Fast Convex Visual Foothold Adaptation for Quadrupedal Locomotion

TL;DR

This paper introduces a perception-based control framework for quadrupedal robots that rapidly identifies safe foothold regions using neural network regression and convex decomposition, enhancing locomotion safety and efficiency.

Contribution

It presents a novel combination of neural network approximation, convex decomposition, and MPC for fast, safe foothold adaptation in quadrupedal locomotion.

Findings

Successfully tested on HyQReal robot in simulation

Achieves faster foothold adaptation compared to previous methods

Demonstrates improved safety in dynamic terrains

Abstract

This extended abstract provides a short introduction on our recently developed perception-based controller for quadrupedal locomotion. Compared to our previous approach based on Visual Foothold Adaptation (VFA) and Model Predictive Control (MPC), our new framework combines a fast approximation of the safe foothold regions based on Neural Network regression, followed by a convex decomposition routine in order to generate safe landing areas where the controller can freely optimize the footholds location. The aforementioned framework, which combines prediction, convex decomposition, and MPC solution, is tested in simulation on our 140kg hydraulic quadruped robot (HyQReal).