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

Task and motion planning (TAMP) algorithms have been developed to help robotsplan behaviors in discrete and continuous spaces. Robots face complexreal-world scenarios, where it is hardly possible to model all objects or theirphysical properties for robot planning (e.g., in kitchens or shopping centers).In this paper, we define a new object-centric TAMP problem, where the TAMProbot does not know object properties (e.g., size and weight of blocks). Wethen introduce Task-Motion Object-Centric planning ({\bf TMOC}), a groundedTAMP algorithm that learns to ground objects and their physical properties witha physics engine. TMOC is particularly useful for those tasks that involvedynamic complex robot-multi-object interactions that can hardly be modeledbeforehand. We have demonstrated and evaluated TMOC in simulation and using areal robot. Results show that TMOC outperforms competitive baselines from theliterature in cumulative utility.

Learning to Ground Objects for Robot Task and Motion Planning