Motion generation for robots in highly dynamic environments is challenging due to the need for high efficiency and error tolerance. Robots must generate motion efficiently within milliseconds to react to environmental changes swiftly. Furthermore, the limitations of perceptual systems in detecting fast-moving objects necessitate robust motion generation that can tolerate perceptual errors. This paper presents a motion generation framework that ensures both high efficiency and error tolerance for the dynamic task of robotic table tennis. To achieve high efficiency, this study introduces a novel analytical solution to the ball flight equation using Chebyshev approximation, offering a time complexity of O (1). For robotic motion generation, this study proposes a dimension-reduced task planner and employs piecewise cubic polynomial and Variable-Sigmoid-Based motion templates for individual joint motions, with coefficients determined analytically and rapidly. To enhance perceptual error tolerance, this study develops a policy optimizer based on a striking-at-the-center principle. The proposed task planner accelerates paddle motion determination by an average of 9.27 times. The proposed ball motion prediction method enhances the efficiency of determining the ball-paddle collision point by up to a factor of two. Additionally, the proposed framework improves the success rate of planning and striking by 16.0% and 18.3%, respectively, compared to methods that do not account for error tolerance. It also reduces the landing position error in the x and y directions by 32.5% and 35.6%, while improving the accuracy of passing-net height by 24.0%.
AbeyruwanSWGraesserLD’AmbrosioDB, et al. (2023) i-sim2real: reinforcement learning of robotic policies in tight human-robot interaction loops. In: Conference on Robot Learning. PMLR, pp. 212–224.
BüchlerDGuistSCalandraR, et al. (2022) Learning to play table tennis from scratch using muscular robots. IEEE Transactions on Robotics38(6): 3850–3860.
4.
CaronSKheddarATempierO (2019) Stair climbing stabilization of the hrp-4 humanoid robot using whole-body admittance control. In: 2019 International Conference on Robotics and Automation (ICRA). IEEE, pp. 277–283.
5.
ChenXTianYHuangQ, et al. (2010) Dynamic model based ball trajectory prediction for a robot ping-pong player. In: 2010 IEEE International Conference on Robotics and Biomimetics. IEEE, pp. 603–608.
6.
ChenTRongXLiY (2021) Optimized method for planning and controlling the somersault motion of quadruped robot. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE. pp. 7658–7664.
7.
CreveauxTBastienJVillarsC, et al. (2012) Model of joint displacement using sigmoid function. Experimental approach for planar pointing task and squat jump. arXiv preprint arXiv:1207.2627.
8.
CursiFKalanderMWuS, et al. (2024) Safe table tennis swing stroke with low-cost hardware. In: 2024 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 18279–18285.
9.
DingTGraesserLAbeyruwanS, et al. (2022) Learning high speed precision table tennis on a physical robot. Proc. IEEE/RSJ Int. Conf. Intell. Robot. Syst. (IROS): 10780–10787.
10.
D’AmbrosioDBAbeyruwanSWGraesserL, et al. (2024) Achieving human level competitive robot table tennis. In: 7th Robot Learning Workshop: Towards Robots with Human-Level Abilities. IEEE.
11.
GaoWGraesserLChoromanskiK, et al. (2020) Robotic table tennis with model-free reinforcement learning. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 5556–5563.
12.
GaoYTebbeJZellA (2022) Optimal stroke learning with policy gradient approach for robotic table tennis. Applied Intelligence53: 1–14.
13.
Gomez-GonzalezSNeumannGSchölkopfB, et al. (2016) Using probabilistic movement primitives for striking movements. In: IEEE-RAS International Conference on Humanoid Robots, IEEE, pp. 502–508.
14.
Gomez-GonzalezSNeumannGolkopfB, et al. (2020) Adaptation and robust learning of probabilistic movement primitives. IEEE Transactions on Robotics36(2): 366–379.
15.
GuistSSchneiderJDittrichA, et al. (2023) Hindsight states: blending sim and real task elements for efficient reinforcement learning. arXiv preprint arXiv:2303.02234.
16.
GuistSSchneiderJMaH, et al. (2024) Safe & accurate at speed with tendons: a robot arm for exploring dynamic motion. In: RSS 2024 Workshop: Data Generation for Robotics. IEEE. https://openreview.net/forum?id=AOmgPFj67O
17.
GuoQShiXMurakamiK, et al. (2025) Seal: a sample-efficient adjustment-learning method for table tennis robot serve. In: 2025 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 14924–14930.
18.
HereidAHaribOHartleyR, et al. (2019) Rapid trajectory optimization using c-frost with illustration on a cassie-series dynamic walking biped. In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp. 4722–4729.
19.
IjspeertAJNakanishiJSchaalS (2002) Movement imitation with nonlinear dynamical systems in humanoid robots. ICRA2: 1398–1403.
20.
