Skip to content
Chinese robotics — Deployment discovery·· 6 days agoSignalEditorial score75

Zhiwang Future Demonstrates Second-Generation Dual-Arm Robot at CeMAT

具身智能的“算账时代”:这家企业在仓库里死磕“1公分”与“1比1”替人

Summary

At the CeMAT exhibition on November 3, Zhiwang Future showcased its second-generation dual-arm robot, Armstrong Pro, performing autonomous navigation and item picking in a pharmaceutical warehouse. CEO Sun Junkai highlighted that while early industry focus was on basic mobility, current clients prioritize proven commercial viability. The company's WISE-RL architecture combines world action models with reinforcement learning to handle physical constraints like a 1cm reach limitation. Although initial failure rates remain between 1% and 3%, the system uses continuous data feedback to improve efficiency, aiming for a 1:1 labor replacement ratio over time.

Source: Chinese robotics — Deployment 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.

Control
Reported autonomousOpen source S3

Reported numbers

  • Reported failure rate

    1%

    View original evidence
    ” 即便到现在,机器人的整体失败率依然在1%到3%。
    Open source S13
  • Reported failure rate

    3%

    View original evidence
    ” 即便到现在,机器人的整体失败率依然在1%到3%。
    Open source S13
  • Reported duration

    8 hours

    View original evidence
    未来甚至会超过1,因为—人一天8小时后下班,机器人晚上还能巡检、盘点、提前排产。
    Open source S22
  • items

    100,000

    View original evidence
    只有在系统积累了10万个SKU的经验后,当第10万零1个新SKU出现时,学习时间才能缩短到“小时/分钟级别”。
    Open source S19
  • paper: not_reported

What remains unknown

Not established in the collected evidence: Environment, 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.

在具身智能企业智往未来的展台上,观众正通过iPad体验“下单”——随着指令下发,其二代 机器人 轮式双臂 机器人 Armstrong Pro自主导航至密集货架,精准抓取指定物品并放入料箱。

Open source S3

” 即便到现在,机器人的整体失败率依然在1%到3%。

Open source S13

未来甚至会超过1,因为—人一天8小时后下班,机器人晚上还能巡检、盘点、提前排产。

Open source S22

在上述药企的算账逻辑里,一个工人三年的 综合 成本在几十万元左右,而机器人的生命周期是五年。

Open source S23

人的产能受情绪、熟练度、疲劳度影响,但机器人的产能是标准化、可控的。

Open source S24

只有在系统积累了10万个SKU的经验后,当第10万零1个新SKU出现时,学习时间才能缩短到“小时/分钟级别”。

Open source S19

Source:Chinese robotics — Deployment discovery · finance.eastmoney.com

Timezone · UTC

Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).