Apple-Picking Robot Picking Path Planning Algorithm Based on Improved PSO

To solve the problem that the robot often collides with the obstacles such as branches around the fruit during picking due to its inability to adapt to the fruit growing environment, this paper proposes an apple-picking robot picking path planning algorithm based on the improved PSO. The main contents of the algorithm are: firstly, the fruit and its surrounding branches are extracted from the 3D point cloud data, and the picking direction of the fruit is calculated; then the point cloud on the surface of the fruit and branches is used to establish the spatial model of obstacles; finally, an improved particle swarm optimization (PSO) algorithm is proposed to plan the obstacle avoidance trajectory of the end-effector in space, which can dynamically adjust the velocity weights according to the trend of the particle fitness value and the position of the particle swarm center of mass. The experimental results show that the improved PSO has faster convergence speed than the standard PSO, and the path planning method proposed in this paper improves the fruit-picking success rate to 85.93% and reduces the picking cycle to 12 s. This algorithm can effectively reduce the collision between the manipulator and branches during apple picking and improve the picking success rate and picking efficiency.