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

Robot manipulation is increasingly poised to interact with humans inco-shared workspaces. Despite increasingly robust manipulation and controlalgorithms, failure modes continue to exist whenever models do not capture thedynamics of the unstructured environment. To obtain longer-term horizons inrobot automation, robots must develop introspection and recovery abilities. Wecontribute a set of recovery policies to deal with anomalies produced byexternal disturbances as well as anomaly classification through the use ofnon-parametric statistics with memoized variational inference with scalableadaptation. A recovery critic stands atop of a tightly-integrated, graph-basedonline motion-generation and introspection system that resolves a wide range ofanomalous situations. Policies, skills, and introspection models are learnedincrementally and contextually in a task. Two task-level recovery policies:re-enactment and adaptation resolve accidental and persistent anomaliesrespectively. The introspection system uses non-parametric priors along withMarkov jump linear systems and memoized variational inference with scalableadaptation to learn a model from the data. Extensive real-robot experimentationwith various strenuous anomalous conditions is induced and resolved atdifferent phases of a task and in different combinations. The system executesaround-the-clock introspection and recovery and even elicited self-recoverywhen misclassifications occurred.

Endowing Robots with Longer-term Autonomy by Recovering from External  Disturbances in Manipulation through Grounded Anomaly Classification and  Recovery Policies