XCR-1: An Experimental Cognitive Robot Based on an Associative Neural Architecture

Abstract

The experimental cognitive robot XCR-1 is a small three-wheel robot with gripper hands, multiple sensory modalities, and self-talk. The robot XCR-1 is designed for studies and experiments with a new paradigm for cognitive computation, namely an associative neural processing style that inherently and seamlessly combines sub-symbolic and symbolic computation. This operation is realized by using associative neurons and neuron groups organized according to the Haikonen Cognitive Architecture. Recently, there have been many efforts toward machine consciousness, and the Haikonen Cognitive Architecture is one attempt in that direction. Human consciousness is characterized by subjective inner experience that is related to qualia. Accordingly, it can be proposed that true conscious machines should also have some kind of inner experience and qualia. On the other hand, it has been argued that qualia are direct and cannot be artificially realized in symbolic systems. In order to facilitate qualia-related practical investigations, the robot XCR-1 utilizes direct perception processes, with dedicated hardware and without symbolic pre-programmed algorithms. The robot XCR-1 does not utilize microprocessors or programs of any kind. Natural language is one manifestation of symbolic processing. The robot XCR-1 is designed also for experiments with simple speech and the basic grounding of the meaning of words. The experiments with the robot XCR-1 could be greatly enhanced if dedicated associative neuron group chips were available.