Learning to select and generalize striking movements in robot table tennis
Обучение выбору и обобщению ударных движений робота в настольном теннисе
2013-01-30
SCID: 54.1/wcctdh93
Discuss with AI
dynamical systemskinesthetic teach-inmixture of motor primitivesmotor primitivesrobot table tennis
Figures from the paper
Abstract (AI)
Learning new motor tasks from physical interactions is an important goal for both robotics and machine learning. However, when moving beyond basic skills, most monolithic machine learning approaches fail to scale. For more complex skills, methods that are tailored for the domain of skill learning are needed. In this paper, we take the task of learning table tennis as an example and present a new framework that allows a robot to learn cooperative table tennis from physical interaction with a human. The robot first learns a set of elementary table tennis hitting movements from a human table tennis teacher by kinesthetic teach-in, which is compiled into a set of motor primitives represented by dynamical systems. The robot subsequently generalizes these movements to a wider range of situations using our mixture of motor primitives approach. The resulting policy enables the robot to select appropriate motor primitives as well as to generalize between them. Finally, the robot plays with a human table tennis partner and learns online to improve its behavior. We show that the resulting setup is capable of playing table tennis using an anthropomorphic robot arm.
Key Findings
1
A framework enables an anthropomorphic robot arm to learn cooperative table tennis through physical interaction with a human.
2
A mixture-of-motor-primitives approach generalizes demonstrated movements to a wider range of situations while selecting appropriate primitives.
3
Elementary table-tennis hitting movements are acquired from a human teacher via kinesthetic teach-in and encoded as dynamical-system motor primitives.
4
The resulting system demonstrates table-tennis play with a human using the learned and generalized striking movements.
5
The robot learns online during play with a human partner, progressively improving its behavior.
Research Object
a robot learning and performing cooperative table tennis with a human
Research Subject
selection, generalization, and online improvement of table-tennis hitting movements and motor primitives across playing situations
Publication Details
Publication Date
2013-01-30
Journal
Publisher
ISSN
Cited by
396
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest