GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Control

2024-01-25

arXiv.org

AI Summary

To address distributed safe coordination of large-scale multi-agent systems (MAS) in cluttered environments, this paper proposes Graph Control Barrier Functions (GCBFs), a novel paradigm that achieves global safety guarantees for arbitrarily sized MAS using a single, unified safety certificate. The method integrates graph neural networks with distributed control: leveraging local LiDAR point-cloud perception, it constructs a GCBF-enhanced neural training framework capable of modeling nonlinear agent dynamics and enabling real-time collision avoidance. In experiments with a 1,000-drone swarm, the approach achieves a safety rate of 99.7%, outperforming handcrafted CBFs by 20% and state-of-the-art reinforcement learning methods by 40%, while preserving task completion performance. Key contributions include: (i) a unified, certificate-based safety formulation; (ii) scalable, graph-structured distributed control; and (iii) an end-to-end distributed architecture tightly coupling perception, decision-making, and control.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Natural Language Processing: Safety and Robustness
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Distributed, scalable, and safe control of large-scale multi-agent systems is a challenging problem. In this paper, we design a distributed framework for safe multi-agent control in large-scale environments with obstacles, where a large number of agents are required to maintain safety using only local information and reach their goal locations. We introduce a new class of certificates, termed graph control barrier function (GCBF), which are based on the well-established control barrier function theory for safety guarantees and utilize a graph structure for scalable and generalizable distributed control of MAS. We develop a novel theoretical framework to prove the safety of an arbitrary-sized MAS with a single GCBF. We propose a new training framework GCBF+ that uses graph neural networks to parameterize a candidate GCBF and a distributed control policy. The proposed framework is distributed and is capable of taking point clouds from LiDAR, instead of actual state information, for real-world robotic applications. We illustrate the efficacy of the proposed method through various hardware experiments on a swarm of drones with objectives ranging from exchanging positions to docking on a moving target without collision. Additionally, we perform extensive numerical experiments, where the number and density of agents, as well as the number of obstacles, increase. Empirical results show that in complex environments with agents with nonlinear dynamics (e.g., Crazyflie drones), GCBF+ outperforms the hand-crafted CBF-based method with the best performance by up to 20% for relatively small-scale MAS with up to 256 agents, and leading reinforcement learning (RL) methods by up to 40% for MAS with 1024 agents. Furthermore, the proposed method does not compromise on the performance, in terms of goal reaching, for achieving high safety rates, which is a common trade-off in RL-based methods.

Problem

• Multi-Robot Systems
• Obstacle Avoidance
• Collision Prevention

Innovation

• GCBF+
• multi-robot collaboration
• collision avoidance