Recent Approaches for Perceptive Legged Locomotion

TL;DR

This paper reviews recent methods enabling legged robots to perceive their environment in real-time, highlighting the challenges and solutions for integrating vision with complex locomotion controllers in unstructured terrains.

Contribution

It compares three recent perceptive locomotion approaches, analyzing how vision is integrated to improve autonomous legged robot navigation in complex environments.

Findings

Different vision integration strategies are effective for robust locomotion.

Perceptive approaches enhance obstacle avoidance and terrain adaptation.

Challenges remain in real-time perception and control coordination.

Abstract

As both legged robots and embedded compute have become more capable, researchers have started to focus on field deployment of these robots. Robust autonomy in unstructured environments requires perception of the world around the robot in order to avoid hazards. However, incorporating perception online while maintaining agile motion is more challenging for legged robots than other mobile robots due to the complex planners and controllers required to handle the dynamics of locomotion. This report will compare three recent approaches for perceptive locomotion and discuss the different ways in which vision can be used to enable legged autonomy.