Movement templates for learning of hitting and batting
The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
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 other side of the net or court. It requires altering learned movements to hit a varying target with the necessary velocity at a specific instant in time. Such a task cannot be incorporated straightforwardly in most movement representations suitable for learning. For example, the standard formulation of the dynamical system based motor primitives (introduced by Ijspeert et al. [1]) does not satisfy this property despite their flexibility which has allowed learning tasks ranging from locomotion to kendama. In order to fulfill this requirement, we reformulate the Ijspeert framework to incorporate the possibility of specifying a desired hitting point and a desired hitting velocity while maintaining all advantages of the original formulation. We show that the proposed movement template formulation works well in two scenarios, i.e., for hitting a ball on a string with a table tennis racket at a specified velocity and for returning balls launched by a ball gun successfully over the net using forehand movements. All experiments were carried out on a Barrett WAM using a four camera vision system.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
A New Approach to Linear Filtering and Prediction Problems
Kalman, R. E. (1960) · Journal of Basic Engineering · doi:10.1115/1.3662552 · Cited by 31,751
Movement imitation with nonlinear dynamical systems in humanoid robots
Ijspeert, A. J., Nakanishi, J., & Schaal, S. (2003) · Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292) · doi:10.1109/robot.2002.1014739 · Cited by 840 · cited 6×
“While the original formulation in [1], [2] for discrete dynamical systems motor primitives used a second-order system to represent the phase z of the movement, this formulation has proven to be unnecessarily complicated in practice.”
BackgroundMethodInfluentialMotor Learning and Performance
Schmidt, R. A., & Wrisberg, C. A. (1991) · Cited by 664
Timing an attacking forehand drive in table tennis.
Bootsma, R. J., & Van Wieringen, P. C. (1990) · Journal of Experimental Psychology: Human Perception and Performance · doi:10.1037//0096-1523.16.1.21 · Cited by 546
Policy Gradient Methods for Robotics
Peters, J., & Schaal, S. (2006) · 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2006.282564 · Cited by 498 · cited 2×
“Although some of the presented examples, e.g., the tennis swing [1] or the T-ball batting [8], are striking movements, these standard motor primitives cannot properly encode a hitting movement.”
BackgroundSelf-citationLearning from demonstration and adaptation of biped locomotion
Nakanishi, J., Morimoto, J., Endo, G., Cheng, G., Schaal, S., & Kawato, M. (2004) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2004.03.003 · Cited by 399 · cited 1×
“Resulting successes have shown that it is possible to rapidly learn motor primitives for complex behaviors such as tennis swings [1] with only a final target, constrained reaching [4], drumming [5], biped locomotion [2], [6] and even in tasks with potential industrial application [7].”
BackgroundSchaal, S., Peters, J., Nakanishi, J., & Ijspeert, A. (2005) · Springer Tracts in Advanced Robotics · doi:10.1007/11008941_60 · Cited by 343
Self-citationDynamics systems vs. optimal control — a unifying view
Schaal, S., Mohajerian, P., & Ijspeert, A. (2007) · Progress in Brain Research · doi:10.1016/s0079-6123(06)65027-9 · Cited by 260 · cited 7×
“Since then, it has been simplified and in [3] it was shown that a single first order system suffices ˙ z = − τα z z. (1) This canonical system has the time constant τ = 1 /T where T is the duration of the motor primitive, a parameter α z which is chosen such that z ≈ 0 at T to ensure that the influence…”
BackgroundMethodInfluentialMovement reproduction and obstacle avoidance with dynamic movement primitives and potential fields
Park, D.-H., Hoffmann, H., Pastor, P., & Schaal, S. (2008) · Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots · doi:10.1109/ichr.2008.4755937 · Cited by 254 · cited 1×
“The transformation function f ( z ) alters the output of the first system, in Eq.”
BackgroundA Robot Ping-Pong Player: Experiments in Real-Time Intelligent Control
Anderson, R. L. (1988) · Medical Entomology and Zoology · Cited by 162
Research works printed but not linked: 3
- ramanantsoa, 1994, Towards a stroke construction model, Int J Table Tennis Sci, 2, 97
- tyldesley, 1975, Operational timing, Journal of Human Movement Studies, 1, 172
- schaal, 2003, Learning Motor Primitives, Proceedings of the International Symposium on Robotics Research
Cited by
End-to-End Training of Deep Visuomotor Policies
Levine, S., Finn, C., Darrell, T. J., & Abbeel, P. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.00702 · Cited by 1,344
“Several recent papers provide surveys of policy search in robotics [3, 14].”
