Change search
ReferencesLink to record
Permanent link

Direct link
Predictive learning from demonstration
Umeå University, Faculty of Science and Technology, Department of Computing Science.
Umeå University, Faculty of Science and Technology, Department of Computing Science.
Umeå University, Faculty of Science and Technology, Department of Computing Science.
2011 (English)In: Agents and artificial Intelligence: Second International Conference, ICAART 2010, Valencia, Spain, January 22-24, 2010. Revised Selected Papers / [ed] Joaquim Filipe, Berlin: Springer Verlag , 2011, 1, 186-200 p.Chapter in book (Refereed)
Abstract [en]

A model-free learning algorithm called Predictive Sequence Learning (PSL) is presented and evaluated in a robot Learning from Demonstration (LFD) setting. PSL is inspired by several functional models of the brain. It constructs sequences of predictable sensory-motor patterns, without relying on predefined higher-level concepts. The algorithm is demonstrated on a Khepera II robot in four different tasks. During training, PSL generates a hypothesis library from demonstrated data. The library is then used to control the robot by continually predicting the next action, based on the sequence of passed sensor and motor events. In this way, the robot reproduces the demonstrated behavior. PSL is able to successfully learn and repeat three elementary tasks, but is unable to repeat a fourth, composed behavior. The results indicate that PSL is suitable for learning problems up to a certain complexity, while higher level coordination is required for learning more complex behaviors.

Place, publisher, year, edition, pages
Berlin: Springer Verlag , 2011, 1. 186-200 p.
, Communications in Computer and Information Science, ISSN 1865-0929 ; 129
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Computer Science
URN: urn:nbn:se:umu:diva-44191DOI: 10.1007/978-3-642-19890-8_14ISBN: 978-3-642-19889-2OAI: diva2:419040
Second International Conference, ICAART 2010, Valencia, Spain, January 22-24, 2010
Available from: 2011-05-25 Created: 2011-05-25 Last updated: 2012-01-04Bibliographically approved
In thesis
1. Cognition Rehearsed: Recognition and Reproduction of Demonstrated Behavior
Open this publication in new window or tab >>Cognition Rehearsed: Recognition and Reproduction of Demonstrated Behavior
2012 (English)Doctoral thesis, comprehensive summary (Other academic)
Alternative title[sv]
Robotövningar : Igenkänning och återgivande av demonstrerat beteende
Abstract [en]

The work presented in this dissertation investigates techniques for robot Learning from Demonstration (LFD). LFD is a well established approach where the robot is to learn from a set of demonstrations. The dissertation focuses on LFD where a human teacher demonstrates a behavior by controlling the robot via teleoperation. After demonstration, the robot should be able to reproduce the demonstrated behavior under varying conditions. In particular, the dissertation investigates techniques where previous behavioral knowledge is used as bias for generalization of demonstrations.

The primary contribution of this work is the development and evaluation of a semi-reactive approach to LFD called Predictive Sequence Learning (PSL). PSL has many interesting properties applied as a learning algorithm for robots. Few assumptions are introduced and little task-specific configuration is needed. PSL can be seen as a variable-order Markov model that progressively builds up the ability to predict or simulate future sensory-motor events, given a history of past events. The knowledge base generated during learning can be used to control the robot, such that the demonstrated behavior is reproduced. The same knowledge base can also be used to recognize an on-going behavior by comparing predicted sensor states with actual observations. Behavior recognition is an important part of LFD, both as a way to communicate with the human user and as a technique that allows the robot to use previous knowledge as parts of new, more complex, controllers.

In addition to the work on PSL, this dissertation provides a broad discussion on representation, recognition, and learning of robot behavior. LFD-related concepts such as demonstration, repetition, goal, and behavior are defined and analyzed, with focus on how bias is introduced by the use of behavior primitives. This analysis results in a formalism where LFD is described as transitions between information spaces. Assuming that the behavior recognition problem is partly solved, ways to deal with remaining ambiguities in the interpretation of a demonstration are proposed.

The evaluation of PSL shows that the algorithm can efficiently learn and reproduce simple behaviors. The algorithm is able to generalize to previously unseen situations while maintaining the reactive properties of the system. As the complexity of the demonstrated behavior increases, knowledge of one part of the behavior sometimes interferes with knowledge of another parts. As a result, different situations with similar sensory-motor interactions are sometimes confused and the robot fails to reproduce the behavior.

One way to handle these issues is to introduce a context layer that can support PSL by providing bias for predictions. Parts of the knowledge base that appear to fit the present context are highlighted, while other parts are inhibited. Which context should be active is continually re-evaluated using behavior recognition. This technique takes inspiration from several neurocomputational models that describe parts of the human brain as a hierarchical prediction system. With behavior recognition active, continually selecting the most suitable context for the present situation, the problem of knowledge interference is significantly reduced and the robot can successfully reproduce also more complex behaviors.

Place, publisher, year, edition, pages
Umeå: Department of Computing Science, Umeå University, 2012. 30 p.
Report / UMINF, ISSN 0348-0542 ; 11.16
Behavior Recognition, Learning and Adaptive Systems, Learning from Demonstration, Neurocomputational Modeling, Robot Learning
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computer and Information Science
urn:nbn:se:umu:diva-50980 (URN)978-91-7459-349-5 (ISBN)
Public defence
2012-01-26, S1031, Norra Beteendevetarhuset, Umeå Universitet, Umeå, 13:15 (English)
Available from: 2012-01-04 Created: 2012-01-03 Last updated: 2012-01-04Bibliographically approved

Open Access in DiVA

fulltext(394 kB)256 downloads
File information
File name FULLTEXT02.pdfFile size 394 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Billing, ErikHellström, ThomasJanlert, Lars Erik
By organisation
Department of Computing Science
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 256 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 911 hits
ReferencesLink to record
Permanent link

Direct link