Coal mine disaster relief robot navigation system and method based on information fusion

Abstract

The invention discloses a coal mine disaster relief robot navigation system based on information integration and a method. An ultrasonic wave module 1, a vision module 2 and an inertia module 3 form an information acquisition module, the information acquired by the information acquisition module is processed by an information processing module, so that the path planning is realized; and the improved neural network-extended Kalman filter (NNEFK) method is provided, and the method can effectively solve the problem that the information integration is not matched, improves the convergence and thereal-time property, and reduces the errors of the navigation system and the method by the design of a feedback link. The navigation system and the method can effectively improve the navigation capability of a coal mine disaster relief robot.

Description

technical field [0001] The invention relates to a robot navigation system and method, in particular to a navigation system and method using multi-sensor information fusion technology applied to coal mine disaster relief robots. Background technique [0002] my country is a big country of coal production and consumption. In my country's energy industry, coal accounts for about 70% of my country's primary energy production and consumption structure. According to the forecast of the National Energy Work Conference, by the end of the "Twelfth Five-Year Plan", my country's total coal consumption will exceed 4 billion tons, of which domestic production will exceed 3.8 billion tons, and my country's coal production will account for 50% of the global total. The continuous increase of coal production, coupled with the poor natural conditions of coal mines, relatively backward technology and lack of management, have resulted in frequent mine disasters and accidents, with heavy casualt...

AI Technical Summary

Problems solved by technology

Compared with previous navigation systems and methods, the present invention adopts ultrasonic navigation, visual navigation and inertial navigation to design a multi-sensor fusion navigation system and method suitable for coal mine disaster relief robots, and proposes an improved neural network-extended Kalman filter method (NNEKF: Neural network Extended Kalman Filter), this algorithm can effectively solve the problem of information fusion mismatch, improve the convergence and real-time performance of the system, and reduce the error

Images