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/

Zendy Plus

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

Zendy Tools

Zendy Open

Dexterous in-hand manipulation in robotics, particularly with multi-fingeredrobotic hands, poses significant challenges due to the intricate avoidance ofcollisions among fingers and the object being manipulated. Collision-free pathsfor all fingers must be generated in real-time, as the rapid changes in handand finger positions necessitate instantaneous recalculations to preventcollisions and ensure undisturbed movement. This study introduces a real-timeapproach to motion planning in high-dimensional spaces. We first explicitlymodel the collision-free space using neural networks that are retrievable inreal time. Then, we combined the C-space representation with closed-loopcontrol via dynamical system and sampling-based planning approaches. Thisintegration enhances the efficiency and feasibility of path-finding, enablingdynamic obstacle avoidance, thereby advancing the capabilities ofmulti-fingered robotic hands for in-hand manipulation tasks.

Enhancing Dexterity in Confined Spaces: Real-Time Motion Planning for Multi-Fingered In-Hand Manipulation