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

We present a footstep planning policy for quadrupedal locomotion that is ableto directly take into consideration a-priori safety information in itsdecisions. At its core, a learning process analyzes terrain patches,classifying each landing location by its kinematic feasibility, shin collision,and terrain roughness. This information is then encoded into a small vectorrepresentation and passed as an additional state to the footstep planningpolicy, which furthermore proposes only safe footstep location by applying amasked variant of the Proximal Policy Optimization algorithm. The performanceof the proposed approach is shown by comparative simulations and experiments onan electric quadruped robot walking in different rough terrain scenarios. Weshow that violations of the above safety conditions are greatly reduced bothduring training and the successive deployment of the policy, resulting in aninherently safer footstep planner. Furthermore, we show how, as a byproduct,fewer reward terms are needed to shape the behavior of the policy, which inreturn is able to achieve both better final performances and sample efficiency.

SafeSteps: Learning Safer Footstep Planning Policies for Legged Robots via Model-Based Priors