BackgroundImitation Learning: A Survey of Learning Methods
Hussein, A., Gaber, M. M., Elyan, E., & Jayne, C. (2018) · ACM Computing Surveys · doi:10.1145/3054912 · Cited by 1,060
“This led to a series of work that utilizes the dynamic system in Ijspeert et al. [2002b] to learn from demonstrations and subsequently use reinforcement learning for self-improvement [Kober and Peters 2010, 2014; Buchli et al. 2011; Pastor et al. 2011].”
MethodA Survey on Policy Search for Robotics
Deisenroth, M. P. (2011) · Foundations and Trends in Robotics · doi:10.1561/2300000021 · Cited by 798
“In contrast to exploration in action space, exploration in parameter space is able to use more structured noise and can adapt the variance of the exploration noise in dependence of the state features φt(x).”
Background(2013) · Lincoln Repository (University of Lincoln) · Cited by 503
Self-citationLearning to select and generalize striking movements in robot table tennis
Mülling, K., Kober, J., Kroemer, O., & Peters, J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364912472380 · Cited by 396
“Modified hitting primitives The formulation of Kober et al. (2010) with a linear velocity allows us to directly incorporate the desired velocity such that the desired final velocity can be adapted (in addition to the desired initial and final position in Ijspeert’s formulation).”
BackgroundMethodInfluentialSelf-citationDynamic movement primitives in robotics: A tutorial survey
Saveriano, M., Abu-Dakka, F. J., Kramberger, A., & Peternel, L. (2023) · The International Journal of Robotics Research · doi:10.1177/02783649231201196 · Cited by 267
“To this end, Kober et al. (2010b) extend the classical DMP formulation in Section 2.1.1 to let the DMP to track a target moving at a given velocity.”
BackgroundMethodInfluentialMohammad Khansari-Zadeh, S., & Billard, A. (2014) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.03.001 · Cited by 225
“During the last decade, DS has been used to model discrete motions [6, 7, 29, 30], rhythmic motions [ 31, 32], hitting motions [33, 34, 7], obstacle avoidance [ 35, 36, 37], etc.”
BackgroundMethodKim, S., Shukla, A., & Billard, A. (2014) · IEEE Transactions on Robotics · doi:10.1109/tro.2014.2316022 · Cited by 220
“A body of work has been devoted to the autonomous control of fast movements such as catching [13], [18], [25], [28], [30]–[32], [44], hitting flying objects [24], [37], and juggling [6], [33], [35].”
BackgroundUsing probabilistic movement primitives in robotics
Paraschos, A., Daniel, C., Peters, J., & Neumann, G. (2018) · Autonomous Robots · doi:10.1007/s10514-017-9648-7 · Cited by 205
“MP frameworks can be trained from demonstrations using simple learning methods, e.g. linear regression, and have been successfully used in fairly complex scenarios, including “Ball-in-the-Cup” Kober et al. (2010), Ball-Throwing (Ude et al. 2010; da Silva et al. 2012), Pancake-Flipping (Kormushev et al. 2010), Tetherba…”
BackgroundMethodInfluentialSelf-citationHierarchical Relative Entropy Policy Search
Daniel, C., Neumann, G. M., Kroemer, O., & Peters, J. (2014) · Lincoln Repository (University of Lincoln) · Cited by 166
Self-citationCurrent Researches and Future Development Trend of Intelligent Robot: A Review
Wang, T., Tao, Y., & Liu, H. (2018) · Machine Intelligence Research · doi:10.1007/s11633-018-1115-1 · Cited by 170
“In some studies[122, 123], motion primitive constructs a compact expression of the robot′s control laws, which is used to take actions like colliding, knocking and seizing.”
BackgroundReinforcement learning to adjust parametrized motor primitives to new situations
Kober, J., Wilhelm, A., Oztop, E., & Peters, J. (2012) · Autonomous Robots · doi:10.1007/s10514-012-9290-3 · Cited by 163
Self-citationKulvičius, T., Ning, K., Tamošiūnaitė, M., & Wörgötter, F. (2011) · IEEE Transactions on Robotics · doi:10.1109/tro.2011.2163863 · Cited by 162
“Note that many too wide kernels might lead to worse accuracy in the position profile because of large overlap of kernels at the joining point [see case n = 30, σ = 0.03 in panel (d)].”
BackgroundInfluentialEmbodied large language models enable robots to complete complex tasks in unpredictable environments
Mon-Williams, R., Li, G., Long, R., Du, W., & Lucas, C. G. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01005-x · Cited by 132
“Nevertheless, the existence of ‘intelligence’ and feedback from force and vision within the ELLMER framework means that systems will be better equipped to detect inaccuracies and wear-and-tear and thus act to ensure these issues do not go undetected and cause unwanted consequences ‘in the wild’.”
