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

Uncertainties in the real world mean that is impossible for system designersto anticipate and explicitly design for all scenarios that a robot mightencounter. Thus, robots designed like this are fragile and fail outside ofhighly-controlled environments. Causal models provide a principled framework toencode formal knowledge of the causal relationships that govern the robot'sinteraction with its environment, in addition to probabilistic representationsof noise and uncertainty typically encountered by real-world robots. Combinedwith causal inference, these models permit an autonomous agent to understand,reason about, and explain its environment. In this work, we focus on theproblem of a robot block-stacking task due to the fundamental perception andmanipulation capabilities it demonstrates, required by many applicationsincluding warehouse logistics and domestic human support robotics. We propose anovel causal probabilistic framework to embed a physics simulation capabilityinto a structural causal model to permit robots to perceive and assess thecurrent state of a block-stacking task, reason about the next-best action fromplacement candidates, and generate post-hoc counterfactual explanations. Weprovide exemplar next-best action selection results and outline plannedexperimentation in simulated and real-world robot block-stacking tasks.

Towards a Causal Probabilistic Framework for Prediction, Action-Selection & Explanations for Robot Block-Stacking Tasks