Train Carriage Disinfection Robot Based on Visual SLAM

Train Carriage Disinfection Robot Based on Visual SLAM

Under the trend of normalization of the prevention and control of the CoviD-19 epidemic, robots have gradually received attention in the field of assisting people in daily disinfection work. In this paper, a solution is presented for the localization, navigation and obstacle avoidance of the disinfection robot for train carriage. Integrated the vision and IMU sensors, the VIO localization scheme based on visual SLAM is adopted to make the scheme more adaptable and robust to the train carriage. In terms of navigation and obstacle avoidance, the global navigation and local navigation which using A* algorithm and DWA algorithm separately are combined to achieve the function. And on this basis, the method of obstacle expansion and limiting the obstacle avoidance range are proposed to improve the algorithm, so that the robot can move smoothly in the special environment of the train carriage. In the experiment, we built our disinfection robot and a simulated carriage environment on the spot, and completed the test of the algorithm. The results show that the VIO localization scheme and the improved algorithm can better adapt to the environment of the train carriage, and the robot can successfully realize the functions of localization, navigation and obstacle avoidance in the carriage.