Learning motor skills: from algorithms to robot experiments
Kober, J. (2014) · it - Information Technology · doi:10.1515/itit-2014-1039 · Cited by 157
Self-citationLearning table tennis with a Mixture of Motor Primitives
Muelling, K., Kober, J., & Peters, J. (2010) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/ichr.2010.5686298 · Cited by 132
“978-1-4244-8689-2/10/$26.00 ©2010 IEEE 411”
MethodInfluentialSelf-citationLearning to Play Table Tennis From Scratch Using Muscular Robots
Büchler, D., Guist, S., Calandra, R., Berenz, V., Schölkopf, B., & Peters, J. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3176207 · Cited by 107
“These works use techniques, such as imitation learning [3], choosing or optimizing from safe demonstrations [4]–[6], minimizing acceleration for optimized trajectories [7], distributing torques over all degrees of freedom (DoFs) [8] as well as cautious learning control approaches [9].”
Self-citationData-Efficient Generalization of Robot Skills with Contextual Policy Search
Kupcsik, A., Deisenroth, M., Peters, J., & Neumann, G. (2013) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v27i1.8546 · Cited by 92
“The results show that CrKR could not compete with model-free REPS.”
MethodInfluentialSelf-citationHierarchical reinforcement learning with movement primitives
Stulp, F., & Schaal, S. (2011) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2011.6100841 · Cited by 84
“In [10], [7], the (moving) goal of the movement is determined such that a pre-specified velocity vector is achieved when coming into contact with a table tennis ball.”
BackgroundLearning task-parameterized dynamic movement primitives using mixture of GMMs
Pervez, A., & Lee, D. (2017) · Intelligent Service Robotics · doi:10.1007/s11370-017-0235-8 · Cited by 82
“When generalizing for novel goal positions, the DMPs can produce high accelerations at the beginning of the movement [15].”
BackgroundModel-based contextual policy search for data-efficient generalization of robot skills
Kupcsik, A., Deisenroth, M. P., Peters, J., Loh, A. P., Vadakkepat, P., & Neumann, G. M. (2014) · Artificial Intelligence · doi:10.1016/j.artint.2014.11.005 · Cited by 101
“Additionally, we can also adapt the final desired velocity ġ of the movement with the extension given in [19].”
MethodSelf-citationModel-Free Preference-Based Reinforcement Learning
Wirth, C., Fürnkranz, J., & Neumann, G. M. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10269 · Cited by 70
“In order to keep the computation tractable, we adapt the weighted formulation of a GP given in Kober et al. (2010) to the sparse Gaussian process case given in Snelson and Ghahramani (2006).”
MethodMerging Position and orientation Motion Primitives
Saveriano, M., Franzel, F., & Lee, D. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793786 · Cited by 66
“The approach in [29] has been proposed to learn hitting motions in table tennis, but it can be used to merge motion primitives.”
BackgroundMethodInfluentialColome, A., & Torras, C. (2018) · IEEE Transactions on Robotics · doi:10.1109/tro.2018.2808924 · Cited by 60
Learning Stylistic Dynamic Movement Primitives from multiple demonstrations
Matsubara, T., Hyon, S.-H., & Morimoto, J. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5651049 · Cited by 57
“Recent progresses in each task can be founded for table tennis in [18], [19], [20].”
BackgroundEstimating the non-linear dynamics of free-flying objects
Kim, S., & Billard, A. (2012) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2012.05.022 · Cited by 55
Controlling the Solo12 quadruped robot with deep reinforcement learning
Aractingi, M., Léziart, P., Flayols, T., Pérez, J., Silander, T., & Souères, P. (2023) · Scientific Reports · doi:10.1038/s41598-023-38259-7 · Cited by 76
Survey of robotic arm and parameters
Patidar, V., & Tiwari, R. (2016) · International Conference on Computer Communication and Informatics (ICCCI) · doi:10.1109/iccci.2016.7479938 · Cited by 58
Demonstration based trajectory optimization for generalizable robot motions
Koert, D., Maeda, G. J., Lioutikov, R., Neumann, G. M., & Peters, J. (2016) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2016.7803324 · Cited by 56
“To obtain generalizable robot motions from human demonstrations a number of frameworks employ the concept of movement primitives [20], [21], [22].”
MethodSelf-citationLearning to sequence movement primitives from demonstrations
Manschitz, S., Kober, J., Gienger, M., & Peters, J. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6943187 · Cited by 63
“…by investigating two different kinds of sequence graphs: The local graph presumes the ordering to be arbitrary and is not considering it in the representation, while the global graph is trying to construct a more detailed description of the skill based on the ordering of the primitives.”
