Traversing Environments Using Possibility Graphs for Humanoid Robots

TL;DR

This paper introduces the Possibility Graph, a high-level planning framework that efficiently sequences multiple locomotion modes for humanoid robots to navigate complex, obstacle-rich environments.

Contribution

It presents a novel multi-modal motion planning method that rapidly explores action possibilities using high-level approximations, improving traversal efficiency in challenging terrains.

Findings

Successfully traverses complex environments with multiple action modes

Rapidly explores action possibilities using high-level approximations

Enables efficient sequencing of walking, crawling, and jumping

Abstract

Locomotion for legged robots poses considerable challenges when confronted by obstacles and adverse environments. Footstep planners are typically only designed for one mode of locomotion, but traversing unfavorable environments may require several forms of locomotion to be sequenced together, such as walking, crawling, and jumping. Multi-modal motion planners can be used to address some of these problems, but existing implementations tend to be time-consuming and are limited to quasi-static actions. This paper presents a motion planning method to traverse complex environments using multiple categories of actions. We introduce the concept of the "Possibility Graph", which uses high-level approximations of constraint manifolds to rapidly explore the "possibility" of actions, thereby allowing lower-level single-action motion planners to be utilized more efficiently. We show that the Possibility Graph can quickly find paths through several different challenging environments which require various combinations of actions in order to traverse.