Research on Hand-eye calibration method based on genetic BP neural network for harvesting Robot

• 1、Institute of Industry & Equipment Technology, Hefei University of Technology, Hefei 230041
• 2、Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031

Abstract：In the field of harvesting robot control with vision feedback, hand-eye system calibration is very important which directly affects the precision of the task.In order to improve the accuracy of fixed binocular camera hand-eye calibration, a hand-eye system calibration algorithm using back-propagating (BP) neural network optimized by genetic algorithm was proposed in this paper. The BP neural network calibration model was established by using the coordinates of the target in the camera coordinate system and the robot arm coordinate system as the input and output. Because the BP neural network model has the disadvantage of being trapped in the local minimum, a genetic algorithm is introduced to optimize the initial weights and thresholds of the BP neural network. The results showed that compared with the traditional multiple linear regression fitting model and BP neural network model, The BP neural network model optimized by genetic algorithm can significantly reduce the calibration error and speed up the convergence. The average errors for the measured distances between the tested results and the predicted ones by the proposed genetic BP neural network model, the conventional BP neural network model, and the linear regression fitting model were 1.7126mm, 2.4002mm, and 3.3771mm, respectively.

Keywords： Harvesting robot fixed binocular vision Hand-eye calibration genetic back-propagating (BP) neural network linear regression