A method of robot ranging based on multi-sensor fusion

Abstract

Robot ranging is an important foundation that a robot senses the environment. Methods used in the industry at the present involve a ranging sensor, binocular vision, laser scanning radar and the like. The ranging sensor is low in cost, but relatively poor in effect; the binocular vision needs a complicated algorithm and a high-performance calculation chip; the laser scanning radar is expensive. Although the ranging sensor is low in cost and relatively poor in effect, sensors with different theories can be complemented one another. Therefore, according to the advantages and the disadvantages of different sensors and the state (the speed size and the distance) of the robot, a value of the current selected proper sensor is decided, so that the relatively good ranging effect can be achieved, namely a robot ranging algorithm based on multi-sensor fusion is achieved; therefore, low-cost and high-performance robot ranging is realized.

Description

technical field [0001] The present invention relates to a robot ranging method, in particular to a robot ranging method based on multi-sensor fusion. Background technique [0002] Sensor technology is a major aspect of intelligence. It enables the robot to perceive the uncertain environment around it and respond accordingly. [0003] Robot ranging is an important basis for robots to perceive the environment. At present, the methods used in the industry mainly include ranging sensors, binocular vision, laser scanning radar and other methods; among them, ranging sensors such as infrared ranging sensors and ultrasonic ranging sensors, although the price It is cheap, but the ranging effect is poor; binocular vision requires complex algorithms and high-performance computing chips; laser scanning radar is expensive, ranging from thousands of dollars to tens of thousands of dollars. It can be seen that due to its own limitations, the accuracy and reliability of a single ranging s...

Images