论文标题
更安全：使用重点和高效的轨迹搜索通过增强学习进行安全避免碰撞
SAFER: Safe Collision Avoidance using Focused and Efficient Trajectory Search with Reinforcement Learning
论文作者
论文摘要
避免碰撞是移动机器人和代理在现实世界中安全运作的关键。在这项工作中，我们提出了一种更安全的，这是一种有效，有效的避免碰撞系统，能够通过纠正操作员发送的控制命令来改善安全性。它结合了现实世界增强学习（RL），基于搜索的在线轨迹计划和自动紧急干预，例如自动紧急制动（AEB）。 RL的目的是学习一种有效的纠正控制动作，该动作用于集中搜索无碰撞轨迹，并减少触发自动紧急制动的频率。这种小说的设置使RL政策能够在现实世界中的室内环境中直接安全地学习移动机器人，即使在培训期间，实际崩溃也可以最大程度地减少。我们的实际实验表明，与多个基线相比，我们的方法具有更高的平均速度，更低的崩溃率，更少的紧急干预，较小的计算开销以及整体控制更平滑。
Collision avoidance is key for mobile robots and agents to operate safely in the real world. In this work we present SAFER, an efficient and effective collision avoidance system that is able to improve safety by correcting the control commands sent by an operator. It combines real-world reinforcement learning (RL), search-based online trajectory planning, and automatic emergency intervention, e.g. automatic emergency braking (AEB). The goal of the RL is to learn an effective corrective control action that is used in a focused search for collision-free trajectories, and to reduce the frequency of triggering automatic emergency braking. This novel setup enables the RL policy to learn safely and directly on mobile robots in a real-world indoor environment, minimizing actual crashes even during training. Our real-world experiments show that, when compared with several baselines, our approach enjoys a higher average speed, lower crash rate, less emergency intervention, smaller computation overhead, and smoother overall control.
