Evolving a Behavioral Repertoire for a Walking Robot

TL;DR

This paper introduces TBR-Evolution, an innovative evolutionary algorithm that efficiently develops a diverse set of walking controllers for a hexapod robot, enabling it to reach any point in its reachable space with minimal real-world experiments.

Contribution

The paper presents a novel transferability-based evolutionary algorithm that rapidly evolves a comprehensive repertoire of walking behaviors for legged robots.

Findings

Learned a diverse set of controllers with only a few dozen experiments.

Enabled the robot to reach every point in its reachable space.

Demonstrated faster evolution compared to independent controller development.

Abstract

Numerous algorithms have been proposed to allow legged robots to learn to walk. However, the vast majority of these algorithms is devised to learn to walk in a straight line, which is not sufficient to accomplish any real-world mission. Here we introduce the Transferability-based Behavioral Repertoire Evolution algorithm (TBR-Evolution), a novel evolutionary algorithm that simultaneously discovers several hundreds of simple walking controllers, one for each possible direction. By taking advantage of solutions that are usually discarded by evolutionary processes, TBR-Evolution is substantially faster than independently evolving each controller. Our technique relies on two methods: (1) novelty search with local competition, which searches for both high-performing and diverse solutions, and (2) the transferability approach, which com-bines simulations and real tests to evolve controllers for a physical robot. We evaluate this new technique on a hexapod robot. Results show that with only a few dozen short experiments performed on the robot, the algorithm learns a repertoire of con-trollers that allows the robot to reach every point in its reachable space. Overall, TBR-Evolution opens a new kind of learning algorithm that simultaneously optimizes all the achievable behaviors of a robot.