Repositioning method for mobile robot

Abstract

The invention discloses a repositioning method for a mobile robot. The repositioning method comprises the following steps: S1, establishing a motion model of the mobile robot, forecasting a posture state of the mobile robot at the current moment t according to a posture state of the mobile robot at the previous moment t-1 and an input control value in the combination of a Monte Carlo positioning method, and obtaining particle sampling distribution of the mobile robot at the moment t; S2, establishing a sensing model of a laser ranging sensor, and calculating a weight value of each particle according to laser ranging sensor information acquired at the moment t; S3, establishing a sensing model of a vision sensor, and calculating a weight value of each particle according to vision sensor information acquired at the moment t; S4, updating the weight values of the particles according to the sensing model of the laser ranging sensor and the sensing model of the vision sensor; and S5, repeating the steps S1 and S4 until the mobile robot is repositioned successfully. According to the repositioning method, the repositioning precision and the speed of the mobile robot are improved.

Description

technical field [0001] The invention relates to a mobile robot, in particular to a relocation method for a mobile robot. Background technique [0002] In recent years, the relocalization problem has become a hot topic in the field of mobile robotics. Mobile robot relocalization is a foundation for mobile robot to realize intelligent navigation and environment exploration research, and it is also one of the key technologies for mobile robot to realize real intelligence and complete autonomy. [0003] The relocalization of a mobile robot is to re-determine the pose of the robot based on the known map environment and sensor data. Research on mobile robot relocalization has largely focused on two types of sensors. [0004] One is the laser ranging sensor, which is very fast and can obtain very accurate distance and other information. Only the laser ranging sensor is used for mobile robot relocation, and the drawing is accurate and has a high degree of accuracy in a small envir...

AI Technical Summary

Problems solved by technology

[0004] One is the laser ranging sensor, which is very fast and can obtain very accurate distance and other information. Only the laser ranging sensor is used for mobile robot relocation, and the drawing is accurate and has a high degree of accuracy in a small environment. However, in a large environment, due to the cumulative error, the relocation of the robot is not ideal, and because the laser ranging sensor has less information, relocation cannot be achieved well in a more complex environment.

[0005] Another commonly used sensor is the visual sensor. The amount of information obtained by the visual sensor is rich. When only using the visual sensor for mobile robot relocation, due to the excessive data to be processed, the real-time performance of the algorithm cannot be guaranteed, especially in large-scale applications. Or in an environment where the feature points are not obvious, it is easy to have the problem that relocation cannot keep up with the running speed of the robot, resulting in poor relocation accuracy.

Images