Transfer Learning for Unseen Robot Detection and Joint Estimation on a Multi-Objective Convolutional Neural Network
| Autor: | Inka Brijacak, Kyrre Glette, Jim Torresen, Ole Jakob Elle, Saeed Yahyanejad, Justinas Miseikis |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Computer science business.industry Deep learning 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Convolutional neural network Field (computer science) 030218 nuclear medicine & medical imaging Image (mathematics) Computer Science - Robotics 03 medical and health sciences Range (mathematics) 0302 clinical medicine Robot Artificial intelligence Transfer of learning business Robotics (cs.RO) computer Robotic arm 0105 earth and related environmental sciences |
| Zdroj: | ISR |
| Popis: | A significant problem of using deep learning techniques is the limited amount of data available for training. There are some datasets available for the popular problems like item recognition and classification or self-driving cars, however, it is very limited for the industrial robotics field. In previous work, we have trained a multi-objective Convolutional Neural Network (CNN) to identify the robot body in the image and estimate 3D positions of the joints by using just a 2D image, but it was limited to a range of robots produced by Universal Robots (UR). In this work, we extend our method to work with a new robot arm - Kuka LBR iiwa, which has a significantly different appearance and an additional joint. However, instead of collecting large datasets once again, we collect a number of smaller datasets containing a few hundred frames each and use transfer learning techniques on the CNN trained on UR robots to adapt it to a new robot having different shapes and visual features. We have proven that transfer learning is not only applicable in this field, but it requires smaller well-prepared training datasets, trains significantly faster and reaches similar accuracy compared to the original method, even improving it on some aspects. Comment: Regular paper submission to 2018 IEEE International Conference on Intelligence and Safety Robotics (ISR). Camera Ready paper |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|