Cooperative Search and Containment Method Based on Ground Robot

Abstract

The present invention relates to technologies such as image processing, real-time mapping, path planning, and robots. In order to propose a collaborative search and containment platform for ground robots, the present invention uses a ground robot equipped with a camera and a processor for a collaborative search and containment method based on ground robots. For target search, one of the robots is additionally equipped with a laser radar, and the robot equipped with a laser radar uses the laser radar to build an environmental map and transmits the map to other robots. All robots obtain and process image information of the surrounding environment through the camera. The pre-trained detection and tracking algorithm recognizes the specified target object among multiple objects, tracks it for a long time, and transmits data between robots through a wireless network; when a robot detects a target, it will track it, and Send the target location information to other ground robots in real time for real-time path planning and round-up. The invention is mainly applied to robot design occasions.

Description

technical field [0001] The invention relates to the fields of computer vision, image processing, real-time mapping, path planning, etc., and solves how to search and block a specific target in an unknown environment with multiple robots. Background technique [0002] With the development of robot technology, people's requirements for robots are no longer limited to a single robot. In recent years, with the emergence of robot production lines and the application of flexible manufacturing systems, researchers are becoming more and more interested in the system platform composed of multiple robots, and the research of multiple robots has become an important aspect of robotics research. Especially in the field of military industry, how multiple robots can establish an environmental map in an unknown environment, detect and track specific targets, and finally realize target roundup has become a hot topic. [0003] There are three main parts of ground robot collaborative search a...

AI Technical Summary

Problems solved by technology

If the detection algorithm is only used for tracking, it is difficult to achieve the effect of real-time detection on the embedded system of the ground robot. However, if the tracking algorithm is used alone, the first frame needs to be manually initialized, which cannot achieve the effect of autonomous tracking of the target, and if the tracking fails , it is impossible to recapture the target, how to learn from each other is an urgent problem to be solved

The purpose of path planning is to establish a smooth and reasonable path in the known environmental map, and to find the optimal route as much as possible on the basis of avoiding obstacles on the environmental map. Commonly used methods include A* (A-star algorithm, heuristic Search), RRT (Rapidly-exploring Randomized Trees, fast exploration random tree) algorithm, etc., but when tracking moving objects, real-time path planning is required, and the above methods are difficult to achieve high efficiency and accuracy

Images