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

This paper introduces the task of {\em Planar Robot Casting (PRC)}: where oneplanar motion of a robot arm holding one end of a cable causes the other end toslide across the plane toward a desired target. PRC allows the cable to reachpoints beyond the robot workspace and has applications for cable management inhomes, warehouses, and factories. To efficiently learn a PRC policy for a givencable, we propose Real2Sim2Real, a self-supervised framework that automaticallycollects physical trajectory examples to tune parameters of a dynamicssimulator using Differential Evolution, generates many simulated examples, andthen learns a policy using a weighted combination of simulated and physicaldata. We evaluate Real2Sim2Real with three simulators, Isaac Gym-segmented,Isaac Gym-hybrid, and PyBullet, two function approximators, Gaussian Processesand Neural Networks (NNs), and three cables with differing stiffness, torsion,and friction. Results with 240 physical trials suggest that the PRC policiescan attain median error distance (as % of cable length) ranging from 8% to 14%,outperforming baselines and policies trained on only real or only simulatedexamples. Code, data, and videos are available athttps://tinyurl.com/robotcast.

Planar Robot Casting with Real2Sim2Real Self-Supervised Learning