Geekplus AI Ping Pong Robots Demonstrate Embodied Decision-Making at CIIE
进博体验|“过招”人形机器人,AI乒乓对打藏着物理智能真功夫
At the 9th China International Import Expo, two full-size humanoid robots from Hitch Open performed stable AI-driven ping pong rallies. Dr. Allen Yang noted these systems, derived from the HOPE challenge, operate within tight reaction windows but currently lag behind trained human players in competitive play. The demo showcases real-time perception and control loops rather than commercial deployment.
Source: Chinese robotics — Hardware and sensing · Read original article ↗
English translation unavailable. Choose the original article to read it.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- Reported autonomousOpen source S7
Reported numbers
camera_refresh_rate
5
View original evidence
Hitch Open联合创始人Dr. Allen Yang在接受采访时介绍,全尺寸人形机器人需在约0.3秒内完成来球感知、轨迹预测、决策与挥拍并保持全身稳定,其中视觉相机每5毫秒刷新一帧,留给决策系统的反应窗口仅有几十毫秒,真正的技术先进性体现在预测、规划、控制能否形成实时闭环,经得起连续运行与失败恢复的反复测试。
Open source S9perception_time
≈0.3 seconds
View original evidence
Hitch Open联合创始人Dr. Allen Yang在接受采访时介绍,全尺寸人形机器人需在约0.3秒内完成来球感知、轨迹预测、决策与挥拍并保持全身稳定,其中视觉相机每5毫秒刷新一帧,留给决策系统的反应窗口仅有几十毫秒,真正的技术先进性体现在预测、规划、控制能否形成实时闭环,经得起连续运行与失败恢复的反复测试。
Open source S9
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
摘要: 进博会现场,记者现场体验了一次人机对战环节,在机器人稳定的喂球节奏里,直观感受到了物理智能的真实质感。
Open source S2
实际上,作为本届进博会的科技亮点展项,这套AI自主决策机器人乒乓对打系统并非简单的表演项目。
Open source S7
Hitch Open联合创始人Dr. Allen Yang在接受采访时介绍,全尺寸人形机器人需在约0.3秒内完成来球感知、轨迹预测、决策与挥拍并保持全身稳定,其中视觉相机每5毫秒刷新一帧,留给决策系统的反应窗口仅有几十毫秒,真正的技术先进性体现在预测、规划、控制能否形成实时闭环,经得起连续运行与失败恢复的反复测试。
Open source S9
第九届中国国际进口博览会现场,3号馆Hitch Open展位前人头攒动,两台全尺寸人形机器人隔乒乓球桌相对而立,挥拍、击球、回位一气呵成,连贯的对打节奏吸引了不少观展者驻足拍摄。
Open source S3
据了解,Hitch Open将于11月7日在临港展区主会场举行全球发布会,正式首发物理智能开源平台,同步落成漕河泾・Hitch Open物理智能联合创新中心,并发布2027全球积分赛历与青少年品牌Hitch Open Junior,通过“以赛促研、以赛兴产、以赛育人”的路径,推动具身智能技术从实验室成果走向真实产业落地。
Open source S13
Source:Chinese robotics — Hardware and sensing · msn.cn