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

Enabling robots to effectively imitate expert skills in longhorizon taskssuch as locomotion, manipulation, and more, poses a long-standing challenge.Existing imitation learning (IL) approaches for robots still grapple withsub-optimal performance in complex tasks. In this paper, we consider how thischallenge can be addressed within the human cognitive priors. Heuristically, weextend the usual notion of action to a dual Cognition (high-level)-Action(low-level) architecture by introducing intuitive human cognitive priors, andpropose a novel skill IL framework through human-robot interaction, calledCognition-Action-based Skill Imitation Learning (CasIL), for the robotic agentto effectively cognize and imitate the critical skills from raw visualdemonstrations. CasIL enables both cognition and action imitation, whilehigh-level skill cognition explicitly guides low-level primitive actions,providing robustness and reliability to the entire skill IL process. Weevaluated our method on MuJoCo and RLBench benchmarks, as well as on theobstacle avoidance and point-goal navigation tasks for quadrupedal robotlocomotion. Experimental results show that our CasIL consistently achievescompetitive and robust skill imitation capability compared to othercounterparts in a variety of long-horizon robotic tasks.

CasIL: Cognizing and Imitating Skills via a Dual Cognition-Action Architecture