arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.01487cs.ROcs.SYeess.SY
收藏

基于最优控制和强化学习的高约束空间多车冲突消解

Multi-vehicle Conflict Resolution in Highly Constrained Spaces by Merging Optimal Control and Reinforcement Learning

University of California at Berkeley(加州大学伯克利分校)

Xu Shen, Francesco Borrelli

摘要:

我们提出了一种新的方法来解决问题的多车辆冲突解决在高度受限的空间。一个最优控制问题,制定纳入非线性,非完整的车辆动力学和精确的防撞约束。首先在简化的离散环境中使用强化学习(RL)学习配置策略,然后使用这些策略来塑造原问题的约束空间,从而获得问题的解决方案。仿真结果表明,我们的方法可以探索有效的行动,以解决冲突在有限的空间,并产生灵巧的机动,是无碰撞和运动学上可行的。

英文摘要:

We present a novel method to address the problem of multi-vehicle conflict resolution in highly constrained spaces. An optimal control problem is formulated to incorporate nonlinear, non-holonomic vehicle dynamics and exact collision avoidance constraints. A solution to the problem can be obtained by first learning configuration strategies with reinforcement learning (RL) in a simplified discrete environment, and then using these strategies to shape the constraint space of the original problem. Simulation results show that our method can explore efficient actions to resolve conflicts in confined space and generate dexterous maneuvers that are both collision-free and kinematically feasible.

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。

↑