PingpongDuo: Agile Humanoid Table Tennis Doubles with Safe Team Coordination
Overview
PingpongDuo introduces a hierarchical framework for agile humanoid doubles table tennis with safe team coordination. It improves ball-return success by 13.2% in simulation and achieves 2 cm positioning error. Real-world tests show a 2.15 m clearance-and-recovery cycle in 2.4 seconds with peak speed 2.23 m/s, and robots sustain over 10 consecutive strikes in strict alternation.
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
1 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · Reported success rate: 13.2 percent · Basis not reported
“one another to support rapid transitions. A racket-arm residual further refines strikes after movement using return feedback from a simulator calibrated with real ball-flight and contact measurements. In simulation, PingpongDuo improves the ball-return success rate by 13.2% over the state-of-the-art baseline, while achieving approximately 2 cm positioning error during clearance. In real-world experiments, a robot co”
Exact source · revision 1Source owner not reported
Reported quantity · positioning error: 2 other · Basis not reported
“one another to support rapid transitions. A racket-arm residual further refines strikes after movement using return feedback from a simulator calibrated with real ball-flight and contact measurements. In simulation, PingpongDuo improves the ball-return success rate by 13.2% over the state-of-the-art baseline, while achieving approximately 2 cm positioning error during clearance. In real-world experiments, a robot co”
Exact source · revision 1Source owner not reported
Reported quantity · clearance-and-recovery cycle length: 2.15 other · Basis not reported
“mpletes a 2.15 m clearance-and-recovery cycle in 2.4 s with a peak speed of 2.23 m/s, while two robots sustain more than 10 consecutive strikes in strict alternation.”
Exact source · revision 1Source owner not reported
Reported quantity · clearance-and-recovery cycle time: 2.4 other · Basis not reported
“mpletes a 2.15 m clearance-and-recovery cycle in 2.4 s with a peak speed of 2.23 m/s, while two robots sustain more than 10 consecutive strikes in strict alternation.”
Exact source · revision 1Source owner not reported
Reported quantity · peak speed: 2.23 other · Basis not reported · Differing source assertions
“mpletes a 2.15 m clearance-and-recovery cycle in 2.4 s with a peak speed of 2.23 m/s, while two robots sustain more than 10 consecutive strikes in strict alternation.”
Exact source · revision 1Source owner not reported
Reported quantity · consecutive strikes: 10 other · Basis not reported
“mpletes a 2.15 m clearance-and-recovery cycle in 2.4 s with a peak speed of 2.23 m/s, while two robots sustain more than 10 consecutive strikes in strict alternation.”
Exact source · revision 1Source owner not reported
Reported quantity · total moving distance: 2.15 other · Basis not reported · Differing source assertions
“实机测试中，一台机器人能在 2.4 秒内完成总移动距离 2.15 米的让位与回位，峰值速度达到 2.23 米/秒。”
Exact source · revision 1qbitai
Reported quantity · peak speed: 2.23 other · Basis not reported · Differing source assertions
“实机测试中，一台机器人能在 2.4 秒内完成总移动距离 2.15 米的让位与回位，峰值速度达到 2.23 米/秒。”
Exact source · revision 1qbitai
Reported quantity · average continuous legal return count: 4.87 other · Basis not reported · Differing source assertions
“在使用相同风险过滤器的条件下，把规则站位换成学习得到的联合站位，仿真中的平均连续合法回球数从3.79次提高到4.87次。”
Exact source · revision 1qbitai
Reported quantity · total moving distance: 2.15 other · Basis not reported · Differing source assertions
“实机测试中，一台机器人能在 2.4 秒内完成总移动距离 2.15 米的让位与回位，峰值速度达到 2.23 米/秒。”
Exact source · revision 1qbitai
Reported quantity · average continuous legal return count: 4.87 other · Basis not reported · Differing source assertions
“在使用相同风险过滤器的条件下，把规则站位换成学习得到的联合站位，仿真中的平均连续合法回球数从3.79次提高到4.87次。”
Exact source · revision 1qbitai
Report timeline
Follow attributed reports and material updates.
- QbitAI — Robotics on WeChatSignalTwo Unitree G1 Robots Play Table Tennis Doubles: PingpongDuo Enables Humanoid Team Coordination
A research team from Shanghai Chuangzhi College, Yuance Future, Hong Kong University, and NVIDIA has developed PingpongDuo, a system that enables two Unitree G1 humanoid robots to perform table tennis doubles. The system combines perception, team coordination, and whole-body motion control, using reinforcement learning for planning and risk assessment. Real-world testing showed improved performance over traditional rule-based strategies, with the robots achieving 18 consecutive alternating returns in a human-robot doubles match.
- arXiv Robotics — research abstractsPingpongDuo: Agile Humanoid Table Tennis Doubles with Safe Team Coordination
This paper presents PingpongDuo, a hierarchical framework for agile humanoid doubles table tennis with safe team coordination. The system includes a team-level planner that selects positioning targets and filters risky proposals, and individual-level footwork and striking skills guided by human motion references. In simulation, PingpongDuo improves ball-return success rate by 13.2% over the state-of-the-art baseline, and in real-world experiments, a robot completes a 2.15 m clearance-and-recovery cycle in 2.4 seconds with a peak speed of 2.23 m/s.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).