ViT-A*: Legged Robot Path Planning using Vision Transformer A*

TL;DR

This paper introduces ViT-A*, a neural network-based path planning method for quadruped robots that uses Vision Transformers for map processing, enabling effective navigation in complex environments.

Contribution

It presents a novel end-to-end differentiable path planner utilizing Vision Transformers to improve map handling for legged robot navigation.

Findings

Effective path planning demonstrated on Boston Dynamics Spot.

Handles larger maps efficiently with ViT preprocessing.

Reliable navigation in complex terrains shown in experiments.

Abstract

Legged robots, particularly quadrupeds, offer promising navigation capabilities, especially in scenarios requiring traversal over diverse terrains and obstacle avoidance. This paper addresses the challenge of enabling legged robots to navigate complex environments effectively through the integration of data-driven path-planning methods. We propose an approach that utilizes differentiable planners, allowing the learning of end-to-end global plans via a neural network for commanding quadruped robots. The approach leverages 2D maps and obstacle specifications as inputs to generate a global path. To enhance the functionality of the developed neural network-based path planner, we use Vision Transformers (ViT) for map pre-processing, to enable the effective handling of larger maps. Experimental evaluations on two real robotic quadrupeds (Boston Dynamics Spot and Unitree Go1) demonstrate the effectiveness and versatility of the proposed approach in generating reliable path plans.