BackgroundSelf-citationComplicated robot activity recognition by quality-aware deep reinforcement learning
Li, X., Zhong, J., & Kamruzzaman, M. M. (2020) · Future Generation Computer Systems · doi:10.1016/j.future.2020.11.017 · Cited by 59
Ping-pong robotics with high-speed vision system
Li, H., Wu, H., Lou, L., Kühnlenz, K., & Ravn, O. (2012) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2012.6485142 · Cited by 40
“Robotic table tennis also servers as an ideal platform for different research directions, such as motion learning[1][2], strategy design for juggling[3] and wall bouncing[4] and so on.”
BackgroundLearning motion dynamics to catch a moving object
Kim, S., Gribovskaya, E., & Billard, A. (2010) · 2010 10th IEEE-RAS International Conference on Humanoid Robots · doi:10.1109/ichr.2010.5686332 · Cited by 39
“Recent work extended the original DMP formulation to allow a non-zero velocity at the target and was successfully used for hitting a moving target [9].”
BackgroundLearning quadrotor maneuvers from optimal control and generalizing in real-time
Tomić, T., Maier, M., & Haddadin, S. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907087 · Cited by 38
“DMPs are applied to a variety of robotics problems [21], [22], [23], since they can produce both discrete or rythmic movements that can quickly be adapted to changes in a dynamic environment [24].”
BackgroundLearning sequential motor tasks
Daniel, C., Neumann, G. M., Kroemer, O., & Peters, J. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630937 · Cited by 37
“For the exact description of the DMP framework we refer to [17].”
Self-citationBatting an in-flight object to the target
Jia, Y.-B., Gardner, M., & Mu, X. (2019) · The International Journal of Robotics Research · doi:10.1177/0278364918817116 · Cited by 43
“Kober et al. (2010) developed a system which, based on the motor primitives (Ijspeert et al., 2002), could control a paddle to reach to hit (but not to return) a served ping pong ball after learning from human demonstrations.”
BackgroundLearning concurrent motor skills in versatile solution spaces
Daniel, C., Neumann, G., & Peters, J. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6386047 · Cited by 36
“To describe the motion of the robot arm, we use a recent adaption of dynamic motor primitives (DMPs) to hitting movements as presented in [23].”
MethodSelf-citationLearning Manipulation by Sequencing Motor Primitives with a Two-Armed Robot
Lioutikov, R., Kroemer, O., Maeda, G. J., & Peters, J. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-08338-4_115 · Cited by 34
“Although the original in [6] did not aim at sequencing of primitives, it could be adopted as an extension of this paper to address transitions with non-zero velocity.”
BackgroundMethodSelf-citationLearning Parametric Dynamic Movement Primitives from Multiple Demonstrations
Matsubara, T., Hyon, S.-H., & Morimoto, J. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-17537-4_43 · Cited by 34
Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State RegularizationPreprint
Lee, Y., Lim, J. J., Anandkumar, A., & Zhu, Y. (2021) · CaltechAUTHORS (California Institute of Technology) · doi:10.48550/arxiv.2111.07999 · Cited by 56
A novel DMP formulation for global and frame independent spatial scaling in the task space
Koutras, L., & Doulgeri, Z. (2020) · IEEE RO-MAN · doi:10.1109/ro-man47096.2020.9223500 · Cited by 31
Zhao, Y., Xiong, R., & Zhang, Y. (2017) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-017-0515-8 · Cited by 29
“All of those research papers cover the fields of motion model [7, 11, 19, 36, 38, 40], rebound model [4, 27, 39], real-time sensing and measurement [6, 16, 30, 37], motion planning and control [17, 29], and manipulation or action learning [12, 13, 15, 21, 24].”
BackgroundLearning to Play Minigolf: A Dynamical System-Based Approach
Khansari-Zadeh, S. M., Kronander, K., & Billard, A. (2012) · Advanced Robotics · doi:10.1080/01691864.2012.728692 · Cited by 28
“In [17], a modification to the original formulation of DMP is proposed to generate striking motions in table-tennis.”
MethodLearning optimal striking points for a ping-pong playing robot
Huang, Y., Schölkopf, B., & Peters, J. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354030 · Cited by 28
“As an approach to generalizing of plans from demonstrations, the dynamic motor primitive (DMP) [23], [24] trained by kinesthetic teach-in generates the joint movement trajectory [13].”
