ARMOR: Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning

TL;DR

ARMOR is a novel egocentric perception system for humanoid robots that improves collision avoidance and motion planning by integrating wearable-like sensors and a transformer-based imitation learning policy, demonstrating significant reductions in collisions and computational latency.

Contribution

The paper introduces ARMOR, a new perception system combining hardware and software, and a transformer-based IL policy for dynamic collision avoidance in humanoid robots.

Findings

63.7% reduction in collisions

78.7% improvement in success rate

26x reduction in computational latency

Abstract

Humanoid robots have significant gaps in their sensing and perception, making it hard to perform motion planning in dense environments. To address this, we introduce ARMOR, a novel egocentric perception system that integrates both hardware and software, specifically incorporating wearable-like depth sensors for humanoid robots. Our distributed perception approach enhances the robot's spatial awareness, and facilitates more agile motion planning. We also train a transformer-based imitation learning (IL) policy in simulation to perform dynamic collision avoidance, by leveraging around 86 hours worth of human realistic motions from the AMASS dataset. We show that our ARMOR perception is superior against a setup with multiple dense head-mounted, and externally mounted depth cameras, with a 63.7% reduction in collisions, and 78.7% improvement on success rate. We also compare our IL policy against a sampling-based motion planning expert cuRobo, showing 31.6% less collisions, 16.9% higher success rate, and 26x reduction in computational latency. Lastly, we deploy our ARMOR perception on our real-world GR1 humanoid from Fourier Intelligence. We are going to update the link to the source code, HW description, and 3D CAD files in the arXiv version of this text.