English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Robotics grasping refers to the task of making a robotic system pick anobject by applying forces and torques on its surface. Despite the recentadvances in data-driven approaches, grasping remains an unsolved problem. Mostof the works on this task are relying on priors and heavy constraints to avoidthe exploration problem. Novelty Search (NS) refers to evolutionary algorithmsthat replace selection of best performing individuals with selection of themost novel ones. Such methods have already shown promising results on hardexploration problems. In this work, we introduce a new NS-based method that cangenerate large datasets of grasping trajectories in a platform-agnostic manner.Inspired by the hierarchical learning paradigm, our method decouples approachand prehension to make the behavioral space smoother. Experiments conducted on3 different robot-gripper setups and on several standard objects shows that ourmethod outperforms state-of-the-art for generating diverse repertoire ofgrasping trajectories, getting a higher successful run ratio, as well as abetter diversity for both approach and prehension. Some of the generatedsolutions have been successfully deployed on a real robot, showing theexploitability of the obtained repertoires.

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