Situation Recognition and Behavior Induction based on Geometric Symbol Representation of Multimodal Sensorimotor Patterns

Memorization, abstraction, and generation of a time-series of sensors and motion patterns are some of the most important functions for intelligent robots, because these memories are useful for situation recognition and behavior decision making. In conventional research, recurrent neural networks are often used for such memory functions. However, they cannot memorize a lot of patterns and its learning algorithm is unreliable. In this paper, we propose a method for the induction of behavior and situational estimation based on hidden Markov models, which is currently one of the most useful stochastic models. With the proposed method, we show the feasibility of: (1) Both recognition and association are executed at the same time, and (2) A multiple degrees of freedom and multiple sensorimotor patterns are acceptable