Fast and Continuous Foothold Adaptation for Dynamic Locomotion through CNNs

TL;DR

This paper introduces a real-time, CNN-based foothold adaptation method for legged robots that improves terrain navigation by adjusting foot placement reactively using visual feedback, achieving significant speed improvements.

Contribution

It presents a novel, fast CNN-based foothold classifier enabling continuous, reactive terrain adaptation for dynamic legged locomotion using only onboard sensors.

Findings

Up to 200 times faster computation than heuristic methods

Effective foothold adaptation improves robot stability and safety

Validated on HyQ robot in simulated and real environments

Abstract

Legged robots can outperform wheeled machines for most navigation tasks across unknown and rough terrains. For such tasks, visual feedback is a fundamental asset to provide robots with terrain-awareness. However, robust dynamic locomotion on difficult terrains with real-time performance guarantees remains a challenge. We present here a real-time, dynamic foothold adaptation strategy based on visual feedback. Our method adjusts the landing position of the feet in a fully reactive manner, using only on-board computers and sensors. The correction is computed and executed continuously along the swing phase trajectory of each leg. To efficiently adapt the landing position, we implement a self-supervised foothold classifier based on a Convolutional Neural Network (CNN). Our method results in an up to 200 times faster computation with respect to the full-blown heuristics. Our goal is to react to visual stimuli from the environment, bridging the gap between blind reactive locomotion and purely vision-based planning strategies. We assess the performance of our method on the dynamic quadruped robot HyQ, executing static and dynamic gaits (at speeds up to 0.5 m/s) in both simulated and real scenarios; the benefit of safe foothold adaptation is clearly demonstrated by the overall robot behavior.