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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Building assistive interfaces for controlling robots through arbitrary,high-dimensional, noisy inputs (e.g., webcam images of eye gaze) can bechallenging, especially when it involves inferring the user's desired action inthe absence of a natural 'default' interface. Reinforcement learning fromonline user feedback on the system's performance presents a natural solution tothis problem, and enables the interface to adapt to individual users. However,this approach tends to require a large amount of human-in-the-loop trainingdata, especially when feedback is sparse. We propose a hierarchical solutionthat learns efficiently from sparse user feedback: we use offline pre-trainingto acquire a latent embedding space of useful, high-level robot behaviors,which, in turn, enables the system to focus on using online user feedback tolearn a mapping from user inputs to desired high-level behaviors. The keyinsight is that access to a pre-trained policy enables the system to learn morefrom sparse rewards than a na\"ive RL algorithm: using the pre-trained policy,the system can make use of successful task executions to relabel, in hindsight,what the user actually meant to do during unsuccessful executions. We evaluateour method primarily through a user study with 12 participants who performtasks in three simulated robotic manipulation domains using a webcam and theireye gaze: flipping light switches, opening a shelf door to reach objectsinside, and rotating a valve. The results show that our method successfullylearns to map 128-dimensional gaze features to 7-dimensional joint torques fromsparse rewards in under 10 minutes of online training, and seamlessly helpsusers who employ different gaze strategies, while adapting to distributionalshift in webcam inputs, tasks, and environments.

ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning