Learning to select and generalize striking movements in robot table tennis

Mülling, Katharina; Kober, Jens; Kroemer, Oliver; Peters, Jan

doi:10.1177/0278364912472380

Cited by 338 publications

(260 citation statements)

References 46 publications

Supporting

Mentioning

258

Contrasting

Unclassified

Order By: Relevance

“…The mixture of motor primitives (MoMP) [4] is a HRL algorithm that uses a very different hierarchical approach. MoMP first learns sub-policies (called motor primitives) and then learns a gating network to generate new movements by combining the sub-policies.…”

Section: B Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Layered direct policy search for learning hierarchical skills

End

Akrour

Peters

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Abstract-Solutions to real world robotic tasks often require complex behaviors in high dimensional continuous state and action spaces. Reinforcement Learning (RL) is aimed at learning such behaviors but often fails for lack of scalability. To address this issue, Hierarchical RL (HRL) algorithms leverage hierarchical policies to exploit the structure of a task. However, many HRL algorithms rely on task specific knowledge such as a set of predefined sub-policies or sub-goals. In this paper we propose a new HRL algorithm based on information theoretic principles to autonomously uncover a diverse set of sub-policies and their activation policies. Moreover, the learning process mirrors the policys structure and is thus also hierarchical, consisting of a set of independent optimization problems. The hierarchical structure of the learning process allows us to control the learning rate of the sub-policies and the gating individually and add specific information theoretic constraints to each layer to ensure the diversification of the subpolicies. We evaluate our algorithm on two high dimensional continuous tasks and experimentally demonstrate its ability to autonomously discover a rich set of sub-policies.

show abstract

Section: B Related Workmentioning

confidence: 99%

“…Many HRL methods have been proposed in order to reduce the complexity of the task [1]- [4]. The HAM framework [5] can learn complex hierarchical sub-routines.…”

Section: Introductionmentioning

confidence: 99%

Layered direct policy search for learning hierarchical skills

End

Akrour

Peters

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…They are based on learning motor primitives for acquiring new behaviors for the robots by reinforcement learning. In robotics, there are also many works studied that learn motor primitives for more complex behaviors, such as playing table tennis ( [37], [38], [39]). Some approaches that have been proposed presents systems that control the switches between the physics-based controllers to carry out locomotion ( [34] by optimizing control strategies ( [40], [41]).…”

Section: Learning-based Approachesmentioning

confidence: 99%

Skill learning based catching motion control

Cimen

Kavafoglu

et al. 2015

Computer Animation & Virtual

View full text Add to dashboard Cite

In real world, it is crucial to learn biomechanical strategies that prepare the body in kinematics and kinetics terms during the interception tasks, such as kicking, throwing and catching. Based on this, we presents a real-time physics-based approach that generate natural and physically plausible motions for a highly complex task-ball catching. We showed that ball catching behavior as many other complex tasks, can be achieved with the proper combination of rather simple motor skills, such as standing, walking, reaching. Since learned biomechanical strategies can increase the conscious in motor control, we concerned several issues that needs to be planned. Among them, we intensively focus on the concept of timing. The character learns some policies to know how and when to react by using reinforcement learning in order to use time accurately. We demonstrate the effectiveness of our method by presenting some of the catching animation results executed in different catching strategies.In each simulation, the balls were projected randomly, but within a interval of limits, in order to obtain different arrival flight time and height conditions.

show abstract

“…3. A combination of primitives allows the robot to deal with many situations where only few primitives are activated in the same context [8].…”

Section: Learning a Complex Task With Many Motor Primitivesmentioning

confidence: 99%

Towards Robot Skill Learning: From Simple Skills to Table Tennis

Peters

Kober

Mülling

et al. 2013

Advanced Information Systems Engineering

Self Cite

View full text Add to dashboard Cite

Abstract. Learning robots that can acquire new motor skills and refine existing ones have been a long-standing vision of both robotics, and machine learning. However, off-the-shelf machine learning appears not to be adequate for robot skill learning, as it neither scales to anthropomorphic robotics nor do fulfills the crucial real-time requirements. As an alternative, we propose to divide the generic skill learning problem into parts that can be well-understood from a robotics point of view. In this context, we have developed machine learning methods applicable to robot skill learning. This paper discusses recent progress ranging from simple skill learning problems to a game of robot table tennis.

show abstract

Learning to select and generalize striking movements in robot table tennis

Cited by 338 publications

References 46 publications

Layered direct policy search for learning hierarchical skills

Layered direct policy search for learning hierarchical skills

Skill learning based catching motion control

Towards Robot Skill Learning: From Simple Skills to Table Tennis

Contact Info

Product

Resources

About