Proceedings

Motor Simulation via Coupled Internal Models Using Sequential Monte Carlo

Haris Dindo, Daniele Zambuto, Giovanni Pezzulo

Download BibTeX Cite

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 2113-2118.

https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-353

Abstract

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.

Haris Dindo, Daniele Zambuto, and Giovanni Pezzulo. 2011. Motor Simulation via Coupled Internal Models Using Sequential Monte Carlo. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11. IJCAI, 2113–2118. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-353
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards