Chapter

From Motor Learning to Interaction Learning in Robots

Volume 264 of the series Studies in Computational Intelligence pp 253-291

Methods for Learning Control Policies from Variable-Constraint Demonstrations

  • Matthew HowardAffiliated withInstitute of Perception Action and Behaviour, University of Edinburgh
  • , Stefan KlankeAffiliated withInstitute of Perception Action and Behaviour, University of Edinburgh
  • , Michael GiengerAffiliated withHonda Research Institute Europe (GmBH)
  • , Christian GoerickAffiliated withHonda Research Institute Europe (GmBH)
  • , Sethu VijayakumarAffiliated withInstitute of Perception Action and Behaviour, University of Edinburgh

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Many everyday human skills can be framed in terms of performing some task subject to constraints imposed by the task or the environment. Constraints are usually not observable and frequently change between contexts. In this chapter, we explore the problem of learning control policies from data containing variable, dynamic and non-linear constraints on motion. We discuss how an effective approach for doing this is to learn the unconstrained policy in a way that is consistent with the constraints. We then go on to discuss several recent algorithms for extracting policies from movement data, where observations are recorded under variable, unknown constraints. We review a number of experiments testing the performance of these algorithms and demonstrating how the resultant policy models generalise over constraints allowing prediction of behaviour under unseen settings where new constraints apply.