Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity

TL;DR

This paper introduces a hierarchical approach to quality-diversity algorithms, enabling physical robots to adapt quickly to damages by efficiently learning and utilizing diverse skills, reducing complexity and failure rates.

Contribution

The paper presents the Hierarchical Trial and Error algorithm, which improves skill learning and adaptation in robots through hierarchical decomposition of behaviors.

Findings

Achieves 20% fewer actions in maze navigation in simulation.

Reduces actions by 43% in physical robot adaptation.

Decreases failure rates by 78% in challenging scenarios.

Abstract

In real-world environments, robots need to be resilient to damages and robust to unforeseen scenarios. Quality-Diversity (QD) algorithms have been successfully used to make robots adapt to damages in seconds by leveraging a diverse set of learned skills. A high diversity of skills increases the chances of a robot to succeed at overcoming new situations since there are more potential alternatives to solve a new task.However, finding and storing a large behavioural diversity of multiple skills often leads to an increase in computational complexity. Furthermore, robot planning in a large skill space is an additional challenge that arises with an increased number of skills. Hierarchical structures can help reducing this search and storage complexity by breaking down skills into primitive skills. In this paper, we introduce the Hierarchical Trial and Error algorithm, which uses a hierarchical behavioural repertoire to learn diverse skills and leverages them to make the robot adapt quickly in the physical world. We show that the hierarchical decomposition of skills enables the robot to learn more complex behaviours while keeping the learning of the repertoire tractable. Experiments with a hexapod robot show that our method solves a maze navigation tasks with 20% less actions in simulation, and 43% less actions in the physical world, for the most challenging scenarios than the best baselines while having 78% less complete failures.