Singularity-Avoidance Control of Robotic Systems with Model Mismatch and Actuator Constraints

TL;DR

This paper introduces a learning-based control method using Gaussian processes and control barrier functions to avoid singularities in robotic systems with model mismatch and actuator constraints, validated through simulations.

Contribution

It presents a novel control strategy combining Gaussian process regression with CBFs to prevent singularities under model mismatch and actuator limits.

Findings

Effective singularity avoidance demonstrated in simulations

Bounded prediction error ensures safety and feasibility

Applicable to robots with actuator constraints

Abstract

Singularities, manifesting as special configuration states, deteriorate robot performance and may even lead to a loss of control over the system. This paper addresses the kinematic singularity concerns in robotic systems with model mismatch and actuator constraints through control barrier functions (CBFs). We propose a learning-based control strategy to prevent robots entering singularity regions. More precisely, we leverage Gaussian process (GP) regression to learn the unknown model mismatch, where the prediction error is restricted by a deterministic bound. Moreover, we offer the criteria for parameter selection to ensure the feasibility of CBFs subject to actuator constraints. The proposed approach is validated by high-fidelity simulations on a 2 degrees-of-freedom (DoFs) planar robot.