Application of Sensor Data Information Cognitive Computing Algorithm in Adaptive Control of Wheeled Robot

Abstract

The four-wheel drive robot has a coupling relationship between the four wheels due to the characteristics of the wheel train distribution. During the operation, there are problems with the stability and control accuracy of the robot’s overall motion. To solve this problem, this paper constructs an adaptive control algorithm based on cognitive computing. We use real-time sensor data as learning samples for online learning, and obtain new sample averages, new feature values, feature vectors, and new subspaces. This information is stored in the semantic long-term memory by projecting the newly read sample into the subspace obtained in the previous calculation. In addition, fuzzy control and partial discharge control are combined to correct the stored information online. Taking into account the distribution characteristics of the wheel system structure, we reasonably allocate the overall error to a single wheel, which will convert the overall error correction into a single wheel error correction. The simulation experiment in the Matlab-Simulink environment shows that after using the fuzzy adaptive controller for error correction, the error value of the robot’s linear velocity and angular velocity is between −1 and 1.5. In addition, the followability and the performance of tracking the target are obviously improved, and the accuracy of robot motion control is improved.