Tsinghua's TacTalent reports 93.8% success for GPT-6 Astra on contact-heavy tasks
Tsinghua University researchers published the TacTalent technical report on October 17 evaluating OpenAI's GPT-6 Astra on contact-rich manipulation. On the UniVTAC and OpenViTac visuo-tactile benchmarks, Astra averaged 93.8% and 81.8% success respectively, 22.9 and 13.1 percentage points above the best specialist models cited in the report. The team did not fine-tune a task-specific policy; instead it gave Astra a few demonstrations through the RoboICL framework and fed tactile sensor deformation as images, lifting UniVTAC from 76.3% with vision only to 93.8%, with key removal rising from 30% to 90%. The report notes that all 19 tasks ran in simulation, only about 10% of samples were used across 210 test rollouts, and specialist scores came largely from previously published work not tested under identical conditions; Astra's median API response was about 14 seconds, too slow for real-time contact control. A RoboDojo study reported in September had put Astra's average success at just 22.48% across 42 manipulation tasks.
The report suggests a general multimodal model can use tactile images for some contact-rich tasks without task-level fine-tuning, but the results come only from simulation and await real-robot validation.
9 月,自 OpenAI 发布 GPT-6 Astra 后,其在空间理解、三维建模和软件操作等方面展现出的能力,引起了具身智能行业的广泛关注。
过去几年,机器人公司一直在尝试训练自己的基础模型,而 Astra 的出现带给了行业一个新的启发:机器人需要的通用智能,会不会直接来自 GPT 这样的基础模型?
随后,一些研究团队开始将 Astra 接入机械臂,测试它的机器人控制能力。不过,早期实验结果并不理想。9 月公布的一项 RoboDojo 研究显示,Astra 在 42 项操作任务中的平均成功率仅为 22.48%,尤其在精确对齐、复杂双臂协调等任务上存在明显不足。
对于涉及摩擦、受力和持续接触的精细操作,机器人还需要根据触觉反馈不断调整动作,因此,这类任务一直被视为专用模型的重要优势领域。
#OpenAI#GPT-6 Astra#Tsinghua University#TacTalent#RoboICL#UniVTAC#OpenViTac#RoboDojo#SimpleTouch