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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Quadrupedal robots are skillful at locomotion tasks while lackingmanipulation skills, not to mention dexterous manipulation abilities. Inspiredby the animal behavior and the duality between multi-legged locomotion andmulti-fingered manipulation, we showcase a circus ball challenge on aquadrupedal robot, ANYmal. We employ a model-free reinforcement learningapproach to train a deep policy that enables the robot to balance andmanipulate a light-weight ball robustly using its limbs without any contactmeasurement sensor. The policy is trained in the simulation, in which werandomize many physical properties with additive noise and inject randomdisturbance force during manipulation, and achieves zero-shot deployment on thereal robot without any adjustment. In the hardware experiments, dynamicperformance is achieved with a maximum rotation speed of 15 deg/s, and robustrecovery is showcased under external poking. To our best knowledge, it is thefirst work that demonstrates the dexterous dynamic manipulation on a realquadrupedal robot.

Circus ANYmal: A Quadruped Learning Dexterous Manipulation with Its Limbs