🛰️ Daily AI Frontier
‹ back to 2026-09-09

从Demo到1000万次真实作业,万勋发布NOVA2.0柔性具身大脑

Industry & News Embodied Robotics

Ranking

Overall 54
Content 55
Popularity N/A

No observed public metrics; popularity remains neutral/archived.

Representative image for 从Demo到1000万次真实作业,万勋发布NOVA2.0柔性具身大脑

Merged summary

TL;DR - Wanxun Technology launched NOVA 2.0, a tactile-native, hierarchical control architecture for flexible embodied robots, claiming commercial deployment across 40+ real-world scenarios and more than 10 million operations. It targets reliable, low-latency robot control in unpredictable and extreme environments.

  • NOVA 2.0 separates high-level task planning from “subconscious” motion primitives, generating trajectories and corrections in a claimed 20 ms.
  • The architecture couples tactile sensing, morphology-aware computation, and soft robotic bodies to adapt across arms, dual-arm systems, dexterous hands, and humanoid configurations.
  • Wanxun says reusable motion primitives enable new tasks with as little as 1% of conventional startup data, followed by continual learning from real operations.
  • Reported deployments span construction, energy, transportation, autonomous driving, and manufacturing; performance and commercialization figures are company-reported claims.

Sources (1)

从Demo到1000万次真实作业,万勋发布NOVA2.0柔性具身大脑

雷峰网 (AI科技评论) 2026-09-09
Public signals N/A
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-26 14:16:28.759967 UTC

TL;DR - Wanxun Technology launched NOVA 2.0, a tactile-native, hierarchical control architecture for flexible embodied robots, claiming commercial deployment across 40+ real-world scenarios and more than 10 million operations. It targets reliable, low-latency robot control in unpredictable and extreme environments.

  • NOVA 2.0 separates high-level task planning from “subconscious” motion primitives, generating trajectories and corrections in a claimed 20 ms.
  • The architecture couples tactile sensing, morphology-aware computation, and soft robotic bodies to adapt across arms, dual-arm systems, dexterous hands, and humanoid configurations.
  • Wanxun says reusable motion primitives enable new tasks with as little as 1% of conventional startup data, followed by continual learning from real operations.
  • Reported deployments span construction, energy, transportation, autonomous driving, and manufacturing; performance and commercialization figures are company-reported claims.
item →