{"number":"US12703086B2","kindCode":"B2","documentType":"grant","title":{"original":"Transformation for covariate shift of grasp neural networks","english":"Transformation for covariate shift of grasp neural networks"},"abstract":{"original":"A covariate shift generally refers to the change of the distribution of the input data (e.g., noise distribution) between the training and inference regimes. Such covariate shifts can degrade the performance grasping neural networks, and thus robotic grasping operations. As described herein, an output of a grasp neural network can be transformed, so as to determine appropriate locations on a given object for a robot or autonomous machine to grasp.","english":"A covariate shift generally refers to the change of the distribution of the input data (e.g., noise distribution) between the training and inference regimes. Such covariate shifts can degrade the performance grasping neural networks, and thus robotic grasping operations. As described herein, an output of a grasp neural network can be transformed, so as to determine appropriate locations on a given object for a robot or autonomous machine to grasp."},"applicants":["Siemens Aktiengesellschaft"],"inventors":["Juan L. Aparicio Ojea","Heiko Claussen","Ines Ugalde Diaz","Gokul Narayanan Sathya Narayanan","Eugen Solowjow","Chengtao Wen","Wei Xi Xia","Yash Shahapurkar","Shashank Tamaskar"],"filingDate":"2023-10-17","publicationDate":"2026-08-11","grantDate":"2026-08-11","verifiedWithOffice":true,"pdfUrl":"https://downloadpatent.com/pdf/US12703086B2.pdf","pages":{"en":"https://downloadpatent.com/patent/US12703086B2","zh-Hant":"https://downloadpatent.com/zh-Hant/patent/US12703086B2","ja":"https://downloadpatent.com/ja/patent/US12703086B2"}}