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

Adaptive falling and recovery skills greatly extend the applicability ofrobot deployments. In the case of legged mobile manipulators, the robot armcould adaptively stop the fall and assist the recovery. Prior works on fallingand recovery strategies for legged mobile manipulators usually rely onassumptions such as inelastic collisions and falling in defined directions toenable real-time computation. This paper presents a learning-based approach toreducing fall damage and recovery. An asymmetric actor-critic trainingstructure is used to train a time-invariant policy with time-varying rewardfunctions. In simulated experiments, the policy recovers from 98.9\% of initialfalling configurations. It reduces base contact impulse, peak joint internalforces, and base acceleration during the fall compared to the baseline methods.The trained control policy is deployed and extensively tested on the ALMA robothardware. A video summarizing the proposed method and the hardware tests isavailable at https://youtu.be/avwg2HqGi8s.

Learning Arm-Assisted Fall Damage Reduction and Recovery for Legged Mobile Manipulators