LP-NavOA: Integrated Local Navigation and Obstacle Avoidance for Humanoid Robots under Limited Perception

2026-06-22

AI Summary

This work addresses the challenge of enabling humanoid robots to simultaneously achieve obstacle avoidance, sparse goal recovery, and whole-body motion stability in cluttered environments with limited perception. The authors propose LP-NavOA, a novel framework that decouples a frozen whole-body motion policy from a lightweight recurrent local planner, achieving end-to-end navigation using only proprioception, short-range ranging, and goal direction in the robot’s body frame. The approach leverages ray-conditioned PPO training, A*-guided waypoint distillation, and a circular velocity–heading command interface that overrides heading without requiring a global map or external planner. In MuJoCo simulations, on-time arrival rates improve from 38–40% to 85–97%, substantially reducing contact-intensive locomotion; real-world experiments on the Unitree G1 platform further demonstrate successful deployment without human intervention.

Abstract

Humanoid local navigation in cluttered environments must jointly resolve obstacle avoidance, sparse-goal recovery, and stable whole-body locomotion under short-range and partially observable sensing. Explicit planner-control decompositions introduce latency and can mismatch agile humanoid command-tracking limits, while purely reactive controllers may lose the goal after obstacle occlusion. We present LP-NavOA, a limited-perception navigation and obstacle-avoidance framework for humanoid robots. A raycast-conditioned perception-action proximal policy optimization (PPO) locomotion backbone is first trained with a robot-centered circular heading-speed command and a shared command-side safety filter. With this backbone frozen, A-star and waypoint teachers generate rollouts for distilling a recurrent local planner that overwrites only the heading command at deployment, leaving the whole-body policy intact. At runtime, LP-NavOA uses proprioception, short-range local range sensing, and a body-frame goal direction, requiring no global map, waypoint stream, or external planner. In MuJoCo open-wall and indoor layouts, the distilled planner produces obstacle bypassing and post-avoidance goal recovery, raising teacher-calibrated on-time arrival from 38--40\% to 85--97\% and reducing brush/contact-heavy progress relative to a backbone-only controller. Ablations show that dynamic route shaping, teacher-active data collection, and the circular command interface are important for navigation efficiency and for training the 3.0\,m/s backbone. A Unitree G1 deployment analysis demonstrates hardware executability without continuous joystick steering.

Problem

• humanoid navigation
• obstacle avoidance
• limited perception
• local planning
• whole-body locomotion

Innovation

• humanoid navigation
• limited perception
• policy distillation
• obstacle avoidance
• whole-body locomotion