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

Re-grasp manipulation leverages on ergonomic tools to assist humans inaccomplishing diverse tasks. In certain scenarios, humans often employ externalforces to effortlessly and precisely re-grasp tools like a hammer. Previousdevelopment on controllers for in-grasp sliding motion using passive dynamicactions (e.g.,gravity) relies on apprehension of finger-object contactinformation, and requires customized design for individual objects with variedgeometry and weight distribution. It limits their adaptability to diverseobjects. In this paper, we propose an end-to-end sliding motion controllerbased on imitation learning (IL) that necessitates minimal prior knowledge ofobject mechanics, relying solely on object position information. To expeditetraining convergence, we utilize a data glove to collect expert datatrajectories and train the policy through Generative Adversarial ImitationLearning (GAIL). Simulation results demonstrate the controller's versatility inperforming in-hand sliding tasks with objects of varying friction coefficients,geometric shapes, and masses. By migrating to a physical system using visualposition estimation, the controller demonstrated an average success rate of86%, surpassing the baseline algorithm's success rate of 35% of BehaviorCloning(BC) and 20% of Proximal Policy Optimization (PPO).

In-Hand Re-grasp Manipulation with Passive Dynamic Actions via Imitation Learning