TOP-Nav: Legged Navigation Integrating Terrain, Obstacle and Proprioception Estimation

arXiv:2404.15256v1 Announce Type: cross
Abstract: Legged navigation is typically examined within open-world, off-road, and challenging environments. In these scenarios, estimating external disturbances requires a complex synthesis of multi-modal information. This underlines a major limitation in existing works that primarily focus on avoiding obstacles. In this work, we propose TOP-Nav, a novel legged navigation framework that integrates a comprehensive path planner with Terrain awareness, Obstacle avoidance and close-loop Proprioception. TOP-Nav underscores the synergies between vision and proprioception in both path and …

abstract arxiv cs.ai cs.cv cs.ro cs.sy eess.sy environments focus information major modal multi-modal navigation novel obstacles open-world proprioception synthesis type work world