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.

翻译：从幻觉中学习(LfH)是最近自主航行的机器学习模式,它使用在完全安全的环境中收集的培训数据,并增加了许多想象障碍,使环境受到高度限制,学习即使在高度受限制(更危险)空间也产生可行导航的导航规划人员。然而,LfH要求在部署期间对机器人的认知进行幻觉,以便与幻觉培训数据相匹配,这就需要有时无法实现的先前知识,并往往产生非常保守的规划。在这项工作中,我们提出了一个新的LfH模式,不需要运行时间幻觉,我们称之为“软性部署”的特征,因此可以适应更现实的导航情景。这个新型的Halluced学习和Sober部署(HLSD)模式在300个模拟导航环境的基准测试中进行了测试,这些模拟环境具有广泛的困难程度,在现实世界中也存在。在大多数情况下,HLSD超越了原始LFH方法和经典导航规划员。