Ubtech Demonstrates Embodied AI Synergy with Astra Model and Proprietary Thinker Models
Astra 遇上优必选人形机器人：从通用大模型直接控制，到具身智能高效协同
Ubtech (HK9880) conducted six experiments combining the general-purpose Astra model with its proprietary Thinker-VLA and Thinker-WM models to explore embodied intelligence. Real-world tests showed that while Astra can understand scenes and plan tasks, direct control often fails at fine motor skills due to high computational costs. Integrating Thinker-VLA for execution and Thinker-WM for future prediction improved efficiency and task success rates, illustrating a path toward scalable robotic applications.
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
model processing time
≈70 minutes
View original evidence
本次实验记录： 模型累计处理耗时：约 70 分钟 Token 消耗：约 9557.8 万 Astra API 估算费用：约 579 美元 最终结果：未完成抓取 这揭示了通用大模型直接控制机器人的现实挑战：它能够理解空间关系、生成动作决策，但面对连续运动和精细操作时，仍可能需要大量推理与反复修正。
Open source S13Astra API estimated cost
≈579
View original evidence
本次实验记录： 模型累计处理耗时：约 70 分钟 Token 消耗：约 9557.8 万 Astra API 估算费用：约 579 美元 最终结果：未完成抓取 这揭示了通用大模型直接控制机器人的现实挑战：它能够理解空间关系、生成动作决策，但面对连续运动和精细操作时，仍可能需要大量推理与反复修正。
Open source S13
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
本次实验记录： 模型累计处理耗时：约 70 分钟 Token 消耗：约 9557.8 万 Astra API 估算费用：约 579 美元 最终结果：未完成抓取 这揭示了通用大模型直接控制机器人的现实挑战：它能够理解空间关系、生成动作决策，但面对连续运动和精细操作时，仍可能需要大量推理与反复修正。
Open source S13
尽管经过多轮尝试，机器人最终未能完成魔方抓取。
Open source S12
实验中，机器人成功完成了福袋抓取。
Open source S16
Source：Chinese robotics — Robot learning research · stock.10jqka.com.cn