A Compositional Neuro-Controller for Advanced Motor Control Tasks

TL;DR

This paper introduces a biologically inspired compositional neuro-controller that enables efficient incremental learning and switching between multiple motor control styles in robotics, inspired by the modular structure of biological motor systems.

Contribution

The paper proposes a novel modular neuro-controller that improves learning efficiency and adaptability for complex motor tasks in robotics, inspired by biological systems.

Findings

The compositional controller outperforms simple controllers in trajectory reproduction.

It can learn and switch between multiple locomotion styles.

Demonstrated effectiveness on a simulated snake robot.

Abstract

Humans and animals developed a sophisticated motor control apparatus and there is much evidence that it has a modular structure. The modularity offers a range of benefits, e.g. ability to learn dissociable motion styles without interference and forgetting, fast adaptation and de-adaptation to changes conditions. However in robotics, building a controller that can efficiently incrementally learn new motion styles and provide switching between them is a formidable challenge. In this paper we address the problem by proposing a novel biologically inspired compositional neuro-controller. We have shown that the compositional controller is able to reproduce a set of trajectories more efficiently comparing to a simple controller, exploiting incremental learning benefits. Second, we have demonstrated that the proposed controller is able to learn different locomotion styles and switch between them in a simulated robot-snake.