Combining active learning and reactive control for robot grasping |
| |
| Authors: | OB Kroemer R Detry J Piater J Peters |
| |
| Affiliation: | 1. Max Planck Institute for Biological Cybernetics, Spemannstr. 38, 72076 Tübingen, Germany;2. Universit de Liége, INTELSIG Lab, Department of Electrical Engineering and Computer Science, Belgium;1. University of Ni?, Faculty of Mechanical Engineering, Department for Mechatronics and Control, Aleksandra Medvedeva 14, 18000 Ni?, Serbia;2. Department of Software Engineering, Faculty of Computer Science and Information Technology, University of Malaya, 50603, Kuala Lumpur;3. Department of Computer and Information Technology, Foulad Institute of Technology, Foulad shahr, Isfahan 8491663763, Iran;4. Young Researchers and Elite Club, Mashhad Branch, Islamic Azad University, Mashhad, Iran;5. Department of Computer System and Technology,Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia;6. Department of Mechanical Convergence Engineering, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 133-791, Republic of Korea;1. Learning Algorithms and Systems Laboratory (LASA), École Polytechnique Fédérale de Lausanne (EPFL), Switzerland;2. Computer Vision & Active Perception Lab, Centre for Autonomous Systems, Royal Institute of Technology, Stockholm, Sweden;1. Institute of Systems and Robotics, Department of Electrical and Computer Engineering, University of Coimbra - Polo II, 3030-290 Coimbra, Portugal;2. Citard Services Ltd., Cyprus;3. Robotics Institute, Khalifa University, Abu Dhabi, United Arab Emirates |
| |
| Abstract: | Grasping an object is a task that inherently needs to be treated in a hybrid fashion. The system must decide both where and how to grasp the object. While selecting where to grasp requires learning about the object as a whole, the execution only needs to reactively adapt to the context close to the grasp’s location. We propose a hierarchical controller that reflects the structure of these two sub-problems, and attempts to learn solutions that work for both. A hybrid architecture is employed by the controller to make use of various machine learning methods that can cope with the large amount of uncertainty inherent to the task. The controller’s upper level selects where to grasp the object using a reinforcement learner, while the lower level comprises an imitation learner and a vision-based reactive controller to determine appropriate grasping motions. The resulting system is able to quickly learn good grasps of a novel object in an unstructured environment, by executing smooth reaching motions and preshaping the hand depending on the object’s geometry. The system was evaluated both in simulation and on a real robot. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
