Research and Development for the Hurdle Avoidance During Transplanting Manipulation Based on Kinect Vision Processing

Abstract

: To avoid damage to plants during the transplanting process, a transplanting method based on the combination of the Kinect machine visual system and the low-damage transplanting end effector was proposed to reduce the damage to the stems and leaves from transplanting end effectors during the transplanting process. The inclined manipulator was designed can avoid the characteristics of the seedling itself during the transplanting process to avoid obstacles. Under the experimental condition, the oblique transplanting manipulator assisted by the Kinect vision processing system achieved 4.70% leaf damage, 16.70% stem bending, 83.45% substrate integrity, and the transplanting quality parameters were 87.36%. The completion time of a single transplant was 8.32±0.4 s, the results proved that the low-damage transplanting manipulator based on the machine vision system can effectively reduce the damage rate of the stems and leaves. This obstacle avoidance transplant method can be extended to seedlings planted in 50 plugs. Research and development for hurdle avoidance during transplanting manipulation based on Kinect vision processing can provide theoretical support for future obstacle avoidance transplantation.