Hand-eye calibration method and device based on BP neural network with SVD supervision

• Main Authors: CHEN HONGJIANG, HU JUN, ZHOU WEIJUN, NING WEIBO, FAN ZHUN, HE SHUXING, ZHU JIAQI, CHEN XUCONG, GU MINQIANG, YUAN YE, TAN YECHENG
• Format: Patent
• Language: Chinese; English
• Published: 29.07.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a hand-eye calibration method and device based on a BP neural network with SVD supervision. The method comprises the following steps: 1) establishing a mechanical arm base coordinate system and an optical system coordinate system; (2) the tail end of the mechanical arm and the handheld probe are controlled to move on the calibration platform for multiple times, a first coordinate set of the handheld probe in an optical system coordinate system and a second coordinate set of a calibration tool at the tail end of the mechanical arm in a mechanical arm base coordinate system are obtained, and a training set and a test set are constructed; 3) pre-training the established BP neural network model by using the training set to obtain an initial BP neural network model; 4) performing strong supervision training on the initial BP neural network model by using the training set updated by the SVD algorithm to obtain an optimized BP neural network model; and 5) testing and optimizing the BP neural