374},
  year={2019},
  publisher={IEEE}
}
@inproceedings{agishev:hal-02128383,
  TITLE = {{Tactile Interaction of Human with Swarm of Nano-Quadrotors augmented with Adaptive Obstacle Avoidance}},
  AUTHOR = {Agishev, Ruslan and Tsykunov, Evgeny and Labazanova, Luiza and Tleugazy, Akerke and Tsetserukou, Dzmitry},
  URL = {https://hal.science/hal-02128383},
  BOOKTITLE = {{1st International Workshop on Human-Drone Interaction}},
  ADDRESS = {Glasgow, United Kingdom},
  ORGANIZATION = {{Ecole Nationale de l'Aviation Civile [ENAC]}},
  YEAR = {2019},
  MONTH = May,
  KEYWORDS = {Human ; robot interaction ; tactile display ; wearable computers ; robot formation motion planning ; impedance control ; potential fields},
  PDF = {https://hal.science/hal-02128383/file/HDI_2019_paper_14.pdf},
  HAL_ID = {hal-02128383},
  HAL_VERSION = {v1},
}
```

## License <a name="license"></a>
Project is distributed under [MIT License](https://github.com/RuslanAgishev/adaptive_swarm/blob/master/LICENSE)

adaptive_swarm

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README