A new bio-inspired perceptual control architecture applied to solve navigation tasks

In this paper a new general purpose perceptual control architecture is presented and applied to robot navigation in cluttered environments. In nature, insects show the ability to react to certain stimuli with simple reflexes using direct sensory-motor pathways, which can be considered as basic behaviors, while high brain regions provide secondary pathway allowing the emergence of a cognitive behavior which modulates the basic abilities. Taking inspiration from this evidence, our architecture modulates, through a reinforcement learning, a set of competitive and concurrent basic behaviors in order to accomplish the task assigned through a reward function. The core of the architecture is constituted by the Representation layer, where different stimuli, triggering competitive reflexes, are fused to form a unique abstract picture of the environment. The representation is formalized by means of Reaction-Diffusion nonlinear partial differential equations, under the paradigm of the Cellular Neural Networks, whose dynamics converges to steady-state Turing patterns. A suitable unsupervised learning, introduced at the afferent (input) stage, leads to the shaping of the basins of attractions of the Turing patterns in order to incrementally drive the association between sensor stimuli and patterns. In this way, at the end of the leaning stage, each pattern is characteristic of a particular behavior modulation, while its trained basin of attraction contains the set of all the environment conditions, as recorded through the sensors, leading to the emergence of that particular behavior modulation. Robot simulations are reported to demonstrate the potentiality and the effectiveness of the approach. ©2009 SPIE.