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

We explore how high-speed robot arm motions can dynamically manipulate cablesto vault over obstacles, knock objects from pedestals, and weave betweenobstacles. In this paper, we propose a self-supervised learning framework thatenables a UR5 robot to perform these three tasks. The framework finds a 3D apexpoint for the robot arm, which, together with a task-specific trajectoryfunction, defines an arcing motion that dynamically manipulates the cable toperform tasks with varying obstacle and target locations. The trajectoryfunction computes minimum-jerk motions that are constrained to remain withinjoint limits and to travel through the 3D apex point by repeatedly solvingquadratic programs to find the shortest and fastest feasible motion. Weexperiment with 5 physical cables with different thickness and mass and compareperformance against two baselines in which a human chooses the apex point.Results suggest that a baseline with a fixed apex across the three tasksachieves respective success rates of 51.7%, 36.7%, and 15.0%, and a baselinewith human-specified, task-specific apex points achieves 66.7%, 56.7%, and15.0% success rate respectively, while the robot using the learned apex pointcan achieve success rates of 81.7% in vaulting, 65.0% in knocking, and 60.0% inweaving. Code, data, and supplementary materials are available at https://sites.google.com/berkeley.edu/dynrope/home.

Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cables