MethodSelf-citationDynamic Trajectory Generation and a Robust Controller to Intercept a Moving Ball in a Game Setting
Prakash, R., Behera, L., Mohan, S., & Jagannathan, S. (2019) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2019.2913129 · Cited by 27
“[19] also added the term ( 1 − x ) to prevent large jumps in acceleration at the beginning of the movement.”
BackgroundMethodInfluentialKhansari, M., Kronander, K., & Billard, A. (2014) · Robotics: Science and Systems · doi:10.15607/rss.2014.x.022 · Cited by 26
Dynamically Consistent Online Adaptation of Fast Motions for Robotic Manipulators
Pekarovskiy, A., Nierhoff, T., Hirche, S., & BUSS, M. J. (2017) · IEEE Transactions on Robotics · doi:10.1109/tro.2017.2765666 · Cited by 29
Optimizing the Execution of Dynamic Robot Movements With Learning Control
Koç, O., Maeda, G. J., & Peters, J. (2019) · IEEE Transactions on Robotics · doi:10.1109/tro.2019.2906558 · Cited by 25
“Striking movement primitives suited to table tennis have been proposed in [1] and [33] as an extension of discrete dynamic movement primitives (DMP).”
BackgroundSelf-citationLearning nonlinear dynamical system for movement primitives
Yin, X., & Chen, Q. (2014) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2014.6974516 · Cited by 24
“The transformation system have to be modified to handle time problem [15], [16]. where t m is position of the moving target, t 0 m is the initial position of the moving target which can be calculate by t 0 m = t − τ ˙ t , t and ˙ t are the final position and velocity of the target, a = t − x 01 is…”
BackgroundSharma, R. S., Shukla, S., Karki, H., Shukla, A., Behera, L., & Venkatesh, K. S. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793911 · Cited by 24
“[9] for safe accelerations, with online changing path specifications.”
BackgroundDynamic Movement Primitives for moving goals with temporal scaling adaptation
Koutras, L., & Doulgeri, Z. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196765 · Cited by 24
“In [17] a DMP formulation has been proposed in the context of hitting a moving ball with a specified velocity.”
MethodLearning to control planar hitting motions in a minigolf-like task
Kronander, K., Khansari-Zadeh, M. S. M., & Billard, A. (2011) · 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2011.6094402 · Cited by 23
“These methods have been successfully developed to learn motion primitives such as discrete (point-to-point) motions [7], rhythmic motions [6], hitting motions [2], [8], etc.”
MethodTowards Learning of Generic Skills for Robotic Manipulation
Metzen, J. H., Fabisch, A., Senger, L., Fernández, J. D. G., & Kirchner, E. A. (2013) · Künstliche Intell. · doi:10.1007/s13218-013-0280-1 · Cited by 23
“The most popular class of policy representations that have been used to learn movement primitives for robotic manipulation are Dynamical systems Movement Primitives (DMPs) [10,13,16,17].”
BackgroundZhou, P., Zhao, X., Tao, B., & Ding, H. (2022) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2022.3196036 · Cited by 23
“The target position g is a fixed value, which is different from the reference [23].”
BackgroundMethodA novel framework for generalizing dynamic movement primitives under kinematic constraints
Sidiropoulos, A., Papageorgiou, D., & Doulgeri, Z. (2022) · Autonomous Robots · doi:10.1007/s10514-022-10067-4 · Cited by 22
“We also compare our method against the original DMP, the modified DMP proposed in Koutras and Doulgeri (2020) aimed at mitigating the effects of over-scaling by applying a rotation (referred hereafter as DMP-rot) and the approach proposed in Cardoso et al.”
MethodA probabilistic approach to robot trajectory generation
Paraschos, A., Neumann, G. M., & Peters, J. (2013) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2013.7030017 · Cited by 25
“Typically, the generalization to new final positions or velocities is based on heuristics and cannot be directly obtained by imitation learning.”
BackgroundSelf-citationLearning modular policies for robotics
Neumann, G. M., Daniel, C., Paraschos, A., Kupcsik, A., & Peters, J. (2014) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2014.00062 · Cited by 29
“Kober et al. (2010b) us a Gaussian Process (GP) for generalization.”
BackgroundMethodInfluentialSelf-citationHigh Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards
Ploeger, K., Lutter, M., & Peters, J. (2020) · Technischen Universität Darmstadt · doi:10.26083/tuprints-00020583 · Cited by 31
Self-citationWang, Y., Xiong, R., Shen, L., Sun, K., Zhang, J., & Qi, L. (2014) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2014.6917456 · Cited by 20
“In [3], a movement template formulation was proposed incorporating the possibility of specifying a desired hitting point and a desired hitting velocity, which was then”
Towards table tennis with a quadrotor autonomous learning robot and onboard vision
Silva, R., Melo, F. S., & Veloso, M. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353441 · Cited by 20
“4We refer to [18] for additional discussion on these constants.”
