Design of Automatic Target Following Control System for Mobile Robots Based on Deep Learning
Mobile robots are easily affected by surrounding environments when following moving targets,resulting in a decrease in target recognition accuracy and thus affecting the effectiveness of automatic following control.For this purpose,a deep learning based automatic target following control system for mobile robots is designed.The system framework is composed of a perception layer,processing and control layer,and execution layer.The visual sensor,ultrasonic sensor and MEMS sensor in the perception layer are used to collect the information and transmit it to the processing and control layer.The MCU processor runs two programs,the former program processes the images and recognizes the targets by using the residual learning network,depth convolution network and Long short-term memory neural network in the depth learning,the latter program uses the ranging information of the ultrasonic sensor to calculate the target coordinates.The PLC microcontroller carries the control program,combines the angle information collected by MEMS sensors,and designs a dual loop controller based on PID to achieve automatic target following control of the mobile robot.Ex-perimental results show that,the designed system only mistakenly recognizes one image in a dim environment,with strong target rec-ognition function.The average following error of angle and distance in different environments is always below 1.22° and 0.074 m,and it has high anti environmental interference ability.
deep learningmobile robotstarget automatic followingPID control system
万方数据
维普
