Scalable Learning of Safety Guarantees for Autonomous Systems using Hamilton-Jacobi Reachability
Scalable Learning of Safety Guarantees for Autonomous Systems using Hamilton-Jacobi Reachability
复制标题
DOI：
10.1109/icra48506.2021.9561561
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Sylvia L. Herbert;Jason J. Choi;Suvansh Qazi;Marsalis T. Gibson;K. Sreenath;C. Tomlin
中科院分区：
文献类型：
--
作者：
Sylvia L. Herbert;Jason J. Choi;Suvansh Qazi;Marsalis T. Gibson;K. Sreenath;C. Tomlin
像飞机和辅助机器人这样的自主系统经常在保证安全至关重要的情况下运行。Hamilton-Jacobi可达性方法可以为这类系统提供有保证的安全集和控制器。然而，这些相同的场景通常具有未知或不确定的环境、系统动力学或其他代理的预测。随着系统的运行，它可能会学习到有关这些不确定性的新知识，因此应该相应地更新其安全分析。然而，由于分析的计算复杂性，学习和更新安全分析的工作仅限于大约二维的小系统。本文综合了分解、热启动和自适应网格等提高计算速度的技术。使用这个新框架，我们可以比以前的工作快一个或多个数量级更新安全集，使该技术适用于许多现实系统。我们在模拟的2D和10D近悬停四轴飞行器上展示了我们的结果，这些飞行器在有风的环境中运行。
Autonomous systems like aircraft and assistive robots often operate in scenarios where guaranteeing safety is critical. Methods like Hamilton-Jacobi reachability can provide guaranteed safe sets and controllers for such systems. However, often these same scenarios have unknown or uncertain environments, system dynamics, or predictions of other agents. As the system is operating, it may learn new knowledge about these uncertainties and should therefore update its safety analysis accordingly. However, work to learn and update safety analysis is limited to small systems of about two dimensions due to the computational complexity of the analysis. In this paper we synthesize several techniques to speed up computation: decomposition, warm-starting, and adaptive grids. Using this new framework we can update safe sets by one or more orders of magnitude faster than prior work, making this technique practical for many realistic systems. We demonstrate our results on simulated 2D and 10D near-hover quadcopters operating in a windy environment.