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

Animals are capable of precise and agile locomotion using vision. Replicatingthis ability has been a long-standing goal in robotics. The traditionalapproach has been to decompose this problem into elevation mapping and footholdplanning phases. The elevation mapping, however, is susceptible to failure andlarge noise artifacts, requires specialized hardware, and is biologicallyimplausible. In this paper, we present the first end-to-end locomotion systemcapable of traversing stairs, curbs, stepping stones, and gaps. We show thisresult on a medium-sized quadruped robot using a single front-facing depthcamera. The small size of the robot necessitates discovering specialized gaitpatterns not seen elsewhere. The egocentric camera requires the policy toremember past information to estimate the terrain under its hind feet. We trainour policy in simulation. Training has two phases - first, we train a policyusing reinforcement learning with a cheap-to-compute variant of depth image andthen in phase 2 distill it into the final policy that uses depth usingsupervised learning. The resulting policy transfers to the real world and isable to run in real-time on the limited compute of the robot. It can traverse alarge variety of terrain while being robust to perturbations like pushes,slippery surfaces, and rocky terrain. Videos are athttps://vision-locomotion.github.io

Legged Locomotion in Challenging Terrains using Egocentric Vision