A model-predictive switching approach to efficient intention recognition

摘要

Estimating a user's intention is central to close human-robot cooperation. In this paper, the problem of performing intention recognition with tree-structured Dynamic Bayesian Networks for large environments with many features is addressed. The proposed approach reduces the computational complexity of inference O(b <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">s</sup> ) for tree-structured measurement models with an average branching factor b and tree height s to O(b̃ <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">s</sup> ), where b̃ ≪ b. The key idea is to switch between a finite set of reduced system and measurement models in order to restrict inference to the most important features. A model predictive approach to online switching between the reduced models is proposed that exploits an upper bound of the distances of the reduced models to the full model. The effectiveness of the proposed algorithm is validated in the intention recognition for a humanoid robot using a telepresent household scenario.