BackgroundHuang, Y., & Sun, Y. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206626 · Cited by 30
“DMP is a stable non-linear dynamical system, and is capable of modeling discrete movement such as swinging a tennis racket [6], playing table tennis [7] as well as rhythmic movement such as drumming [8] and walking [9].”
BackgroundJin, J., Petrich, L., Dehghan, M., Zhang, Z., & Jägersand, M. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793649 · Cited by 21
“rogramming. In conclusion, our method can be treated as low level learning, which is about learning skills based on geometric constraints, force control and system dynamics(e.g. strike motion learning[35]). Together they form the two-levels of task specification learning. Limitations and future directions: The major li…”
MethodEXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action ModelsPreprint
Dong, P., Hung, K.-H., Gao, T., Sadigh, D., & Finn, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.25477 · Cited by 22
“Reinforcement learning has a long history of real-world deployment in robotics [14, 15, 16, 17, 18, 19, 20, 21].”
Colomé, A., & Torras, C. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942742 · Cited by 23
“Both strategies result in less Gaussian computations and better performance on learning algorithms.”
BackgroundA Survey of Behavior Learning Applications in Robotics -- State of the Art and PerspectivesPreprint
Fabisch, A., Petzoldt, C., Otto, M., & Kirchner, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01868 · Cited by 22
“…et al. 2011), baseball (Peters et al. 2005; Peters and Schaal 2008), badminton (Liu et al. 2013), tennis (Ijspeert et al. 2002), table tennis (Kober et al. 2010; Mülling et al. 2011; Kober et al. 2012; Mülling et al. 2013), tetherball (Daniel et al. 2012; Parisi et al. 2015), darts (Kober…”
BackgroundKick Motions for the NAO Robot Using Dynamic Movement Primitives
Böckmann, A., & Laue, T. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68792-6_3 · Cited by 17
“at the nal velocity is always zero making it unsuitable for kick motions because kick motions need to reach the target with a specic velocity. Solutions to this problem were proposed by Kober et al. [6] and Mulling et al. [9]. They replaced the goal gin eq. 7 with the position, velocity and acceleration of a moving ta…”
BackgroundLearning throwing and catching skills
Kober, J., Muelling, K., & Peters, J. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386267 · Cited by 21
“In [7], we have introduced a modification of the DMPs that allows to generalize them to arbitrary velocities and positions at the end of the movement.”
MethodSelf-citationLearning to Serve: An Experimental Study for a New Learning From Demonstrations Framework
Koc, O., & Peters, J. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2896466 · Cited by 15
“The suggestion proposed in [21] to modify the accelerations with the phase can reduce the initial accelerations, but then we have found that the convergence to the goal positions can suffer drastically.”
BackgroundSelf-citationModel based path planning using Q-Learning
Sharma, A., Gupta, K., Kumar, A., Sharma, A., & Kumar, R. (2017) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit.2017.7915468 · Cited by 14
Trajectory Generation With Spatio-Temporal Templates Learned From Demonstrations
Yin, X., & Chen, Q. (2016) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2016.2613843 · Cited by 14
“In [9] and [10], an additional moving target function is introduced in the original model for this circumstance.”
BackgroundMethodInfluentialAdaptive learning of dynamic movement primitives through demonstration
Samant, R. N., Behera, L., & Pandey, G. S. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727316 · Cited by 14
“[5], [6] using locally weighted regression (LWR) technique to learn the kernel parameters.”
MethodA Novel Trajectory Generation Method for Robot Control
Ning, K., Kulvičius, T., Tamošiūnaitė, M., & Wörgötter, F. (2012) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-012-9683-8 · Cited by 15
“For example, limited by its formulation and structure, the original DMP can not be used to directly incorporate a target velocity or a via-point (but see [21]).”
BackgroundAdaptive Grasping of Moving Objects through Tactile Sensing
Lynch, P., Cullinan, M. F., & McGinn, C. (2021) · Sensors · doi:10.3390/s21248339 · Cited by 15
“Examples include grasping [24], catching [2,6,25,26], batting [27,28], juggling [29] and picking up objects on a conveyor belt [30].”
BackgroundGenerating a Style-Adaptive Trajectory from Multiple Demonstrations
Zhao, Y., Xiong, R., Li, F., & Dai, X. (2014) · International Journal of Advanced Robotic Systems · doi:10.5772/58723 · Cited by 12
“The effectiveness of this method has been validated through various applications, such as walking [13], flight control [14] and hitting and batting [15].”
