论文标题
敏捷的机器人通过幻觉学习和清醒部署导航
Agile Robot Navigation through Hallucinated Learning and Sober Deployment
论文作者
论文摘要
从幻觉中学习（LFH）是一种用于自动导航的机器学习范式，它使用在完全安全的环境中收集的训练数据，并添加了许多虚构的障碍，以使环境受到密切约束，学习导航计划者，即使在高度危险（更危险）的空间中，也会产生可行的导航。但是，LFH需要在部署过程中幻觉使机器人感知与幻觉的培训数据相匹配，这会导致有时不可行的先验知识，并且倾向于产生非常保守的计划。在这项工作中，我们提出了一种新的LFH范式，该范式不需要运行时幻觉 - 我们称为“清醒部署”的功能 - 因此可以适应更现实的导航方案。这种新颖的幻觉学习和清醒部署（HLSD）范式在300个模拟导航环境的基准测试中进行了测试，这些导航环境具有广泛的难度水平，以及在现实世界中。在大多数情况下，HLSD的表现均优于原始LFH方法和经典导航计划者。
Learning from Hallucination (LfH) is a recent machine learning paradigm for autonomous navigation, which uses training data collected in completely safe environments and adds numerous imaginary obstacles to make the environment densely constrained, to learn navigation planners that produce feasible navigation even in highly constrained (more dangerous) spaces. However, LfH requires hallucinating the robot perception during deployment to match with the hallucinated training data, which creates a need for sometimes-infeasible prior knowledge and tends to generate very conservative planning. In this work, we propose a new LfH paradigm that does not require runtime hallucination -- a feature we call "sober deployment" -- and can therefore adapt to more realistic navigation scenarios. This novel Hallucinated Learning and Sober Deployment (HLSD) paradigm is tested in a benchmark testbed of 300 simulated navigation environments with a wide range of difficulty levels, and in the real-world. In most cases, HLSD outperforms both the original LfH method and a classical navigation planner.
