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

Performing object retrieval tasks in messy real-world workspaces involves thechallenges of \emph{uncertainty} and \emph{clutter}. One option is to solveretrieval problems via a sequence of prehensile pick-n-place operations, whichcan be computationally expensive to compute in highly-cluttered scenarios andalso inefficient to execute. The proposed framework selects the option ofperforming non-prehensile actions, such as pushing, to clean a clutteredworkspace to allow a robotic arm to retrieve a target object. Non-prehensileactions, allow to interact simultaneously with multiple objects, which canspeed up execution. At the same time, they can significantly increaseuncertainty as it is not easy to accurately estimate the outcome of a pushingoperation in clutter. The proposed framework integrates topological tools andMonte-Carlo tree search to achieve effective and robust pushing for objectretrieval problems. In particular, it proposes using persistent homology toautomatically identify manageable clustering of blocking objects in theworkspace without the need for manually adjusting hyper-parameters.Furthermore, MCTS uses this information to explore feasible actions to pushgroups of objects together, aiming to minimize the number of pushing actionsneeded to clear the path to the target object. Real-world experiments using aBaxter robot, which involves some noise in actuation, show that the proposedframework achieves a higher success rate in solving retrieval tasks in denseclutter compared to state-of-the-art alternatives. Moreover, it produceshigh-quality solutions with a small number of pushing actions improving theoverall execution time. More critically, it is robust enough that it allows toplan the sequence of actions offline and then execute them reliably online withBaxter.

Persistent Homology Guided Monte-Carlo Tree Search for Effective Non-Prehensile Manipulation