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

Semi-supervised learning improves the performance of supervised machinelearning by leveraging methods from unsupervised learning to extractinformation not explicitly available in the labels. Through the design of asystem that enables a robot to learn inspection strategies from a humanoperator, we present a hybrid semi-supervised system capable of learninginterpretable and verifiable models from demonstrations. The system induces acontroller program by learning from immersive demonstrations using sequentialimportance sampling. These visual servo controllers are parametrised byproportional gains and are visually verifiable through observation of theposition of the robot in the environment. Clustering and effective particlesize filtering allows the system to discover goals in the state space. Thesegoals are used to label the original demonstration for end-to-end learning ofbehavioural models. The behavioural models are used for autonomous modelpredictive control and scrutinised for explanations. We implement causalsensitivity analysis to identify salient objects and generate counterfactualconditional explanations. These features enable decision making interpretationand post hoc discovery of the causes of a failure. The proposed system expandson previous approaches to program synthesis by incorporating repellers in theattribution prior of the sampling process. We successfully learn the hybridsystem from an inspection scenario where an unmanned ground vehicle has toinspect, in a specific order, different areas of the environment. The systeminduces an interpretable computer program of the demonstration that can besynthesised to produce novel inspection behaviours. Importantly, the robotsuccessfully runs the synthesised program on an unseen configuration of theenvironment while presenting explanations of its autonomous behaviour.

Semi-supervised Learning From Demonstration Through Program Synthesis: An Inspection Robot Case Study