Goal Oriented Behavior With a Habit-Based Adaptive Sensorimotor Map Network.

A new robot controller model called an ASM-network, built from adaptive sensorimotor maps, enables a robot to learn object discrimination without explicit representations or external rewards. The model combines a mechanism that generates continuous motor activity from past sensorimotor trajectories with an evaluative mechanism that reinforces trajectories supporting higher-order sensorimotor coordinations. In a minimal cognition task, a single robot learned through random exploration and repetition of supportive trajectories. The results demonstrate that recognizable learning behavior can emerge from enactive principles, adapting based on the internal requirements of the action-generating mechanism.

Study at a glance

Abstract

We present a description of an ASM-network, a new habit-based robot controller model consisting of a network of adaptive sensorimotor maps. This model draws upon recent theoretical developments in enactive cognition concerning habit and agency at the sensorimotor level. It aims to provide a platform for experimental investigation into the relationship between networked organizations of habits and cognitive behavior. It does this by combining (1) a basic mechanism of generating continuous motor activity as a function of historical sensorimotor trajectories with (2) an evaluative mechanism which reinforces or weakens those historical trajectories as a function of their support of a higher-order structure of higher-order sensorimotor coordinations. After describing the model, we then present the results of applying this model in the context of a well-known minimal cognition task involving object discrimination. In our version of this experiment, an individual robot is able to learn the task through a combination of exploration through random movements and repetition of historic trajectories which support the structure of a pre-given network of sensorimotor coordinations. The experimental results illustrate how, utilizing enactive principles, a robot can display recognizable learning behavior without explicit representational mechanisms or extraneous fitness variables. Instead, our model's behavior adapts according to the internal requirements of the action-generating mechanism itself.