Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination

arXiv:2403.17231v1 Announce Type: cross
Abstract: This paper presents a self-supervised learning method to safely learn a motion planner for ground robots to navigate environments with dense and dynamic obstacles. When facing highly-cluttered, fast-moving, hard-to-predict obstacles, classical motion planners may not be able to keep up with limited onboard computation. For learning-based planners, high-quality demonstrations are difficult to acquire for imitation learning while reinforcement learning becomes inefficient due to the high probability of collision during exploration. To safely and efficiently provide …

abstract agile arxiv computation cs.lg cs.ro dynamic environments hallucination learn moving navigation obstacles paper robots self-supervised learning supervised learning type