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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recent work on sim-to-real learning for bipedal locomotion has demonstratednew levels of robustness and agility over a variety of terrains. However, thatwork, and most prior bipedal locomotion work, have not considered locomotionunder a variety of external loads that can significantly influence the overallsystem dynamics. In many applications, robots will need to maintain robustlocomotion under a wide range of potential dynamic loads, such as pulling acart or carrying a large container of sloshing liquid, ideally withoutrequiring additional load-sensing capabilities. In this work, we explore thecapabilities of reinforcement learning (RL) and sim-to-real transfer forbipedal locomotion under dynamic loads using only proprioceptive feedback. Weshow that prior RL policies trained for unloaded locomotion fail for some loadsand that simply training in the context of loads is enough to result insuccessful and improved policies. We also compare training specialized policiesfor each load versus a single policy for all considered loads and analyze howthe resulting gaits change to accommodate different loads. Finally, wedemonstrate sim-to-real transfer, which is successful but shows a widersim-to-real gap than prior unloaded work, which points to interesting futureresearch.

Sim-to-Real Learning for Bipedal Locomotion Under Unsensed Dynamic Loads