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

In this paper, we present a framework for learning quadruped navigation byintegrating central pattern generators (CPGs), i.e. systems of coupledoscillators, into the deep reinforcement learning (DRL) framework. Through bothexteroceptive and proprioceptive sensing, the agent learns to modulate theintrinsic oscillator setpoints (amplitude and frequency) and coordinaterhythmic behavior among different oscillators to track velocity commands whileavoiding collisions with the environment. We compare different neural networkarchitectures (i.e. memory-free and memory-enabled) which learn implicitinteroscillator couplings, as well as varying the strength of the explicitcoupling weights in the oscillator dynamics equations. We train our policies insimulation and perform a sim-to-real transfer to the Unitree Go1 quadruped,where we observe robust navigation in a variety of scenarios. Our results showthat both memory-enabled policy representations and explicit interoscillatorcouplings are beneficial for a successful sim-to-real transfer for navigationtasks. Video results can be found at https://youtu.be/O_LX1oLZOe0.

Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Navigation