Autonomous exploration of RRT robot based on seeded region growing

When the indoor environment is unknown, how to make robots carry out effective autonomous exploration and construct related maps is one of the key issues in the field of mobile robots. Due to the complexity of the real-world environment, how to build high-quality maps during the same exploration process is an important evaluation index for the autonomous exploration of mobile robots. Therefore, a rapid-exploration random tree (RRT) -based robot autonomous exploration method based on seed region growth is proposed. This method uses two-dimensional laser data, which mainly includes four steps: extraction of seed line segments, region growth, overlapping region processing, and impurity point processing. Using the grown laser data as a new sensor data input, a two-sided RRT boundary exploration is established. Local RRT exploration is used to detect the boundary points around the mobile robot; global RRT boundary exploration is used to detect the boundary points at the far end of the robot and the small corners on the map. The two methods are merged to speed up the search for boundary points. After the optimal boundary point is obtained, the robot is continuously moved to the best advantage through closed-loop control. The effectiveness of the proposed method is verified by simulation experiments and actual scenarios in a robot operating system (ROS).