随机动力系统的保守安全性
Conservative Safety Monitors of Stochastic Dynamical Systems
摘要:
为自治系统生成准确的运行时安全评估对于确保其持续增长至关重要。然而,关于未来行为的详尽推理通常太复杂而无法在运行时完成。为了提供可扩展的和正式的安全性估计,我们提出了一种方法,利用设计时模型检验结果在运行时。具体来说,我们建模的系统作为一个概率自动机(PA)和计算有界时间可达性概率的PA在设计时的状态。在运行时,我们结合分布的状态估计与模型检验的结果,产生一个有界时间的安全估计。我们认为,我们的方法产生校准良好的安全概率,假设估计的状态分布是校准良好的。我们在模拟水箱上评估我们的方法。
英文摘要:
Generating accurate runtime safety estimates for autonomous systems is vital to ensuring their continued proliferation. However, exhaustive reasoning about future behaviors is generally too complex to do at runtime. To provide scalable and formal safety estimates, we propose a method for leveraging design-time model checking results at runtime. Specifically, we model the system as a probabilistic automaton (PA) and compute bounded-time reachability probabilities over the states of the PA at design time. At runtime, we combine distributions of state estimates with the model checking results to produce a bounded time safety estimate. We argue that our approach produces well-calibrated safety probabilities, assuming the estimated state distributions are well-calibrated. We evaluate our approach on simulated water tanks.
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。