Cleaning robot motion control system and method based on multi-sensor fusion

Abstract

The invention discloses a cleaning robot motion control system based on multi-sensor fusion. The cleaning robot motion control system comprises an environment sensing module, a bottom layer main control module, a micro-processing module, a central processing module and a servo driving module. The environment sensing module achieves control over the moving posture of the cleaning robot through multi-sensing-mode fusion of an AI target recognition module, an area array radar module and a laser radar module. The system and the method are used for the cleaning robot, flexible control can be achieved, manual interference on cleaning operation of the autonomous cleaning robot is avoided, the crossing risk is greatly reduced, the operation efficiency of the cleaning robot is improved, and reliability and safety are improved.

Description

technical field [0001] The invention relates to the technical field of cleaning robots, in particular to a motion control system and method for a cleaning robot based on multi-sensor fusion. Background technique [0002] With the development of artificial intelligence technology, especially the continuous maturity of unmanned driving technology, the commercialization of low-speed unmanned commercial cleaning robots in indoor and outdoor environments has become possible. With the acceleration of population aging and the low cleaning efficiency and high work intensity, commercial cleaning robots rely on artificial intelligence technology, including SLAM algorithms, computer vision, multi-sensor fusion algorithms and automatic path planning. and other technologies to automatically complete the cleaning task of full-coverage ground in large scenes, and liberate a large number of cleaning workers from repetitive and inefficient work environments. [0003] At present, common clea...

AI Technical Summary

Problems solved by technology

However, the depth camera relies heavily on pure image feature matching, so the effect is very poor when the light is dark or overexposed. In addition, if the measured scene itself lacks texture, it is difficult to perform feature extraction and matching.

The ultrasonic wave is based on the propagation speed of the ultrasonic wave in the air is known, and the ultrasonic wave is measured by the characteristics of the reflection of the obstacle. b. The ultrasonic ranging sensor emits sound waves and has the fan-shaped emission characteristics of sound waves. Therefore, when there are many obstacles in the place where the sound waves pass, there will be more reflected sound waves, more interference, and error reporting; c. Ultrasonic waves are based on emission and reception. The actual distance from the launch point to the obstacle is calculated by the time difference. Therefore, ultrasonic ranging has a delay, and there is a high risk of delay sensors for mobile robots.

[0004] It can be seen that there are many technical drawbacks in the cleaning robots currently on the market, but there is no way for the cleaning robot to distinguish whether the obstacles ahead are objects or pedestrians through the fusion of AI target recognition technology, area array radar modules and lidar multi-sensing methods. a method of motion control

Images