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

Motivated by the goal of endowing robots with a means for focusing attentionin order to operate reliably in complex, uncertain, and time-varyingenvironments, we consider how a robot can (i) determine which portions of itsenvironment to pay attention to at any given point in time, (ii) infer changesin context (e.g., task or environment dynamics), and (iii) switch its attentionaccordingly. In this work, we tackle these questions by modeling contextswitches in a time-varying Markov decision process (MDP) framework. We utilizethe theory of bisimulation-based state abstractions in order to synthesizemechanisms for paying attention to context-relevant information. We thenpresent an algorithm based on Bayesian inference for detecting changes in therobot's context (task or environment dynamics) as it operates online, and usethis to trigger switches between different abstraction-based attentionmechanisms. Our approach is demonstrated on two examples: (i) an illustrativediscrete-state tracking problem, and (ii) a continuous-state tracking problemimplemented on a quadrupedal hardware platform. These examples demonstrate theability of our approach to detect context switches online and robustly ignoretask-irrelevant distractors by paying attention to context-relevantinformation.

Switching Attention in Time-Varying Environments via Bayesian Inference of Abstractions