Hexapod robot autonomous navigation closed-loop controller with fuzzy neural network

Abstract

The invention discloses a hexapod robot autonomous navigation closed-loop controller with a fuzzy neural network, which comprises a hexapod robot formed by a shell and a steering engine, a navigation control system, a safety distance SD decision module, a fuzzy BP neural network module and a neural network weight coefficient training and adjusting module internally arranged in the navigation control system, a detection steering engine and an azimuth sensor arranged at the center of the hexapod robot, and an ultrasonic sensor arranged on the detection steering engine. According to the hexapod robot autonomous navigation closed-loop controller with the fuzzy neural network, a closed-loop control method with a feedback function is adopted, obstacle distance information inputted by the system is obtained through sector scanning of the ultrasonic sensor, and errors caused by interference of a beam angle and the signal crosstalk problem can be avoided, and through the fuzzy neural network and operation of the safe distance SD decision module, the robot can safely and quickly arrive at a target point, and no redundant path is generated.

Description

technical field [0001] The invention relates to a hexapod robot controller, in particular to a fuzzy neural network hexapod robot autonomous navigation closed-loop controller, which belongs to the technical field of robot navigation control. Background technique [0002] The autonomous navigation of robots is one of the core technologies in the field of mobile robot research, and has played an important role in the fields of industry, agriculture, service and medical care; traditional autonomous navigation algorithms include artificial potential field method, grid method and free space method etc. Usually, the surrounding environment is required to be known, and there are problems such as difficulty in obtaining environmental information and low efficiency of path optimization; at present, the research on autonomous navigation of robots tends to develop in the direction of intelligence, and the artificial neural network-based, fuzzy Logic control and navigation algorithm com...

AI Technical Summary

Problems solved by technology

[0002] The autonomous navigation of robots is one of the core technologies in the field of mobile robot research, and has played an important role in the fields of industry, agriculture, service and medical care; traditional autonomous navigation algorithms include artificial potential field method, grid method and free space method etc. Usually, the surrounding environment is required to be known, and there are problems such as difficulty in obtaining environmental information and low efficiency of path optimization; at present, the research on autonomous navigation of robots tends to develop in the direction of intelligence, and the artificial neural network-based, fuzzy Logic control and navigation algorithm combining fuzzy control and neural network; artificial neural network has strong learning and training ability, but lacks the ability to process and describe fuzzy information; fuzzy logic control has logical reasoning ability, but learning and self-adaptive ability The weakness of the system limits its application in unstructured environments; the combination of fuzzy control and neural network can make the system have both the learning and training ability of neural network and the fuzzy reasoning ability of fuzzy control; but these algorithms currently proposed The open-loop control method is adopted, and compared with the closed-loop control method, the performance of the robot path selection and speed control is lacking; the robot obstacle avoidance in the prior art will be provided with multiple ultrasonic sensors, and the ultrasonic sensors are due to the ultrasonic beam angle. The existence of the ultrasonic sensor can not accurately obtain the boundary information of the obstacle; in addition, the safety of the robot's walking is very critical in the autonomous navigation system. The problem arises, so the robot needs to keep a certain safe distance from the obstacle to perform the behavior of turning around. The judgment of this safe distance depends on the two factors of the robot’s overall size and travel speed; in the prior art, the safe distance is Single definition of a certain distance, resulting in path redundancy

Images