A Hybrid Approach for Trajectory Control Design

TL;DR

This paper introduces a hybrid control design method that integrates Gaussian Processes to improve trajectory tracking by reducing unmodeled dynamics, demonstrated through real and simulated experiments.

Contribution

It presents a novel data-driven control approach embedding Gaussian Processes for trajectory tracking without complex terramechanics modeling.

Findings

Effective reduction of unmodeled dynamics

Successful implementation in real and simulated environments

Enhanced trajectory tracking performance

Abstract

This work presents a methodology to design trajectory tracking feedback control laws, which embed non-parametric statistical models, such as Gaussian Processes (GPs). The aim is to minimize unmodeled dynamics such as undesired slippages. The proposed approach has the benefit of avoiding complex terramechanics analysis to directly estimate from data the robot dynamics on a wide class of trajectories. Experiments in both real and simulated environments prove that the proposed methodology is promising.