A Novel Adaptive Controller for Robot Manipulators based on Active Inference

TL;DR

This paper introduces a biologically inspired active inference controller for robot manipulators that enhances adaptability and robustness against large model uncertainties, outperforming traditional adaptive controllers in experiments.

Contribution

It formulates active inference as a control law for robots, providing a scalable, model-free approach that improves adaptability over existing methods.

Findings

AIC outperforms MRAC in adaptability.

AIC maintains high performance with unmodeled dynamics.

The method is scalable to high degrees-of-freedom.

Abstract

More adaptive controllers for robot manipulators are needed, which can deal with large model uncertainties. This paper presents a novel active inference controller (AIC) as an adaptive control scheme for industrial robots. This scheme is easily scalable to high degrees-of-freedom, and it maintains high performance even in the presence of large unmodeled dynamics. The proposed method is based on active inference, a promising neuroscientific theory of the brain, which describes a biologically plausible algorithm for perception and action. In this work, we formulate active inference from a control perspective, deriving a model-free control law which is less sensitive to unmodeled dynamics. The performance and the adaptive properties of the algorithm are compared to a state-of-the-art model reference adaptive controller (MRAC) in an experimental setup with a real 7-DOF robot arm. The results showed that the AIC outperformed the MRAC in terms of adaptability, providing a more general control law. This confirmed the relevance of active inference for robot control.