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

Complex physical tasks entail a sequence of object interactions, each withits own preconditions -- which can be difficult for robotic agents to learnefficiently solely through their own experience. We introduce an approach todiscover activity-context priors from in-the-wild egocentric video capturedwith human worn cameras. For a given object, an activity-context priorrepresents the set of other compatible objects that are required for activitiesto succeed (e.g., a knife and cutting board brought together with a tomato areconducive to cutting). We encode our video-based prior as an auxiliary rewardfunction that encourages an agent to bring compatible objects together beforeattempting an interaction. In this way, our model translates everyday humanexperience into embodied agent skills. We demonstrate our idea using egocentricEPIC-Kitchens video of people performing unscripted kitchen activities tobenefit virtual household robotic agents performing various complex tasks inAI2-iTHOR, significantly accelerating agent learning. Project page:http://vision.cs.utexas.edu/projects/ego-rewards/

Shaping embodied agent behavior with activity-context priors from egocentric video