Research on Continuous Obstacle Avoidance Picking Planning Based on Multi-Objective Clustered Crabapples

In view of the low efficiency and slow development of fruit and vegetable picking in China, the picking sequence and obstacle avoidance of clustered crabapples were studied with them as the picking target. The multi-objective picking sequence of crabapples was planned, and the adaptive pheromone factor, heuristic function, and volatile factor were used to improve the ant colony (ACO) algorithm, so as to improve the convergence speed, adaptability, and global search ability of the algorithm. In order to avoid the collision between the robotic arm and the branches of the fruit tree, the three-dimensional reconstruction of the fruit tree was carried out, the shape and position information of the obstacle branch was determined, the artificial potential field was fused with the RRT, the search orientation of the RRT algorithm was enhanced, the inflection point was reduced, and the convergence speed was improved. The results showed that the average success rate of picking was 89.58%, and the robotic arm did not collide with the branches according to the planned picking sequence during the picking process, so as to achieve the picking purpose and picking effect.