X Square机器人每小时处理1816件包裹，超Figure 45%
1,816 parcels/hour is fast.
1,816 parcels/hour is fast.
每小时处理1,816个包裹，速度很快。
For context, Figure Robot's May endurance run averaged 1,248/hour across 200 hours.
作为参考，Figure Robot在5月份的耐力测试中，200小时平均每小时处理1,248个包裹。
So @XSquareRobot 's 1-hour livestream comes out roughly 45% higher on throughput.
因此，@XSquareRobot的1小时直播吞吐量大约高出45%。
There is a pretty important architectural reason for that.
这背后有一个非常重要的架构原因。
X Square isn't forcing the problem through a humanoid body.
X Square并没有强行让人形机器人来处理这个问题。
WALL-B controls two High-Performance 6-Axis Robot Arms with specialized grippers, continuously replanning as parcels move, get occluded, fail to transfer, or need their barcode side reoriented.
WALL-B控制两个高性能六轴机械臂，配备专用夹爪，随着包裹移动、被遮挡、转移失败或需要重新调整条码面，持续重新规划。
The pile changes after every pick. Parcels overlap, soft bags deform, labels face the wrong way, transfers fail.
每次抓取后，包裹堆都会变化。包裹重叠、软袋变形、标签朝向错误、转移失败。
WALL-B is supposed to reassess that new state, choose another grasp or reorientation, and keep the station running instead of handing the exception back to a human.
WALL-B需要重新评估新状态，选择另一个抓取点或重新定向，保持工作站运行，而不是将异常交回给人类处理。
The same model also extends into household and tabletop settings, where lighting, object positions, materials, and physical interactions are far less predictable.
同样的模型也扩展到家庭和桌面场景，那里的光照、物体位置、材质和物理交互远不那么可预测。
That requires a bigger “brain” that can perceive, reason, and adapt—not just repeat a narrow set of actions. This is what enables robots to move beyond industrial stations and into real household service.
这需要一个更大的“大脑”，能够感知、推理和适应，而不仅仅是重复一系列狭窄的动作。这就是让机器人超越工业工作站，进入真实家庭服务的关键。
And it did that for an hour while X Square processed 1,816 parcels at 98%+ accuracy.
它做到了这一点，持续一小时，而X Square以98%以上的准确率处理了1,816个包裹。
Specialization buys you speed.
专业化带来速度。
It still has to prove its broad generalization.
它仍需证明其广泛的泛化能力。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力