PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Planning and Moving in Dynamic Environments - A Statistical Machine Learning Approach.
S Vijayakumar, M Toussaint, G Petkos and M Howard
In: Creating Brain-Like Intelligence, From Basic Principles to Complex Intelligent Systems Lecture Notes in Computer Science , 5436/2009 . (2009) Springer Berlin / Heidelberg , pp. 151-191. ISBN 978-3-642-00615-9


In this chapter, we develop a new view on problems of move- ment control and planning from a Machine Learning perspective. In this view, decision making, control, and planning are all considered as an inference or (alternately) an information processing problem, i.e., a prob- lem of computing a posterior distribution over unknown variables condi- tioned on the available information (targets, goals, constraints). Further, problems of adaptation and learning are formulated as statistical learning problems to model the dependencies between variables. This approach naturally extends to cases when information is missing, e.g., when the context or load needs to be inferred from interaction; or to the case of apprentice learning where, crucially, latent properties of the observed behavior are learnt rather than the motion copied directly. With this account, we hope to address the long-standing problem of designing adaptive control and planning systems that can flexibly be cou- pled to multiple sources of information (be they of purely sensory nature or higher-level modulations such as task and constraint information) and equally formulated on any level of abstraction (motor control variables or symbolic representations). Recent advances in Machine Learning provide a coherent framework for these problems.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Book Section
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:4815
Deposited By:Marc Toussaint
Deposited On:24 March 2009