E2R: a Hierarchical-Learning inspired Novelty-Search method to generate diverse repertoires of grasping trajectories

TL;DR

This paper introduces a hierarchical novelty search method for robotic grasping that efficiently generates diverse grasping trajectories, outperforming existing methods in success rate and diversity across multiple robot setups and objects.

Contribution

A novel hierarchical learning inspired novelty search approach for generating diverse grasping trajectories in a platform-agnostic way.

Findings

Outperforms state-of-the-art in diversity and success rate

Generates large, exploitable grasping repertoires

Effective across multiple robot configurations and objects

Abstract

Robotics grasping refers to the task of making a robotic system pick an object by applying forces and torques on its surface. Despite the recent advances in data-driven approaches, grasping remains an unsolved problem. Most of the works on this task are relying on priors and heavy constraints to avoid the exploration problem. Novelty Search (NS) refers to evolutionary algorithms that replace selection of best performing individuals with selection of the most novel ones. Such methods have already shown promising results on hard exploration problems. In this work, we introduce a new NS-based method that can generate large datasets of grasping trajectories in a platform-agnostic manner. Inspired by the hierarchical learning paradigm, our method decouples approach and prehension to make the behavioral space smoother. Experiments conducted on 3 different robot-gripper setups and on several standard objects shows that our method outperforms state-of-the-art for generating diverse repertoire of grasping trajectories, getting a higher successful run ratio, as well as a better diversity for both approach and prehension. Some of the generated solutions have been successfully deployed on a real robot, showing the exploitability of the obtained repertoires.