Movement templates for learning of hitting and batting

  title={Movement templates for learning of hitting and batting},
  author={Jens Kober and Katharina Muelling and Oliver Kroemer and Christoph H. Lampert and Bernhard Sch{\"o}lkopf and Jan Peters},
  journal={2010 IEEE International Conference on Robotics and Automation},
Hitting and batting tasks, such as tennis forehands, ping-pong strokes, or baseball batting, depend on predictions where the ball can be intercepted and how it can properly be returned to the opponent. These predictions get more accurate over time, hence the behaviors need to be continuously modified. As a result, movement templates with a learned global shape need to be adapted during the execution so that the racket reaches a target position and velocity that will return the ball over to the… Expand
Learning table tennis with a Mixture of Motor Primitives
This work presents a new approach, called Mixture of Motor Primitives that uses a gating network to activate appropriate motor primitives and shows that the resulting setup was capable of playing rudimentary table tennis using an anthropomorphic robot arm. Expand
Learning to control planar hitting motions in a minigolf-like task
This work shows how a challenging minigolf-like task can be efficiently learned by the robot using a basic hitting motion model and a task-specific adaptation of the hitting parameters: hitting speed and hitting angle. Expand
Batting an in-flight object to the target
This paper investigates the problem of a two-degree-of-freedom robotic arm intercepting an object in free flight and redirecting it to some target with a single strike, assuming all the movements take place in one vertical plane. Expand
Adaptive learning of dynamic movement primitives through demonstration
A novel algorithm for adaptive learning of DMP that can be used to generate complex trajectories required by the robot to perform a complex task and it is shown that the proposed PLCS learns the parameters faster and has a smaller mean squared error as compared to ECS. Expand
Experiments with Motor Primitives in Table Tennis
This work shows experimentally how most elements required for table tennis can be addressed using motor primitives and presents a motor primitive formulation that can deal with hitting and striking movements. Expand
Learning to Play Minigolf: A Dynamical System-Based Approach
This work shows how the challenge of playing minigolf can be efficiently tackled by first learning a basic hitting motion model, and then learning to adapt it to different situations, and demonstrates the generalization ability of the model in various situations. Expand
Learning to Control Planar Hitting Motions of a Robotic Arm in a Mini-Golf-like Task
In this thesis we tackle the problem of goal-oriented adaptation of a robot hitting motion. We propose the parameters that must be learned in order to use and adapt a basic hitting motion to playExpand
Learning to select and generalize striking movements in robot table tennis
This paper presents a new framework that allows a robot to learn cooperative table tennis from physical interaction with a human and shows that the resulting setup is capable of playing table tennis using an anthropomorphic robot arm. Expand
Catching Objects in Flight
This work proposes a new methodology to find a feasible catching configuration in a probabilistic manner and uses the dynamical systems approach to encode motion from several demonstrations, which enables a rapid and reactive adaptation of the arm motion in the presence of sensor uncertainty. Expand
Diogo Carneiro Generalization and Anticipation Skills for Robot Ball Catching Using Supervised Learning
Learning approaches are one of the most interesting ways for endowing robots with advanced capabilities in terms of autonomy and adaptability. This dissertation addresses the problem of robot ballExpand


Timing an attacking forehand drive in table tennis.
Comparison of initial and terminal temporal accuracy of 5 male top table tennis players performing attacking forehand drives led to the conclusion that because of a higher temporal accuracy at theExpand
A learning approach to robotic table tennis
A feed-forward control scheme based on iterative learning control to accurately achieve the stroke movement of the paddle as determined by using three input-output maps implemented by means of locally weighted regression. Expand
Learning perceptual coupling for motor primitives
An augmented version of the dynamic system-based motor primitives which incorporates perceptual coupling to an external variable is proposed which can perform complex tasks such a Ball-in-a-Cup or Kendama task even with large variances in the initial conditions where a skilled human player would be challenged. Expand
Generalization of example movements with dynamic systems
  • A. Gams, A. Ude
  • Computer Science
  • 2009 9th IEEE-RAS International Conference on Humanoid Robots
  • 2009
This paper proposes an approach to learning parametrized sets of dynamic movement primitives based on a library of example movements that enables the generation of a wide range of movements that are adapted to the current configuration of the external world without requiring an expert to appropriately modify the underlying differential equations. Expand
Learning Movement Primitives
A novel reinforcement learning technique based on natural stochastic policy gradients allows a general approach of improving DMPs by trial and error learning with respect to almost arbitrary optimization criteria, and demonstrates the different ingredients of the DMP approach in various examples. Expand
Learning from demonstration: repetitive movements for autonomous service robotics
This paper presents a method for learning and generating rhythmic movement patterns based on a simple central oscillator. It can be used to generate cyclic movements for a robot system which has toExpand
Movement imitation with nonlinear dynamical systems in humanoid robots
The results demonstrate that multi-joint human movements can be encoded successfully by the CPs, that a learned movement policy can readily be reused to produce robust trajectories towards different targets, and that the parameter space which encodes a policy is suitable for measuring to which extent two trajectories are qualitatively similar. Expand
Towards Motor Skill Learning for Robotics
This paper proposes to break the generic skill learning problem into parts that the authors can understand well from a robotics point of view, and designs appropriate learning approaches for these basic components, which will serve as the ingredients of a general approach to motor skill learning. Expand
Rapid synchronization and accurate phase-locking of rhythmic motor primitives
This work demonstrates how an anthropomorphic robot can use imitation learning to acquire a complex drumming pattern and keep it synchronized with an external rhythm generator that changes its frequency over time. Expand
Policy Gradient Methods for Robotics
  • Jan Peters, S. Schaal
  • Engineering, Computer Science
  • 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2006
An overview on learning with policy gradient methods for robotics with a strong focus on recent advances in the field is given and how the most recently developed methods can significantly improve learning performance is shown. Expand