Risk-Aware Decentralized Safe Control via Dynamic Responsibility Allocation (Student Abstract)

Abstract

In this work, we present a novel risk-aware decentralized Control Barrier Function (CBF)-based controller for multi-agent systems. The proposed decentralized controller is composed based on pairwise agent responsibility shares (a percentage), calculated from the risk evaluation of each individual agent faces in a multi-agent interaction environment. With our proposed CBF-inspired risk evaluation framework, the responsibility portions between pairwise agents are dynamically updated based on the relative risk they face. Our method allows agents with lower risk to enjoy a higher level of freedom in terms of a wider action space, and the agents exposed to higher risk are constrained more tightly on action spaces, and are therefore forced to proceed with caution.

Cite

Text

Lyu et al. "Risk-Aware Decentralized Safe Control via Dynamic Responsibility Allocation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.26998

Markdown

[Lyu et al. "Risk-Aware Decentralized Safe Control via Dynamic Responsibility Allocation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/lyu2023aaai-risk/) doi:10.1609/AAAI.V37I13.26998

BibTeX

@inproceedings{lyu2023aaai-risk,
  title     = {{Risk-Aware Decentralized Safe Control via Dynamic Responsibility Allocation (Student Abstract)}},
  author    = {Lyu, Yiwei and Luo, Wenhao and Dolan, John M.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16276-16277},
  doi       = {10.1609/AAAI.V37I13.26998},
  url       = {https://mlanthology.org/aaai/2023/lyu2023aaai-risk/}
}