BackgroundMethodYu, M., Luo, J., Wang, M., Li, J., Liu, C., & Sun, J. (2022) · Acta Astronautica · doi:10.1016/j.actaastro.2022.11.043 · Cited by 11
Batting Performance Analisys of West Java Athletes
Gumilar, A., Negara, J. D. K., Ma’mun, A., Nuryadi, N., Hambali, B., Mudjihartono, M., & Mulyana, D. (2021) · JURNAL PENDIDIKAN JASMANI DAN OLAHRAGA · doi:10.17509/jpjo.v6i2.37215 · Cited by 11
Online deformation of optimal trajectories for constrained nonprehensile manipulation
Pekarovskiy, A., Nierhoff, T., Schenek, J., Nakamura, Y., Hirche, S., & BUSS, M. J. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139531 · Cited by 10
“An extension overcoming the prior problem of accounting only for rest-to-rest motions is presented in [12].”
BackgroundLearning Relevant Features for Manipulation Skills using Meta-Level PriorsPreprint
Kroemer, O., & Sukhatme, G. S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.04439 · Cited by 11
“Example skills include playing ball games [21, 8, 40, 27], opening doors [19, 22], scrubbing surfaces [33, 6], and manipulating objects [38, 32, 4].”
BackgroundFactored Contextual Policy Search with Bayesian optimization
Pinsler, R., Karkus, P., Kupcsik, A., Hsu, D., & Lee, W. S. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793808 · Cited by 11
“For the Gym tasks, we employ an extension [24] of the DMP framework [12] to efficiently generate goal-directed trajectories.”
MethodA novel approach to dynamic movement imitation based on quadratic programming
Cardoso, C., Jamone, L., & Bernardino, A. J. M. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139285 · Cited by 10
“This latter formulation in particular has proven to be a very effective tool for imitation learning, and has been therefore widely used in robotics and inspired many extensions to add velocity goals [15], [16] and allow uncertainty and way-points in the execution [17].”
MethodDesign and implementation of a ball-batting robot with optimal batting decision making ability
Hsiao, T., Yang, C.-M., Lee, I.-H., & Hsiao, C.-C. (2014) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2014.6899452 · Cited by 9
“The frame rates of the vision systems varied from 60 to 1000 frame-per-second (fps) [2-9].”
BackgroundMethodAI Meets Physical World -- Exploring Robot CookingPreprint
Sun, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.07974 · Cited by 9
“DMP is a stable non-linear dynamical system, and is capable of modeling discrete movement such as swinging a tennis racket [10], playing table tennis [11] as well as rhythmic movement such as drumming [22] and walking [17].”
BackgroundAccurate position and velocity control for trajectories based on dynamic movement primitives
Ning, K., Kulvičius, T., Tamošiūnaitė, M., & Wörgötter, F. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979668 · Cited by 8
“Kober et al [15] made a modification of the original DMP formulation in order to implement striking (e.”
MethodInfluentialRobot Anticipation Learning System for Ball Catching
Carneiro, D., da Silva, F. M. T. P., & Georgieva, P. (2021) · Robotics · doi:10.3390/robotics10040113 · Cited by 7
Interaction learning control with movement primitives for lower limb exoskeleton
Wang, J., Wu, D., Gao, Y., & Dong, W. (2022) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2022.1086578 · Cited by 7
“To this effect, a novel ProMPs is proposed by Paraschos et al. (2013, 2018), which incorporates a variety of advantages from other well-known previous MP representations (d’Avella and Bizzi, 2005; Schaal et al., 2005; Kober et al., 2010).”
BackgroundModified dynamic movement primitives for joining movement sequences
Kulvičius, T., Ning, K., Tamošiūnaitė, M., & Wörgötter, F. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979716 · Cited by 12
Kroemer, O., & Sukhatme, G. S. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989546 · Cited by 7
“, playing ball games [3], [4], [5], [6], scrubbing surfaces [7], [8], opening doors [9], [10], and manipulating objects [11], [12], [13].”
BackgroundPose estimation based on PnP algorithm for the racket of table tennis robot
Wang, Q., & Shi, L. (2013) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2013.6561387 · Cited by 7
Generation of movements with boundary conditions based on optimal control theory
Herzog, S., Wörgötter, F., & Kulvičius, T. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.04.006 · Cited by 7
“For comparison with DMPs we used a version of DMPs for generation of hitting and batting movements [5] since it allows generalization to both position and velocity boundary conditions.”
