ORGANIZING THE EXECUTION OF A MOBILE ROBOT OPERATION SCENARIO USING A NEUROMORPHIC TASK MANAGEMENT MECHANISM

The paper presents the results of a study of the possibility of forming and executing a mobile robotoperation scenario using neuromorphic information and control elements (logical elements "AND", "OR"and "NOT"; neuromorphic extrapolator; neuromorphic emergency detector; neuromorphic conditionedreflex formation mechanism). A brief description of these information and control elements is given. Inthis case, the segmented spike model of the CSNM neuron with the possibility of structural learning acts as a basic element. The trained CSNM model is capable of solving the binary classification problem, whichimplies the possibility of using it as a separate information control element – a state detector. It is proposedto organize the execution of the mobile robot operation scenario on the basis of universalneuromorphic modules using the specified neuromorphic information and control elements. The proposedtask management mechanism boils down to the following. Universal neuromorphic modules used as switchblocks are prioritized. The detection of a particular situation is performed by means of a universalneuromorphic module, the priority of which is higher, which leads to the inhibition of all universalneuromorphic modules, the priority of which is lower than this one. By adding or removing universalneuromorphic modules, as well as changing their priority, we get the desired behavior of a mobile robot.The paper presents the results of a study of the proposed mechanism for organizing a robot operationscenario on both a computer model and a real robot. A special emulator was developed for computermodeling, which made it possible to comprehensively investigate the proposed solution. Moving towardsthe target in a room with partitions was chosen as a test task. The experimental results have shown thefundamental applicability of the proposed mechanism for forming and executing a robot operation scenario.The paper highlights the main disadvantages of the current implementation: the possibility of situationsleading to looping of a set of actions performed by a mobile robot, as well as the need for manual coordinationof the main parameters of the scene and the mobile robot (metric characteristics of the specifiedsize of the scene zones, angular and linear velocity of the mobile robot, etc.). The ways to eliminate thesedisadvantages are proposed. The conclusion is made about the prospects of using the segmented spikemodel of a neuron and networks based on it for the tasks of controlling mobile robots