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

Simón C. Smith, Ram Ramamoorthy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Semi-supervised learning improves the performance of supervised machine learning by leveraging methods from unsupervised learning to extract information not explicitly available in the labels. Through the design of a system that enables a robot to learn inspection strategies from a human operator, we present a hybrid semi-supervised system capable of learning interpretable and verifiable models from demonstrations. The system induces a controller program by learning from immersive demonstrations using sequential importance sampling. These visual servo controllers are parametrised by proportional gains and are visually verifiable through observation of the robot’s position in the environment. Clustering and effective particle size filtering allows the system to discover goals in the state space. These goals are used to label the original demonstration for end-to-end learning of behavioural models. The behavioural models are used for autonomous model predictive control and scrutinised for explanations. We implement causal sensitivity analysis to identify salient objects and generate counterfactual conditional explanations. These features enable decision making interpretation and post hoc discovery of the causes of a failure. The proposed system expands on previous approaches to program synthesis by incorporating repellers in the attribution prior of the sampling process. We successfully learn the hybrid system from an inspection scenario where an unmanned ground vehicle has to inspect, in a specific order, different areas of the environment. The system induces an interpretable computer program of the demonstration that can be synthesised to produce novel inspection behaviours. Importantly, the robot successfully runs the synthesised program on an unseen configuration of the environment while presenting explanations of its autonomous behaviour.
Original languageEnglish
Title of host publicationProceedings of the First Workshop on Agents and Robots for reliable Engineered Autonomy (AREA 2020)
EditorsRafael C. Cardoso, Angelo Ferrando, Daniela Briola, Claudio Menghi, Tobias Ahlbrecht
PublisherOpen Publishing Association
Pages81 - 101
Number of pages21
DOIs
Publication statusPublished - 23 Jul 2020
EventFirst Workshop on Agents and Robots for reliable Engineered Autonomy -
Duration: 4 Sept 20204 Sept 2020
https://area2020.github.io/

Publication series

NameElectronic Proceedings in Theoretical Computer Science
PublisherOpen Publishing Association
Volume319
ISSN (Electronic)2075-2180

Conference

ConferenceFirst Workshop on Agents and Robots for reliable Engineered Autonomy
Abbreviated titleAREA 2020
Period4/09/204/09/20
Internet address

Fingerprint

Dive into the research topics of 'Semi-supervised Learning From Demonstration through Program Synthesis: An Inspection Robot Case Study'. Together they form a unique fingerprint.

Cite this