Quality Diversity under Sparse Reward and Sparse Interaction: Application to Grasping in Robotics

TL;DR

This paper explores how Quality-Diversity algorithms can be effectively applied to robotic grasping tasks characterized by reward and behavioral sparsity, demonstrating superior performance over existing methods.

Contribution

It introduces a comprehensive evaluation framework and shows that MAP-Elites variants outperform other methods in sparse grasping scenarios.

Findings

MAP-Elites variants outperform other methods significantly

Sparse interaction can cause deceptive novelty

First demonstration of efficient grasping trajectory generation

Abstract

Quality-Diversity (QD) methods are algorithms that aim to generate a set of diverse and high-performing solutions to a given problem. Originally developed for evolutionary robotics, most QD studies are conducted on a limited set of domains - mainly applied to locomotion, where the fitness and the behavior signal are dense. Grasping is a crucial task for manipulation in robotics. Despite the efforts of many research communities, this task is yet to be solved. Grasping cumulates unprecedented challenges in QD literature: it suffers from reward sparsity, behavioral sparsity, and behavior space misalignment. The present work studies how QD can address grasping. Experiments have been conducted on 15 different methods on 10 grasping domains, corresponding to 2 different robot-gripper setups and 5 standard objects. An evaluation framework that distinguishes the evaluation of an algorithm from its internal components has also been proposed for a fair comparison. The obtained results show that MAP-Elites variants that select successful solutions in priority outperform all the compared methods on the studied metrics by a large margin. We also found experimental evidence that sparse interaction can lead to deceptive novelty. To our knowledge, the ability to efficiently produce examples of grasping trajectories demonstrated in this work has no precedent in the literature.