sh221by/ftncbf

Fault-Tolerant Neural CBF

Fault Tolerant Neural Control Barrier Functions

Fault Tolerant Neural Control Barrier Functions for Robotic Systems under Sensor Faults and Attacks (ICRA 2024)
Full Paper »

Table of Contents

1. Experiments
2. Getting Started
   • Installation
   • Run the Code
3. Citation
4. License
5. Contact
6. Acknowledgments

Experiments

Obstacle Avoidance: We evaluate our proposed method on a controlled system [1]. We consider an Unmanned Aerial Vehicle (UAV) to avoid collision with a tree trunk. We model the system as a Dubins-style [2] aircraft model. The system state consists of a 2D position and aircraft yaw rate $x:=[x_1, x_2, \psi]^T$. We let $u$ denote the control input to manipulate the yaw rate and the dynamics defined in the supplement. We train the NCBF via the method proposed in [3] with $v$ assumed to be $1$ and the control law $u$ designed as $u=\mu_{nom}(x)=-\sin \psi+3 \cdot \frac{x_1 \cdot \sin \psi+x_2 \cdot \cos \psi}{0.5+x_1^2+x_2^2}$.

Spacecraft Rendezvous: We evaluate our approach to a spacecraft rendezvous problem from [5]. A station-keeping controller is required to keep the "chaser" satellite within a certain relative distance from the "target" satellite. The state of the chaser is expressed relative to the target using linearized Clohessy–Wiltshire–Hill equations, with state $x=[p_x, p_y, p_z, v_x, v_y, v_z]^T$, control input $u=[u_x, u_y, u_z]^T$ and dynamics defined in the supplement. We train the NCBF as in [6].

(back to top)

Getting Started

This is an example of how you may give instructions on setting up your project locally. To get a local copy up and running follow these simple example steps.

Installation

Clone the repo and navigate to the folder

git clone https://github.com/HongchaoZhang-HZ/FTNCBF.git

cd FTNCBF

Install packages via pip

pip install -r requirements.txt

Run the code

Choose the system and corresponding NCBFs, e.g., train NCBF for vehicle obstacle avoidance, to train by running the code

python main_Obs.py

Run Obstacle Avoidance in Carla

Copy code and the trained NCBF to Carla folder PythonAPI/examples, and run

python main.py

(back to top)

Citation

If our work is useful for your research, please consider citing:

@INPROCEEDINGS{zhang2024fault,
  author={Zhang, Hongchao and Niu, Luyao and Clark, Andrew and Poovendran, Radha},
  booktitle={2024 IEEE International Conference on Robotics and Automation (ICRA)}, 
  title={Fault Tolerant Neural Control Barrier Functions for Robotic Systems under Sensor Faults and Attacks}, 
  year={2024},
  volume={},
  number={}}

(back to top)

License

Distributed under the MIT License. See LICENSE.txt for more information.

(back to top)

Contact

If you have any questions, please feel free to reach out to us.

Hongchao Zhang - Homepage - [email protected]

(back to top)

Acknowledgments

This research was supported by the AFOSR (grants FA9550-22-1-0054 and FA9550-23-1-0208), and NSF (grants CNS-1941670).

(back to top)