HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:AMF6ALF3record.jsonopen to challenge →
read the original abstract
Humanoid robots have recently achieved impressive progress in locomotion and whole-body control, yet they remain constrained in tasks that demand rapid interaction with dynamic environments through manipulation. Table tennis exemplifies such a challenge: with ball speeds exceeding 5 m/s, players must perceive, predict, and act within sub-second reaction times, requiring both agility and precision. To address this, we present a hierarchical framework for humanoid table tennis that integrates a model-based planner for ball trajectory prediction and racket target planning with a reinforcement learning-based whole-body controller. The planner determines striking position, velocity and timing, while the controller generates coordinated arm and leg motions that mimic human strikes and maintain stability and agility across consecutive rallies. Moreover, to encourage natural movements, human motion references are incorporated during training. We validate our system on a general-purpose humanoid robot, achieving up to 106 consecutive shots with a human opponent and sustained exchanges against another humanoid. These results demonstrate real-world humanoid table tennis with sub-second reactive control, marking a step toward agile and interactive humanoid behaviors.
This paper has not been read by Pith yet.
Forward citations
Cited by 27 Pith papers
-
Physics Models for Sim-to-Real Transfer in Professional-Level Robot Table Tennis
Physics models with Reynolds- and spin-dependent aerodynamics, buckling-adjusted restitution, and a residual NN for racket contacts reduce landing position errors by 59% on 277 professional games and support sim-to-re...
-
Reinforcement Learning-Based Control for an Inline Skating Humanoid Robot
Reinforcement learning produces a policy for passive inline skating on a humanoid robot that achieves up to 50% lower cost of transport than walking and transfers zero-shot to physical hardware.
-
1000 Rallies: An Event-Camera Dataset and Real-Time Learned Ball-State Estimation for Robotic Table Tennis
Creates the first large event-camera dataset for table tennis and uses a CNN to estimate ball state, achieving 36% better bounce prediction and enabling real-time robot rallies.
-
HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning
HumanoidArena is a new benchmark of 7 leg-critical HOI/HSI tasks that evaluates egocentric hierarchical whole-body policies in humanoids and finds performance is strongly conditioned on the low-level GMT used.
-
HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning
HARBOR is a new agentic harness framework that automates robot RL workflows end-to-end across 16 tasks in manipulation, locomotion, and dexterous control, matching or exceeding default configurations while enabling si...
-
TT4D: A Pipeline and Dataset for Table Tennis 4D Reconstruction From Monocular Videos
TT4D delivers a large-scale dataset of high-fidelity 3D table tennis gameplay reconstructed from monocular videos using a novel lift-first pipeline that infers ball trajectories and spin while handling occlusions.
-
DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors
Discrete diffusion policies support native asynchronous execution via unmasking for real-time chunking, delivering higher success rates and 0.7x inference cost versus flow-matching RTC on dynamic robotics benchmarks a...
-
DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors
Discrete diffusion policies act as natural asynchronous executors for robotics by treating action generation as iterative unmasking, yielding higher success rates and lower computation than flow-matching real-time chu...
-
Rhythm: Learning Interactive Whole-Body Control for Dual Humanoids
Rhythm transfers interactive whole-body behaviors from simulation to real dual Unitree G1 humanoids via interaction-aware retargeting and graph-reward RL.
-
USIM and U0: A Vision-Language-Action Dataset and Model for General Underwater Robots
Introduces USIM simulation dataset and U0 VLA model with CAP module for general underwater robot tasks, reporting 0.0359 offline error and 43.1% online success rate.
-
Physics Models for Sim-to-Real Transfer in Professional-Level Robot Table Tennis
Physics models with Re/spin-dependent aerodynamics, buckling-adjusted table restitution, and residual NN racket contact enable sim-to-real transfer for professional-level robot table tennis.
-
TaskNPoint: How to Teach Your Humanoid to Hit a Backhand in Minutes
TaskNPoint lets humanoid robots learn dynamic skills such as tennis backhands from single short human video demonstrations plus under one hour of single-GPU simulation training, achieving zero-shot generalization to n...
-
OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation
OmniContact introduces contact flow as a shared representation of body trajectories and contact signals to learn and chain loco-manipulation meta-skills, reporting 98.7% success on box carrying and 76.5% on push-stack tasks.
-
RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning
A three-stage motion-guided curriculum RL framework trains humanoid robots for soccer shooting, achieving 48.6% lower shot error and 2.96x higher velocity than baselines in simulation and sub-meter accuracy with 13.10...
-
What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents
A systematic study of hierarchical VLA agents identifies design principles that improve robot manipulation performance over flat and naive hierarchical baselines in simulation and real-world experiments.
-
Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
Imagine2Real enables zero-shot humanoid-object interaction by unifying motions as 4D point trajectories, tracking only base/hands/object keypoints inside a BFM latent space, and training with progressive simple reward...
-
MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence
MyoChallenge 2025 introduces standardized table tennis and soccer tasks for musculoskeletal models in the MyoSuite simulation framework to benchmark athletic motor control algorithms.
-
SigLoMa: Learning Open-World Quadrupedal Loco-Manipulation from Ego-Centric Vision
SigLoMa enables dynamic loco-manipulation on quadrupeds from ego-centric 5 Hz vision alone by using Sigma Points for scalable exteroception, an ego-centric Kalman Filter for high-rate state estimation, and an active s...
-
VOFA: Visual Object Goal Pushing with Force-Adaptive Control for Humanoids
VOFA combines a high-level visuomotor policy with a low-level force-adaptive controller to let humanoids push objects up to 17 kg to arbitrary goals using only noisy onboard vision, achieving over 80% real-world success.
-
Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks
GeAN learns actuator dynamics from position trajectories to enable successful sim-to-real transfer of goal-reaching and ball-in-a-cup policies on a 4-DoF pneumatic muscle-actuated robot, reported as the first such tra...
-
HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model
HAIC enables robust humanoid interactions with underactuated objects by predicting their dynamics from proprioceptive history and using a world model for adaptive control.
-
Humanoid Whole-Body Badminton via Multi-Stage Reinforcement Learning
A multi-stage RL curriculum produces a unified whole-body controller enabling humanoid robots to sustain badminton rallies in simulation and return shuttles at up to 19.1 m/s in real hardware, with both EKF-based and ...
-
Cooperative Long Rope Skipping via Multi-Agent Reinforcement Learning
Marope applies hierarchical MARL with decentralized lower-level rope policies and a centralized scheduler to achieve cooperative long rope skipping on Unitree G1 humanoids in simulation and reality.
-
HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers
HANDOFF is a distilled mixture-of-experts humanoid whole-body controller that follows a compact task-space interface, matches SOTA velocity tracking, provides large manipulation workspace on Unitree G1, and supports V...
-
GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors
GRAIL creates over 20,000 synthetic loco-manipulation sequences from known 3D configurations and video priors, then trains policies that achieve 84% pick-up and 90% stair-climbing success on a real Unitree G1 humanoid...
-
Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
Imagine2Real is a zero-shot humanoid-object interaction method that unifies robot and object motion as 4D point trajectories, tracks only sparse keypoints inside a behavior foundation model latent space, and trains wi...
-
A Tutorial on World Models and Physical AI
A tutorial that unifies explicit and implicit world models through shared predictive structure for applications in physical AI such as robotics.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.