Ant Group's Lingbo Technology Opens Tactile Foundation Model LingBot-Touch
Fable 5.2 “撞车”蚂蚁灵波触觉模型，CEO 朱兴：两类模型协同将加速具身产业成熟
On November 10, Ant Group's Lingbo Technology open-sourced the tactile foundation model LingBot-Touch. The model unifies magnetic, visual, and resistive touch signals into a common representation to improve fine manipulation tasks on multiple robotic hands. In tests involving 26 real-world tasks on two robotic hands, integrating LingBot-Touch increased average task success rates by approximately 14 to 26 percentage points across four action models.
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
training_hours
5,000 hours
View original evidence
此次开源的 LingBot-Touch 基于近 5000 小时真实触觉数据预训练，覆盖磁触觉、视触觉和压阻式三类主流传感原理，可将不同信号转化为同一套触觉表征，供不同灵巧手和动作模型使用，让机器人在"看得清楚、想得明白"的同时，进一步补齐精细操作所需的触觉感知。
Open source S6model_parameters
≈5,300,000
View original evidence
为兼顾感知能力与端侧算力，蚂蚁灵波提供了两种容量的模型：此次 26 项真机测试全部使用约 530 万参数的轻量版 LingBot-Touch-Tiny 完成，接入 LingBot-VLA、π0.5 和 T-Rex 后，模型参数量仅增加约 0.13% 至 0.16%；容量较大的 LingBot-Touch-Small 则在感知测试中表现出进一步提升的潜力——当预训练数据增至近 5000 小时时，模型仍能从新增数据中获益，说明触觉预训练还有持续扩展提升的空间。
Open source S19Reported success rate
56.25%
Reported trials
View original evidence
以 T-Rex 控制 Sharpa Wave 拧瓶盖为例，不使用触觉时任务成功率为 56.25%，直接输入传感器原始信号为 62.5%，接入 LingBot-Touch 触觉表征后成功率达到 90%。
Open source S13Reported success rate
90%
Reported trials
View original evidence
以 T-Rex 控制 Sharpa Wave 拧瓶盖为例，不使用触觉时任务成功率为 56.25%，直接输入传感器原始信号为 62.5%，接入 LingBot-Touch 触觉表征后成功率达到 90%。
Open source S13
Dataset details reported by the source
- Modalities
- tactile Open source S6
- paper: not_reported
- dataset: not_reported
- code: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Dataset licensing and commercial-use rights are not established here.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
此次开源的 LingBot-Touch 基于近 5000 小时真实触觉数据预训练，覆盖磁触觉、视触觉和压阻式三类主流传感原理，可将不同信号转化为同一套触觉表征，供不同灵巧手和动作模型使用，让机器人在"看得清楚、想得明白"的同时，进一步补齐精细操作所需的触觉感知。
Open source S6
为兼顾感知能力与端侧算力，蚂蚁灵波提供了两种容量的模型：此次 26 项真机测试全部使用约 530 万参数的轻量版 LingBot-Touch-Tiny 完成，接入 LingBot-VLA、π0.5 和 T-Rex 后，模型参数量仅增加约 0.13% 至 0.16%；容量较大的 LingBot-Touch-Small 则在感知测试中表现出进一步提升的潜力——当预训练数据增至近 5000 小时时，模型仍能从新增数据中获益，说明触觉预训练还有持续扩展提升的空间。
Open source S19
26 项真机测试，任务成功率提高 14 至 26 个百分点 随着通用大模型持续进步，机器人理解复杂任务、推理操作步骤的能力正在增强。
Open source S8
以 T-Rex 控制 Sharpa Wave 拧瓶盖为例，不使用触觉时任务成功率为 56.25%，直接输入传感器原始信号为 62.5%，接入 LingBot-Touch 触觉表征后成功率达到 90%。
Open source S13
"朱兴说，蚂蚁灵波将坚持具身原生路线，持续探索物理操作泛化性的新上限，打造跨构型的机器人行业通用大脑，推动视觉、深度、触觉乃至温度等更多物理模态在统一模型中对齐，并在推进商业化的同时持续向社区开源开放。
Open source S24
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
- Check the exact dataset version, license, modalities and task coverage against the intended use.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：Chinese robotics — Robot learning research · cn.chinadaily.com.cn