Motor simulation via coupled internal models using sequential Monte Carlo

We describe a generative Bayesian model for action understanding in which inverse-forward internal model pairs are considered 'hypotheses' of plausible action goals that are explored in parallel via an approximate inference mechanism based on sequential Monte Carlo methods. The reenactment of internal model pairs can be considered a form of motor simulation, which supports both perceptual prediction and action understanding at the goal level. However, this procedure is generally considered to be computationally inefficient. We present a model that dynamically reallocates computational resources to more accurate internal models depending on both the available prior information and the prediction error of the inverse-forward models, and which leads to successful action recognition. We present experimental results that test the robustness and efficiency of our model in real-world scenarios.

Publication type: 
Contributo in atti di convegno
Author or Creator: 
Dindo, Haris
Zambuto, Daniele
Pezzulo, Giovanni
Publisher: 
AAAI Press, Arlington [VA], USA
Source: 
Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, Barcelona, Catalonia, Spain, 16-22 July 2011, pp. 2113–2119, Barcelona, 16-22 July 2011
Date: 
2011
Resource Identifier: 
http://www.cnr.it/prodotto/i/203805
Language: 
Eng
ISTC Author: 
Giovanni Pezzulo's picture
Real name: