Humanoid Robot Catches Thrown Boxes Using Pure Vision in Three-Stage Reflex Framework
Overview
Researchers from the University of Washington, USC, and other institutions developed Reflex, a three-stage training framework enabling a Unitree G1 humanoid robot to catch unmarked cardboard boxes using only onboard RGB-D cameras. In real-world tests, the robot achieved 65% success at 2.5 meters and 40% at 5 meters, compared to human rates of 85% and 68.3%. The approach addresses whole-body coordination, latency prediction, and visual complexity without external motion capture or reflective markers.
Generated from attributed reports · Updated 23 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · Reported success rate: 85 percent · reported trials · Differing source assertions
“结果是,在2.5米距离下机器人接住了65%的箱子,5米距离下是40%,作为对比,三个真人在同样距离下的成功率是85%和68.3%。”
Exact source · revision 2Source owner not reported
Reported quantity · Reported success rate: 68.3 percent · reported trials · Differing source assertions
“结果是,在2.5米距离下机器人接住了65%的箱子,5米距离下是40%,作为对比,三个真人在同样距离下的成功率是85%和68.3%。”
Exact source · revision 2Source owner not reported
Reported quantity · flight duration: 1 other · Basis not reported
“论文里提到一个关键数字:在真实机器人实验中,箱子从扔出到到达机器人身边大约只有1秒,而摄像头采集图像到机器人做出控制指令这中间的延迟,中位数就有69毫秒。”
Exact source · revision 2Source owner not reported
Reported quantity · control latency: 69 other · Basis not reported
“论文里提到一个关键数字:在真实机器人实验中,箱子从扔出到到达机器人身边大约只有1秒,而摄像头采集图像到机器人做出控制指令这中间的延迟,中位数就有69毫秒。”
Exact source · revision 2Source owner not reported
Report timeline
Follow attributed reports and material updates.
- Chinese robotics — Hardware and sensingSignalHumanoid Robot Catches Thrown Boxes Using Pure Vision in Three-Stage Reflex Framework
Researchers from the University of Washington, USC, and other institutions developed Reflex, a three-stage training framework enabling a Unitree G1 humanoid robot to catch unmarked cardboard boxes using only onboard RGB-D cameras. In real-world tests, the robot achieved 65% success at 2.5 meters and 40% at 5 meters, compared to human rates of 85% and 68.3%. The approach addresses whole-body coordination, latency prediction, and visual complexity without external motion capture or reflective markers.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).