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

Controlling a biped robot to walk stably is a challenging task consideringits nonlinearity and hybrid dynamics. Reinforcement learning can address theseissues by directly mapping the observed states to optimal actions that maximizethe cumulative reward. However, the local minima caused by unsuitable rewardsand the overestimation of the cumulative reward impede the maximization of thecumulative reward. To increase the cumulative reward, this paper designs a gaitreward based on walking principles, which compensates the local minima forunnatural motions. Besides, an Adversarial Twin Delayed Deep Deterministic(ATD3) policy gradient algorithm with a recurrent neural network (RNN) isproposed to further boost the cumulative reward by mitigating theoverestimation of the cumulative reward. Experimental results in the RoboschoolWalker2d and Webots Atlas simulators indicate that the test rewards increase by23.50% and 9.63% after adding the gait reward. The test rewards furtherincrease by 15.96% and 12.68% after using the ATD3_RNN, and the reason may bethat the ATD3_RNN decreases the error of estimating cumulative reward from19.86% to 3.35%. Besides, the cosine kinetic similarity between the human andthe biped robot trained by the gait reward and ATD3_RNN increases by over69.23%. Consequently, the designed gait reward and ATD3_RNN boost thecumulative reward and teach biped robots to walk better.

Teach Biped Robots to Walk via Gait Principles and Reinforcement Learning with Adversarial Critics