Dynamic Motion Modelling for Legged Robots

TL;DR

This paper introduces the Dynamic Gaussian Mixture Model (DGMM), a novel approach for automatically learning and improving motion models of legged robots by integrating sensory data, validated on complex robots and benchmark datasets.

Contribution

The paper presents DGMM, a new motion model representation that reduces manual design effort and incorporates sensory data for enhanced accuracy in legged robot motion modeling.

Findings

DGMM effectively learns complex robot motion models.

Incorporating terrain data improves model accuracy.

Validated on an 8-legged robot and benchmark datasets.

Abstract

An accurate motion model is an important component in modern-day robotic systems, but building such a model for a complex system often requires an appreciable amount of manual effort. In this paper we present a motion model representation, the Dynamic Gaussian Mixture Model (DGMM), that alleviates the need to manually design the form of a motion model, and provides a direct means of incorporating auxiliary sensory data into the model. This representation and its accompanying algorithms are validated experimentally using an 8-legged kinematically complex robot, as well as a standard benchmark dataset. The presented method not only learns the robot's motion model, but also improves the model's accuracy by incorporating information about the terrain surrounding the robot.