Binocular Vision Navigation Method of Marine Garbage Cleaning Robot in Unknown Dynamic Scene

Zhang, C., 2020. Binocular vision navigation method of marine garbage cleaning robot in unknown dynamic scene. In: Yang, Y.; Mi, C.; Zhao, L., and Lam, S. (eds.), Global Topics and New Trends in Coastal Research: Port, Coastal and Ocean Engineering. Journal of Coastal Research, Special Issue No. 103, pp. 864–867. Coconut Creek (Florida), ISSN 0749-0208. When the current method was adopted for the vision navigation of marine garbage cleaning robot, the results of target garbage location were quite different from actual results, and the time of controlling the robot to the target location was too long, resulting in low positioning accuracy and poor path planning effect. Therefore, a method of binocular vision navigation of marine garbage cleaning robot in unknown dynamic scene was put forward. The camera was calibrated to extract the feature points in target image. Moreover, the moving path of robot was planned by dynamic obstacle avoidance algorithm based on escape velocity. In the unknown dynamic scene, the navigation of marine garbage cleaning robot was realized. Experimental results show that the proposed method has high positioning accuracy and good path planning effect.