Wang Xingxing cites millimeter-scale alignment errors as the key bottleneck for embodied AI at CIIE
【第九届进博会】王兴兴：具身智能的卡点不在“脑子” 在“最后几毫米”
At the ninth CIIE forum, Geeks' founder Wang Xingxing stated that current robot challenges stem from input-output misalignment with the physical world rather than planning limitations. He noted that while large-object grasping approaches 100% success, precision assembly remains difficult due to these final-millimeter deviations.
Source: Robotics — Chinese web discovery · 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.
Reported numbers
Reported success rate
100%
time to resolve alignment error
1–2
- paper: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
抓取大物体成功率已接近100%，但精密操作、装配零部件等成功率低很多。
Open source S3
他预计，这一问题未来1到2年可较好解决。
Open source S5
Source：Robotics — Chinese web discovery · chinanews.com.cn