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

Representing and reasoning about uncertainty is crucial for autonomous agentsacting in partially observable environments with noisy sensors. Partiallyobservable Markov decision processes (POMDPs) serve as a general framework forrepresenting problems in which uncertainty is an important factor. Onlinesample-based POMDP methods have emerged as efficient approaches to solvinglarge POMDPs and have been shown to extend to continuous domains. However,these solutions struggle to find long-horizon plans in problems withsignificant uncertainty. Exploration heuristics can help guide planning, butmany real-world settings contain significant task-irrelevant uncertainty thatmight distract from the task objective. In this paper, we propose STRUG, anonline POMDP solver capable of handling domains that require long-horizonplanning with significant task-relevant and task-irrelevant uncertainty. Wedemonstrate our solution on several temporally extended versions of toy POMDPproblems as well as robotic manipulation of articulated objects using a neuralperception frontend to construct a distribution of possible models. Our resultsshow that STRUG outperforms the current sample-based online POMDP solvers onseveral tasks.

Task-Directed Exploration in Continuous POMDPs for Robotic Manipulation of Articulated Objects