蚂蚁集团 Robbyant 开源触觉 AI 模型
Ant Group’s Robbyant open-sources tactile AI model
蚂蚁集团 Robbyant 把触觉模型开源了，不同传感器信号能统一处理，做机器人感知的团队可以少走弯路。和各家自建触觉方案相比，这种跨传感器表征思路更省适配成本，搞具身智能的可以关注下代码。
蚂蚁集团旗下具身智能团队 Robbyant 宣布开源一个触觉 AI 模型，用于机器人触觉信号处理。该模型的核心能力是把来自不同类型触觉传感器的信号映射到统一的表征空间，让机器人在更换或混用传感器时无需重训整套感知系统。
从机制上看，这类共享表征做法类似触觉领域的通用编码器：无论传感器来自哪种硬件形态，模型都将其转换为同一套下游任务可用的特征，进而支撑抓取、材质识别等操作。目前公告信息较简短，模型参数量、训练数据和评测基准尚未披露。
Ant Group’s Robbyant open-sources tactile AI model
The model helps robots process touch signals from different sensor types through a shared representation.
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Robbyant, 蚂蚁集团, 触觉感知, 开源模型.
Source attribution: curated from Tech in Asia (@Minh Le).