MethodVisual Geometric Skill Inference by Watching Human Demonstration
Jin, J., Petrich, L., Zhang, Z., Dehghan, M., & Jägersand, M. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196570 · Cited by 7
“Symbolic task plans can be represented as a tree [5] or graph structure [6, 7] based on the assumption that a task can be decomposed into low-level conditioned elementary skills [8], such as, grasping, striking [9], alignment [10], and peg-in-hole [11].”
BackgroundComputationally efficient Gaussian Process changepoint detection and regression
Grande, R. C. (2014) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 12
Real-Time Trajectory Generation via Dynamic Movement Primitives for Autonomous Racing
Weaver, C., Capobianco, R., Wurman, P. R., Stone, P., & Tomizuka, M. (2024) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc60939.2024.10644244 · Cited by 6
“This is because, at the end of a DMP’s duration, the goal-driven system has driven the trajectory close to the DMP’s target state, which serves as the joining point to the next DMP [12].”
BackgroundMethodInfluentialLearning point-to-point movements on an elastic limb using dynamic movement primitives
Basa, D., & Schneider, A. (2015) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.12.011 · Cited by 6
Autonomous reinforcement learning with hierarchical REPS
Daniel, C., Neumann, G. M., & Peters, J. (2013) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2013.6706759 · Cited by 7
“To describe the motion of the robot arm, we use a recent adaption of dynamic motor primitives (DMPs) to hitting movements as presented in [23].”
MethodSelf-citationPhase portraits as movement primitives for fast humanoid robot control
Maeda, G. J., Koç, O., & Morimoto, J. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.04.007 · Cited by 6
Real-time temporal adaptation of dynamic movement primitives for moving targets
Anand, A. S., Østvik, A., Grøtli, E. I., Vagia, M., & Gravdahl, J. T. (2021) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar53236.2021.9659384 · Cited by 10
“Other approaches involve reaching a moving object by predicting the target trajectory in advance, as presented in [18], [19], based on a dynamic model of the moving target.”
Target-Referred DMPs for Learning Bimanual Tasks from Shared-Autonomy Telemanipulation
Amadio, F., Laghi, M., Raiano, L., Rollo, F., Zunino, A., Raiola, G., & Ajoudani, A. (2022) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids53995.2022.10000233 · Cited by 6
“com a diverse set of tasks, from assembly [3] to table tennis [4].”
BackgroundMovement primitives with multiple phase parameters
Ewerton, M., Maeda, G. J., Neumann, G. M., Kisner, V., Kollegger, G., Wiemeyer, J., & Peters, J. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487134 · Cited by 7
“[6] have designed an alternative DMP formulation to achieve arbitrary velocities at the end of the 2016 IEEE International Conference on Robotics and Automation (ICRA) Stockholm, Sweden, May 16-21, 2016”
MethodSelf-citationDynamic Nonprehensile Manipulation of a Moving Object Using a Batting Primitive
Joe, H.-M., Lee, J., & Oh, J.-H. (2021) · Applied Sciences · doi:10.3390/app11093920 · Cited by 5
“[19] proposed a method to generate the trajectory of the robot arm through learning.”
MethodLearning Robotic Contact Juggling
Tanaka, K., Hamaya, M., Joshi, D. O., von Drigalski, F., Yonetani, R., Matsubara, T., & Ijiri, Y. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636790 · Cited by 5
“Many researchers have sought to realize various robotic juggling, such as devil sticking [1], toss juggling [2], [3], paddle juggling [4], and diabolo [5], [6].”
Background
Metadata
- Authors
- Kober, J., Mülling, K., Krömer, O., Lampert, C. H., Schölkopf, B., & Peters, J.
- Affiliations
- Max Planck Institute for Biological Cybernetics (DE)
- Venue
- 2010 IEEE International Conference on Robotics and Automation
- Publisher
- IEEE
- Published
- 2010-05
- Pages
- 853-858
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W1982803779
- Cited by
- 152
- References
- 21
- Citations by year
- 2026: 2 · 2025: 4 · 2024: 2 · 2023: 6 · 2022: 8 · 2021: 11 · 2020: 9 · 2019: 13 · 2018: 9 · 2017: 12 · 2016: 9 · 2015: 13 · 2014: 17 · 2013: 14 · 2012: 8
- FWCI
- 21.97
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- TUbilio (Technical University of Darmstadt) (submittedVersion)
- Max Planck Institute for Plasma Physics (submittedVersion)
- MPG.PuRe (Max Planck Society) (submittedVersion)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Motor Control and Adaptation
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Keywords
- motor learning, dynamical systems, motor primitives, visual servoing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.