A Fast, Autonomous, Bipedal Walking Behavior over Rapid Regions

TL;DR

This paper presents a novel autonomous bipedal walking system for humanoid robots that integrates rapid perception, planning, and control algorithms to enable fast, continuous locomotion over complex terrains.

Contribution

It introduces a new behavior control system combining recent perception and planning algorithms with a momentum-based controller for efficient bipedal walking.

Findings

Achieves fast, continuous walking without pauses or deliberation.

Integrates perception, planning, and control into a unified system.

Demonstrates effective locomotion over rough terrain.

Abstract

In trying to build humanoid robots that perform useful tasks in a world built for humans, we address the problem of autonomous locomotion. Humanoid robot planning and control algorithms for walking over rough terrain are becoming increasingly capable. At the same time, commercially available depth cameras have been getting more accurate and GPU computing has become a primary tool in AI research. In this paper, we present a newly constructed behavior control system for achieving fast, autonomous, bipedal walking, without pauses or deliberation. We achieve this using a recently published rapid planar regions perception algorithm, a height map based body path planner, an A* footstep planner, and a momentum-based walking controller. We put these elements together to form a behavior control system supported by modern software development practices and simulation tools.