Improving Data Efficiency of Self-supervised Learning for Robotic Grasping
| Autor: | Lars Berscheid, Torsten Kröger, Thomas Rühr |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
0209 industrial biotechnology Robot kinematics Artificial neural network Computer science business.industry GRASP 02 engineering and technology Machine learning computer.software_genre Task (project management) 03 medical and health sciences Computer Science - Robotics 020901 industrial engineering & automation 0302 clinical medicine Grippers Data efficiency 030220 oncology & carcinogenesis Task analysis Artificial intelligence business Robotics (cs.RO) computer Haptic technology |
| Zdroj: | ICRA |
| Popis: | Given the task of learning robotic grasping solely based on a depth camera input and gripper force feedback, we derive a learning algorithm from an applied point of view to significantly reduce the amount of required training data. Major improvements in time and data efficiency are achieved by: Firstly, we exploit the geometric consistency between the undistorted depth images and the task space. Using a relative small, fully-convolutional neural network, we predict grasp and gripper parameters with great advantages in training as well as inference performance. Secondly, motivated by the small random grasp success rate of around 3%, the grasp space was explored in a systematic manner. The final system was learned with 23000 grasp attempts in around 60h, improving current solutions by an order of magnitude. For typical bin picking scenarios, we measured a grasp success rate of 96.6%. Further experiments showed that the system is able to generalize and transfer knowledge to novel objects and environments. Accepted for ICRA 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|