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

One of the fundamental challenges in realizing the potential of legged robotsis generating plans to traverse challenging terrains. Control actions must becarefully selected so the robot will not crash or slip. The high dimensionalityof the joint space makes directly planning low-level actions from onboardperception difficult, and control stacks that do not consider the low-levelmechanisms of the robot in planning are ill-suited to handle fine-grainedobstacles. One method for dealing with this is selecting footstep locationsbased on terrain characteristics. However, incorporating robot dynamics intofootstep planning requires significant computation, much more than in thequasi-static case. In this work, we present an LSTM-based planning frameworkthat learns probability distributions over likely footstep locations using bothterrain lookahead and the robot's dynamics, and leverages the LSTM's sequentialnature to find footsteps in linear time. Our framework can also be used as amodule to speed up sampling-based planners. We validate our approach on asimulated one-legged hopper over a variety of uneven terrains.

Fast Footstep Planning on Uneven Terrain Using Deep Sequential Models