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

Learning from demonstration (LfD) is a proven technique to teach robots newskills. Data quality and quantity play a critical role in LfD trained modelperformance. In this paper we analyze the effect of enhancing an existingteleoperation data collection system with real-time haptic feedback; we observeimprovements in the collected data throughput and its quality for modeltraining. Our experiment testbed was a mobile manipulator robot that openeddoors with latch handles. Evaluation of teleoperated data collection on eightreal world conference room doors found that adding the haptic feedback improvedthe data throughput by 6%. We additionally used the collected data to train siximage-based deep imitation learning models, three with haptic feedback andthree without it. These models were used to implement autonomous door-openingwith the same type of robot used during data collection. Our results show thata policy from a behavior cloning model trained with haptic data performed onaverage 11% better than its counterpart with no haptic feedback data,indicating that haptic feedback resulted in collection of a higher qualitydataset.

Leveraging Haptic Feedback to Improve Data Quality and Quantity for Deep Imitation Learning Models