KoberJMüllingKKrömerO, et al. (2010) Movement templates for learning of hitting and batting. In: IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 853–858.
21.
KoçOMaedaGPetersJ (2016) A new trajectory generation framework in robotic table tennis. In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp. 3750–3756.
22.
KoçOMaedaGPetersJ (2018) Online optimal trajectory generation for robot table tennis. Robotics and Autonomous Systems105: 121–137.
23.
LiZ.PengX.B.AbbeelP.LevineS.BersethG.SreenathK. (2025) Reinforcement learning for versatile, dynamic, and robust bipedal locomotion control. The International Journal of Robotics Research44(5): 840–888.
24.
LiuCHayakawaYNakashimaA (2012) Racket control and its experiments for robot playing table tennis. In: 2012 IEEE International Conference on Robotics and Biomimetics (ROBIO). IEEE, pp. 241–246.
25.
LiuYWangYLuoY, et al. (2024) Constraint-aware online joint-space motion planning for robotic table tennis. In: Proceedings of the 2024 4th International Conference on Robotics and Control Engineering. IEEE, pp. 1–6.
26.
LuoYWangYDongK, et al. (2023) Sirl: self-Imitation reinforcement learning for single-step hitting tasks. In: 2023 International Conference on Advanced Robotics and Mechatronics (ICARM). IEEE, pp. 185–190.
27.
MatsubaraTHyonSHMorimotoJ (2010) Learning stylistic dynamic movement primitives from multiple demonstrations. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, pp. 1277–1283.
28.
MuellingKKoberJPetersJ (2010) Learning table tennis with a mixture of motor primitives. In: 2010 10th IEEE-RAS International Conference on Humanoid Robots. IEEE, pp. 411–416.
29.
MuellingKBoulariasAMohlerB, et al. (2014) Learning strategies in table tennis using inverse reinforcement learning. Biological Cybernetics108: 603–619.
30.
MüllingKKoberJKroemerO, et al. (2013) Learning to select and generalize striking movements in robot table tennis. The International Journal of Robotics Research32(3): 263–279.
31.
NakashimaAOgawaYLiuC, et al. (2011) Robotic table tennis based on physical models of aerodynamics and rebounds. In: 2011 IEEE International Conference on Robotics and Biomimetics. IEEE, pp. 2348–2354.
32.
OrekhovALSimaanN (2020) Solving cosserat rod models via collocation and the magnus expansion. In: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp. 8653–8660.
33.
RenZHuBWangZ, et al. (2023) Knowledge database-based multiobjective trajectory planning of 7-dof manipulator with rapid and continuous response to uncertain fast-flying objects. IEEE Transactions on Robotics39(2): 1012–1028.
34.
SaverianoMAbu-DakkaFJKrambergerA, et al. (2023) Dynamic movement primitives in robotics: a tutorial survey. The International Journal of Robotics Research42(13): 1133–1184.
35.
SuHFangZXuD, et al. (2013) Trajectory prediction of spinning ball based on fuzzy filtering and local modeling for robotic ping–pong player. IEEE Transactions on Instrumentation and Measurement62(11): 2890–2900.
36.
TakenakaTMatsumotoTYoshiikeT, et al. (2009) Real time motion generation and control for biped robot-2 nd report: running gait pattern generation. In: 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, pp. 1092–1099.
37.
TebbeJKrauchLGaoY, et al. (2021) Sample-efficient reinforcement learning in robotic table tennis. In: Proceedings IEEE International Conference on Robotics and Automation. IEEE, pp. 4171–4178.
38.
WangYSunZLuoY, et al. (2023) A novel trajectory-based ball spin estimation method for table tennis robot. IEEE Transactions on Industrial Electronics71(8): 9244–9254.
39.
WangYLuoYZhangH, et al. (2024) A table-tennis robot control strategy for returning high-speed spinning ball. IEEE29(3): 2115–2124.
40.
YangLZhangHZhuX, et al. (2021) Ball motion control in the table tennis robot system using time-series deep reinforcement learning. IEEE Access9: 99816–99827.
41.
ZhangZXuDTanM (2010) Visual measurement and prediction of ball trajectory for table tennis robot. IEEE Transactions on Instrumentation and Measurement59(12): 3195–3205.
42.
ZhangYZhaoYXiongR, et al. (2014) Spin observation and trajectory prediction of a ping-pong ball. In: 2014 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 4108–4114.
43.
ZhangKCaoZLiuJ, et al. (2018) Real-time visual measurement with opponent hitting behavior for table tennis robot. IEEE Transactions on Instrumentation and Measurement67(4): 811–820.
44.
ZhuYZhaoYJinL, et al. (2018) Towards high level skill learning: learn to return table tennis ball using Monte-Carlo based policy gradient method. In: IEEE International Conference on Real-time Computing and Robotics (RCAR). IEEE, pp. 34–41.
