Action Parsing and Goal Inference using Self as Simulator

Gray, J., Breazeal, C., Berlin, M., Brooks, A., Lieberman, J.


An important element of cooperative behavior is the ability to understand a teammate’s actions, as well as to infer their goals and other mental states that are responsible for generating those actions. Simulation Theory argues in favor of an embodied approach whereby humans reuse parts of their own cognitive structure for not only generating one’s own behavior, but also for simulating the mental states responsible for generating that behavior in others. This paper presents our simulation-theoretic approach and demonstrates its performance in a collaborative task scenario. The robot offers its human teammate assistance by either inferring the human’s beliefs states to anticipate their informational needs, or inferring the human’s goal states to physically help the human achieve those goals.

Related Content