Collision-Free Humanoid Traversal in Cluttered Indoor Scenes

TL;DR

This paper introduces HumanoidPF, a novel representation for collision-free humanoid navigation in cluttered indoor environments, enabling effective RL-based traversal and successful real-world transfer with minimal sim-to-real gap.

Contribution

We propose HumanoidPF, a new collision-free motion encoding that improves humanoid navigation in cluttered scenes and demonstrates effective sim-to-real transfer.

Findings

HumanoidPF significantly facilitates RL-based traversal skill learning.

The method exhibits a negligible sim-to-real gap in experiments.

Successful real-world deployment with a teleoperation system.

Abstract

We study the problem of collision-free humanoid traversal in cluttered indoor scenes, such as hurdling over objects scattered on the floor, crouching under low-hanging obstacles, or squeezing through narrow passages. To achieve this goal, the humanoid needs to map its perception of surrounding obstacles with diverse spatial layouts and geometries to the corresponding traversal skills. However, the lack of an effective representation that captures humanoid-obstacle relationships during collision avoidance makes directly learning such mappings difficult. We therefore propose Humanoid Potential Field (HumanoidPF), which encodes these relationships as collision-free motion directions, significantly facilitating RL-based traversal skill learning. We also find that HumanoidPF exhibits a surprisingly negligible sim-to-real gap as a perceptual representation. To further enable generalizable traversal skills through diverse and challenging cluttered indoor scenes, we further propose a hybrid scene generation method, incorporating crops of realistic 3D indoor scenes and procedurally synthesized obstacles. We successfully transfer our policy to the real world and develop a teleoperation system where users could command the humanoid to traverse in cluttered indoor scenes with just a single click. Extensive experiments are conducted in both simulation and the real world to validate the effectiveness of our method. Demos and code can be found in our website: https://axian12138.github.io/CAT/.