Star Dust Intelligence Unveils AOS Operating System to Enable Non-Expert Developers for Embodied AI Applications via a 36-Hour Hackathon
资本退潮、GPT-6疾进时，谁在替具身智能修路？
At a three-station hackathon in Shenzhen, 17 teams built 47 robot apps with a 94% deployment rate using Star Dust's AOS. The system bridges generalist and embodied models to let users create physical applications without coding expertise. This demo validates an ecosystem where non-experts can deploy robots for real-world tasks like cleaning cat litter or writing calligraphy.
Source: Chinese robotics — Robot learning research · 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
applications
47
Reported trials
teams
17
Reported trials
applications
500
Reported trials
Reported duration
36 hours
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
2024年，来杰做了一个简单的内部试验：用三支笔在桌面上摆出箭头，指令机器人把东西放到箭头指向的位置。
Open source S22
三站比赛制作出的47个App，验证了一件事，当工具链足够完整时，非专业开发者也能做出在物理世界运行的机器人应用。
Open source S10
总决赛17支队伍，历时36小时，来自高校、产品、设计等不同背景，甚至是毫无人形机器人或完整App开发经验的参与者。
Open source S7
16款应用在现场最终完成真机迁移，上机率达94%。
Open source S9
2008年7月10日，App Store上线第一天，首批应用只有500款，寥寥几页就能浏览结束。
Open source S3
Source：Chinese robotics — Robot learning research · sohu.com