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

Humans and animals are believed to use a very minimal set of trajectories toperform a wide variety of tasks including walking. Our main objective in thispaper is two fold 1) Obtain an effective tool to realize these basic motionpatterns for quadrupedal walking, called the kinematic motion primitives(kMPs), via trajectories learned from deep reinforcement learning (D-RL) and 2)Realize a set of behaviors, namely trot, walk, gallop and bound from thesekinematic motion primitives in our custom four legged robot, called the`Stoch'. D-RL is a data driven approach, which has been shown to be veryeffective for realizing all kinds of robust locomotion behaviors, both insimulation and in experiment. On the other hand, kMPs are known to capture theunderlying structure of walking and yield a set of derived behaviors. We firstgenerate walking gaits from D-RL, which uses policy gradient based approaches.We then analyze the resulting walking by using principal component analysis. Weobserve that the kMPs extracted from PCA followed a similar patternirrespective of the type of gaits generated. Leveraging on this underlyingstructure, we then realize walking in Stoch by a straightforward reconstructionof joint trajectories from kMPs. This type of methodology improves thetransferability of these gaits to real hardware, lowers the computationaloverhead on-board, and also avoids multiple training iterations by generating aset of derived behaviors from a single learned gait.

Realizing Learned Quadruped Locomotion Behaviors through Kinematic Motion Primitives