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

Quadruped animals seamlessly transition between gaits as they changelocomotion speeds. While the most widely accepted explanation for gaittransitions is energy efficiency, there is no clear consensus on thedetermining factor, nor on the potential effects from terrain properties. Inthis article, we propose that viability, i.e. the avoidance of falls,represents an important criterion for gait transitions. We investigate theemergence of gait transitions through the interaction between supraspinal drive(brain), the central pattern generator in the spinal cord, the body, andexteroceptive sensing by leveraging deep reinforcement learning and roboticstools. Consistent with quadruped animal data, we show that the walk-trot gaittransition for quadruped robots on flat terrain improves both viability andenergy efficiency. Furthermore, we investigate the effects of discrete terrain(i.e. crossing successive gaps) on imposing gait transitions, and find theemergence of trot-pronk transitions to avoid non-viable states. Compared withother potential criteria such as peak forces and energy efficiency, viabilityis the only improved factor after gait transitions on both flat and discretegap terrains, suggesting that viability could be a primary and universalobjective of gait transitions, while other criteria are secondary objectivesand/or a consequence of viability. Moreover, we deploy our learned controllerin sim-to-real hardware experiments and demonstrate state-of-the-art quadrupedagility in challenging scenarios, where the Unitree A1 quadruped autonomouslytransitions gaits between trot and pronk to cross consecutive gaps of up to 30cm (83.3 % of the body-length) at over 1.3 m/s.

DeepTransition: Viability Leads to the Emergence of Gait Transitions in Learning Anticipatory Quadrupedal Locomotion Skills