arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07667cs.AI
收藏

运行时安全指导的策略修复

Runtime-Safety-Guided Policy Repair

Boston University(波士顿大学);Nanyang Technological University(南洋理工大学);Toyota Motor North America R&D(丰田汽车北美研发);Carnegie Mellon University(卡内基梅隆大学)

Weichao Zhou, Ruihan Gao, BaekGyu Kim, Eunsuk Kang, Wenchao Li

摘要:

我们研究了安全关键设置中基于学习的控制策略的策略修复问题。我们考虑一个架构,其中一个高性能的基于学习的控制策略(例如,一个训练为神经网络)与基于模型的安全控制器配对。安全控制器被赋予预测训练的策略是否会导致系统进入不安全状态的能力,并在必要时接管控制。虽然这种架构可以提供额外的安全保证,但在训练策略和安全控制器之间的间歇和频繁切换可能导致不期望的行为和降低的性能。我们建议减少或甚至消除控制切换的“修复”训练的安全控制器所产生的运行时数据的基础上的方式,从原来的政策偏离最小的政策。我们的方法背后的关键思想是制定一个轨迹优化问题,允许联合推理的政策更新和安全约束。实验结果表明,我们的方法是有效的,即使在安全控制器中的系统模型是未知的,只是近似。

英文摘要:

We study the problem of policy repair for learning-based control policies in safety-critical settings. We consider an architecture where a high-performance learning-based control policy (e.g. one trained as a neural network) is paired with a model-based safety controller. The safety controller is endowed with the abilities to predict whether the trained policy will lead the system to an unsafe state, and take over control when necessary. While this architecture can provide added safety assurances, intermittent and frequent switching between the trained policy and the safety controller can result in undesirable behaviors and reduced performance. We propose to reduce or even eliminate control switching by `repairing' the trained policy based on runtime data produced by the safety controller in a way that deviates minimally from the original policy. The key idea behind our approach is the formulation of a trajectory optimization problem that allows the joint reasoning of policy update and safety constraints. Experimental results demonstrate that our approach is effective even when the system model in the safety controller is unknown and only approximated.

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。

↑