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

Autonomous robot-assisted feeding requires the ability to acquire a widevariety of food items. However, it is impossible for such a system to betrained on all types of food in existence. Therefore, a key challenge ischoosing a manipulation strategy for a previously unseen food item. Previouswork showed that the problem can be represented as a linear bandit with visualcontext. However, food has a wide variety of multi-modal properties relevant tomanipulation that can be hard to distinguish visually. Our key insight is thatwe can leverage the haptic context we collect during and after manipulation(i.e., "post hoc") to learn some of these properties and more quickly adapt ourvisual model to previously unseen food. In general, we propose a modifiedlinear contextual bandit framework augmented with post hoc context observedafter action selection to empirically increase learning speed and reducecumulative regret. Experiments on synthetic data demonstrate that this effectis more pronounced when the dimensionality of the context is large relative tothe post hoc context or when the post hoc context model is particularly easy tolearn. Finally, we apply this framework to the bite acquisition problem anddemonstrate the acquisition of 8 previously unseen types of food with 21% fewerfailures across 64 attempts.

Leveraging Post Hoc Context for Faster Learning in Bandit Settings with Applications in Robot-Assisted Feeding