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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper presents a novel approach to generalizing robot manipulationskills by combining a sampling-based task-and-motion planner with an offlinereinforcement learning algorithm. Starting with a small library of scriptedprimitive skills (e.g. Push) and object-centric symbolic predicates (e.g.On(block, plate)), the planner autonomously generates a demonstration datasetof manipulation skills in the context of a long-horizon task. An offlinereinforcement learning algorithm then extracts a policy from the datasetwithout further interactions with the environment and replaces the scriptedskill in the existing library. Refining the skill library improves therobustness of the planner, which in turn facilitates data collection for morecomplex manipulation skills. We validate our approach in simulation, on ablock-pushing task. We show that the proposed method requires less trainingdata than conventional reinforcement learning methods. Furthermore, interactionwith the environment is collision-free because of the use of plannerdemonstrations, making the approach more amenable to persistent robot learningin the real world.

Offline Skill Generalization via Task and Motion Planning