XCR-1: An Experimental Cognitive Robot Based on an Associative Neural Architecture Pentti O. A. Haikonen Received: 7 March 2011 / Accepted: 25 April 2011 / Published online: 4 May 2011 �� Springer Science+Business Media, LLC 2011 Abstract The experimental cognitive robot XCR-1 is a small three-wheel robot with gripper hands, multiple sen- sory 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 pro- cessing 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 Architec- ture. Recently, there have been many efforts toward machine consciousness, and the Haikonen Cognitive Architecture is one attempt in that direction. Human con- sciousness 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 experi- ments 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. Keywords Cognitive robots Machine consciousness Cognitive architecture Associative processing Robot speech Introduction The experimental cognitive robot XCR-1 is a small three- wheel robot with gripper hands, multiple sensory modali- ties, and self-talk [1]. Experimental robots can be favorably used as test beds for cognitive computation methods, especially those that relate to machine cognition and involve sensorimotor integration with motor action gener- ation and control. The acid test of real-world perception and action provides challenges that are easily overlooked and bypassed in computer simulations. Usually, experimental robots are built with micropro- cessors and with a possible link to a master computer, which would execute the actual cognitive computations. These kinds of robots are program controlled, and here, the robot mechanism can be considered as another mechanical output device, not really different from, say, an ink jet printer. More rarely, an experimental robot is realized without the help of a microprocessor or a connected computer. In that case, the robot would not be governed by a program. Associative neural networks can be used to control a robot without any programs or high-level algo- rithms. The robot XCR-1 is realized in this way. However, it can be asked why a robot should use some exotic neural hardware instead of the well-tried micropro- cessors. This question can be put in another way: Consid- ering the robot XCR-1, why less than one thousand transistors are used instead of ten million transistors? Why should one write thousands of lines of computer code when none is needed? Properly designed associative neural P. O. A. Haikonen (&) Department of Philosophy, University of Illinois at Springfield, One University Plaza, Springfield, IL 62703, USA e-mail: pentti.haikonen@pp.inet.fi 123 Cogn Comput (2011) 3:360���366 DOI 10.1007/s12559-011-9100-9

systems are very efficient, self-learning and require no programming. They are also more close to their biological inspiration, the brain and may, perhaps, be better platforms for potential qualia than symbolic programs. The robot XCR-1 is one of the few non-trivial robots, which do not utilize microprocessors or digital processing. Instead, it is based on the associative neural architecture of the Haikonen Cognitive Architecture type [2]. This archi- tecture utilizes an associative neural processing style that inherently combines sub-symbolic and symbolic compu- tation. The XCR-1 robot is depicted in Fig. 1. The Haikonen Cognitive Architecture integrates sen- sory, memory, and motor systems and functions seamlessly within an associative network. The sensory systems of the XCR-1 extract sensory feature signals that are used to indicate the presence of the sensed real-world features. Signal processing is executed by associative neurons that allow the utilization of the same signals as symbols for completely different entities. Human conscious experience involves qualia, the sub- jective qualities of percepts. It can be argued that there can be no human-like consciousness without qualia. Therefore, a conscious robot should also have qualia, but these qualia would not have to be similar to human qualia. The real nature of qualia is not resolved yet, and consequently, the realization of machine qualia is not a straightforward engineering task. The cognitive system of the robot XCR-1 is designed to accommodate the idea that qualia are related to direct representations of sensory information as opposed to symbolic representations that call for interpretation or additional explanatory information [3]. These kinds of indirect symbolic representations would include numeric representations. An example of quale is pain the feel of pain calls for no interpretation, pain is pain. In a computer, pain could be symbolically represented as a number in a file the higher number, the higher pain. It should be obvious that no subjective experience would be present here. In contrast, in direct systems, pain would appear as a dynamic system reaction with system-wide consequences. Recently, the value of emotions in cognition has been recognized. Emotional value evaluation may help to decide the order of importance of the perceived threats and affordances. Emotions may also offer templates for fast responses. Without emotions, learning from experience may be inefficient. Thus, a cognitive robot should also incorporate emotions. The cognitive system of the robot XCR-1 is designed for experiments with emotional moti- vation and behavior control. The body of the robot is shock sensitive, and the robot can be ������punished������ by hitting it. A ������petting������ sensor is provided for ������reward������. These functions provide the basis for the emotional evaluation of percepts and the modification of behavior according to learned emotional value. Associative Processing The robot XCR-1 utilizes associative processing [4], which is based on the use of associative neurons and associative neuron groups. During learning, an associative neuron associates an associative signal vector with the so-called main signal so that later on, the same associative signal vector will evoke the main signal as the output of the neuron. Basically, this operation is similar to the Pavlovian conditioning. Modified Hebbian learning is used learning takes place when the main signal and the associative signal vector coincide, i.e., are present at the same time. One or more coincidences may be required depending on the actual application. Associative neurons are grouped into neuron groups allowing the selection of the most strongly evoked signal. This selection is effected by a Winner-Takes-All threshold operation. Associative neuron groups are also used to associate vectors with vectors. Associative neuron groups are kinds of associative memories. Interference modes that plagued early associative memories are remedied here. Technical details about the used associative neurons and neuron groups are presented in [2]. The principle of the associative neuron group is presented in Fig. 2. Usually, main signals and associative signals originate from sensory pre-processes and indicate the presence of a given sensory feature. In that case, the associative neuron group can allow the transition from sub-symbolic to sym- bolic processing a main signal vector may be taken as a symbol for the corresponding associative signal pattern. For instance, an associative signal pattern may depict a visual object, while the associated main signal pattern, Fig. 1 The XCR-1 robot Cogn Comput (2011) 3:360���366 361 123