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

Simulation-to-reality transfer has emerged as a popular and highly successfulmethod to train robotic control policies for a wide variety of tasks. However,it is often challenging to determine when policies trained in simulation areready to be transferred to the physical world. Deploying policies that havebeen trained with very little simulation data can result in unreliable anddangerous behaviors on physical hardware. On the other hand, excessive trainingin simulation can cause policies to overfit to the visual appearance anddynamics of the simulator. In this work, we study strategies to automaticallydetermine when policies trained in simulation can be reliably transferred to aphysical robot. We specifically study these ideas in the context of roboticfabric manipulation, in which successful sim2real transfer is especiallychallenging due to the difficulties of precisely modeling the dynamics andvisual appearance of fabric. Results in a fabric smoothing task suggest thatour switching criteria correlate well with performance in real. In particular,our confidence-based switching criteria achieve average final fabric coverageof 87.2-93.7% within 55-60% of the total training budget. Seehttps://tinyurl.com/lsc-case for code and supplemental materials.

Learning Switching Criteria for Sim2Real Transfer of Robotic Fabric Manipulation Policies