Catching Spinning Table Tennis Balls in Simulation with End-to-End Curriculum Reinforcement Learning
On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation
Abstract (arXiv)
The game of table tennis is renowned for its extremely high spin rate, but most table tennis robots today struggle to handle balls with such rapid spin. To address this issue, we have contributed a series of methods, including: 1. Curriculum Reinforcement Learning (RL): This method helps the table tennis robot learn to play table tennis progressively from easy to difficult tasks. 2. Analysis of Spinning Table Tennis Ball Collisions: We have conducted a physics-based analysis to generate more realistic trajectories of spinning table tennis balls after collision. 3. Definition of Trajectory States: The definition of trajectory states aids in setting up the reward function. 4. Selection of Valid Rally Trajectories: We have introduced a valid rally trajectory selection scheme to ensure that the robot's training is not influenced by abnormal trajectories. 5. Reality-to-Simulation (Real2Sim) Transfer: This scheme is employed to validate the trained robot's ability to handle spinning balls in real-world scenarios. With Real2Sim, the deployment costs for robotic reinforcement learning can be further reduced. Moreover, the trajectory-state-based reward function is not limited to table tennis robots; it can be generalized to a wide range of cyclical tasks. To validate our robot's ability to handle spinning balls, the Real2Sim experiments were conducted. For the specific video link of the experiment, please refer to the supplementary materials.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 13 of its 26 references that are in the map. First posted on arXiv 3 Mar 2025.
Builds on
13 of 26 references.
References · 13
- 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
- 2019Solving Rubik's Cube with a Robot Handcited by 734
- 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
- 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
- 2021safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Roboticscited by 50
- 2020D2RL: Deep Dense Architectures in Reinforcement Learningcited by 42
- 2020Learning to Play Table Tennis From Scratch using Muscular Robotscited by 35
- 2022i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loopscited by 32
- 2020Robotic Table Tennis with Model-Free Reinforcement Learningcited by 15
- 2020Sample-efficient Reinforcement Learning in Robotic Table Tenniscited by 12
- 2019Real Time Trajectory Prediction Using Deep Conditional Generative Modelscited by 11
- 2019Spin Detection in Robotic Table Tenniscited by 9
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Physics Models for Sim-to-Real Transfer in Professional-Level Robot Table Tennis ↗
- 2022GoalsEye: Learning High Speed Precision Table Tennis on a Physical Robot
- 2025PACE: Physics Augmentation for Coordinated End-to-end Reinforcement Learning toward Versatile Humanoid Table Tennis
- 2025HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning
- 2024Learning Diverse Robot Striking Motions with Diffusion Models and Kinematically Constrained Gradient Guidance
- 2025Learning to Ball: Composing Policies for Long-Horizon Basketball Moves
- 2025Integrating Learning-Based Manipulation and Physics-Based Locomotion for Whole-Body Badminton Robot Control
- 2025Reinforcement Learning for Ballbot Navigation in Uneven Terrain