arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.03314eess.SYcs.LGcs.MAcs.ROcs.SY
收藏

具有学习策略的多智能体系统的碰撞避免验证

Collision Avoidance Verification of Multiagent Systems with Learned Policies

Northeastern University(东北大学);Google(谷歌公司)

Zihao Dong, Shayegan Omidshafiei, Michael Everett

AI总结:

本文提出一种基于后向可达性的方法,通过离线求解MILPs计算相对反投影集合并在线求解LPs,验证多智能体神经网络反馈回路的碰撞避免特性,支持状态不确定性且可扩展至10个智能体。

摘要:

对于许多多智能体控制问题,神经网络(NNs)已经实现了有前景的新能力。然而,这些系统中的许多缺乏形式化保证(例如,碰撞避免、鲁棒性),这阻碍了在安全关键设置中利用这些进步。尽管最近有关于NN控制系统形式化验证的工作,但大多数现有技术无法处理超过一个智能体的场景。为了解决这一研究空白,本文提出了一种基于后向可达性的方法,用于验证多智能体神经网络反馈回路(MA-NFLs)的碰撞避免特性。给定每个智能体的动力学模型和训练好的控制策略,所提出的算法通过离线为每对智能体(同时)求解一系列混合整数线性规划(MILPs)来计算相对反投影集合。我们考虑了状态测量不确定性,使其与真实世界场景高度契合。利用这些结果,智能体可以通过求解低维线性规划(LPs)在线快速检查碰撞避免。我们证明所提出的算法可以验证MA-NFL的无碰撞特性,其中智能体经过训练以模仿碰撞避免算法(互惠速度障碍)。我们进一步在多达10个智能体的系统上展示了该方法的计算可扩展性。

英文摘要:

For many multiagent control problems, neural networks (NNs) have enabled promising new capabilities. However, many of these systems lack formal guarantees (e.g., collision avoidance, robustness), which prevents leveraging these advances in safety-critical settings. While there is recent work on formal verification of NN-controlled systems, most existing techniques cannot handle scenarios with more than one agent. To address this research gap, this paper presents a backward reachability-based approach for verifying the collision avoidance properties of Multi-Agent Neural Feedback Loops (MA-NFLs). Given the dynamics models and trained control policies of each agent, the proposed algorithm computes relative backprojection sets by (simultaneously) solving a series of Mixed Integer Linear Programs (MILPs) offline for each pair of agents. We account for state measurement uncertainties, making it well aligned with real-world scenarios. Using those results, the agents can quickly check for collision avoidance online by solving low-dimensional Linear Programs (LPs). We demonstrate the proposed algorithm can verify collision-free properties of a MA-NFL with agents trained to imitate a collision avoidance algorithm (Reciprocal Velocity Obstacles). We further demonstrate the computational scalability of the approach on systems with up to 10 agents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