Automatic drawing device and method

Abstract

The invention provides an automatic drawing device and a method, which relates to the technical field of robot drawing. The automatic drawing device and the method of the invention transform unknown environmental information into a two-dimensional dynamic raster map recognizable by a robot. When the robot moves, the raster map follows suit and updates as well, which avoids the multiple times of adjustments seen by manual drawing and the tedious work required to follow the movement of the robot, therefore, reducing the time for the robot to draw greatly. In addition, through the establishment of a quadtree model, moving targets can be clearly defined; with one time path planning on a local part of the raster map, a whole process can be done automatically, achieving high computational efficiency and simple programming. And at the same time, the robot can acquire sufficient cloud data to ensure the clarity of the map.

Description

technical field [0001] The invention relates to the field of robot drawing, in particular to an automatic drawing device and method. Background technique [0002] With the development of computer science and technology, artificial intelligence, and computer vision technology, the simultaneous positioning and map creation of intelligent autonomous mobile robots has become a research hotspot in the field of robotics. The precise realization of autonomous positioning and map creation reflects the latest achievements in computer vision and robotics. [0003] The robot starts to move from an unknown position in an unknown environment. During the movement, the robot uses the odometer, wheeled code disc, and depth camera for position estimation and sensor data collection to realize its own positioning, and at the same time build an incremental map. In SLAM, the robot uses its own sensors to identify the feature marks in the unknown environment, and then estimates the global coordi...

AI Technical Summary

Problems solved by technology

However, for the creation of maps in complex environments, the trajectory and attitude adjustment of robots need to be controlled by humans. Even for engineers with rich operating experience, it takes multiple practices to establish a map of the entire unknown environment.

This process often takes a lot of time, and in a complete map, for the robot, there may also be blind spots (positions that the robot cannot scan), and it is difficult to ensure consistency with the real environment

Overall, it is usually time-consuming and cost-intensive to move in complex environments by human-controlled robotic mapping

[0004] In the process of artificially controlling the robot to map, any collision between the robot and the surrounding obstacles will cause a large matching error in the creation of the map. Each collision is likely to cause the failure of the entire map creation. Considering various factors, The current robot map creation needs to be further optimized

Images