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

Kinesthetic Teaching is a popular approach to collecting expert roboticdemonstrations of contact-rich tasks for imitation learning (IL), but ittypically only measures motion, ignoring the force placed on the environment bythe robot. Furthermore, contact-rich tasks require accurate sensing of bothreaching and touching, which can be difficult to provide with conventionalsensing modalities. We address these challenges with a See-Through-your-Skin(STS) visuotactile sensor, using the sensor both (i) as a measurement tool toimprove kinesthetic teaching, and (ii) as a policy input in contact-rich doormanipulation tasks. An STS sensor can be switched between visual and tactilemodes by leveraging a semi-transparent surface and controllable lighting,allowing for both pre-contact visual sensing and during-contact tactile sensingwith a single sensor. First, we propose tactile force matching, a methodologythat enables a robot to match forces read during kinesthetic teaching usingtactile signals. Second, we develop a policy that controls STS mode switching,allowing a policy to learn the appropriate moment to switch an STS from itsvisual to its tactile mode. Finally, we study multiple observationconfigurations to compare and contrast the value of visual and tactile datafrom an STS with visual data from a wrist-mounted eye-in-hand camera. With over3,000 test episodes from real-world manipulation experiments, we find that theinclusion of force matching raises average policy success rates by 62.5%, STSmode switching by 30.3%, and STS data as a policy input by 42.5%. Our resultshighlight the utility of see-through tactile sensing for IL, both for datacollection to allow force matching, and for policy execution to allow accuratetask feedback.

Multimodal and Force-Matched Imitation Learning with a See-Through Visuotactile Sensor