Mobile robot positioning method and system based on three-dimensional point cloud and vision fusion

Abstract

The invention provides a mobile robot positioning method and system based on three-dimensional point cloud and visual fusion, and the method comprises the steps: building an environment map, carryingout the fusion of point cloud and visual features, matching a map, and carrying out the positioning. Wherein the environment map is a feature grid map for establishing an environment, each grid in thefeature grid map stores a point set composed of feature points extracted from the point cloud and feature points of the visual image, and a height value, an intensity value and a normal vector projection value are extracted; the point cloud and visual feature fusion is to project feature points extracted from the image to a point cloud space and form joint feature points with point cloud features. According to map matching and positioning, joint feature points are projected to a two-dimensional grid, feature vectors are extracted, the feature grid is matched with the map, a histogram filter is adopted to determine the posterior probability of each candidate pose, and the position of the robot in the map is determined based on the posterior probabilities.

Description

technical field [0001] The present invention relates to the technical field of mobile robot positioning and navigation, in particular to a mobile robot positioning method and system based on three-dimensional point cloud and vision fusion, especially to a feature grid map matching positioning method for mobile robots based on multi-sensor fusion. Background technique [0002] Mobile robots usually have the function of autonomous positioning and navigation. They need to complete the construction of an environmental map and achieve high-precision positioning based on the constructed map. The positioning problem is a key issue in the field of robotics. [0003] Localization systems play a pivotal role in autonomous vehicles. Other modules, such as perception and path planning, perform corresponding operations based on the positioning results generated by the positioning system to varying degrees. The accuracy of positioning is one of the keys that directly affects the success ...

AI Technical Summary

Problems solved by technology

However, the existing point cloud map solutions need to store a large amount of point cloud data and match the real-time point cloud with the entire map.

However, visual SLAM construction maps are difficult to achieve accurate positioning in outdoor scenes with sparse features.

Images