Institute Homepage DE Sign In

Back

Empirical Inference Article 2010

Combining active learning and reactive control for robot grasping

Thumb ticker sm 12009745 10103538825457245 7502907506146263960 n
Empirical Inference
Jan Peters
Research Group Leader
no image
Empirical Inference
Oliver Kroemer
no image
Empirical Inference
Justus Piater

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 preshapin g the hand depending on the object’s geometry. The system was evaluated both in simulation and on a real robot.

Author(s): Kroemer, O. and Detry, R. and Piater, J. and Peters, J.
Journal: Robotics and Autonomous Systems
Volume: 58
Number (issue): 9
Pages: 1105-1116
Year: 2010
Month: September
Day: 0
Bibtex Type: Article (article)
DOI: 10.1016/j.robot.2010.06.001
Digital: 0
Electronic Archiving: grant_archive
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik
Links:

BibTex 

@article{6636,
  title = {Combining active learning and reactive control for robot grasping},
  journal = {Robotics and Autonomous Systems},
  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 preshapin
  g the hand depending on the object’s geometry. The system was evaluated both in simulation and on a real robot.},
  volume = {58},
  number = {9},
  pages = {1105-1116},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = sep,
  year = {2010},
  slug = {6636},
  author = {Kroemer, O. and Detry, R. and Piater, J. and Peters, J.},
  month_numeric = {9}
}