Ant Group's LingBot-Touch Tactile Foundation Model Open-Source to Equip Robots with Haptic Perception
蚂蚁灵波 LingBot-Touch 触觉基础模型开源，为通用大脑接入“手感”
On November 10, Ant Group's LingBot Technology open-sourced the LingBot-Touch tactile foundation model, designed to unify raw signals from magnetic, visual, and piezoresistive sensors into a shared representation for robot control.
Source: IT Home — Robotics · 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
IT之家从官方介绍获悉，基于近 5000 小时真实触觉数据预训练，LingBot-Touch 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 ，让积累的“手感”能够 跨传感器、跨灵巧手、跨模型 和 跨任务 复 用。
Open source S3Reported success rate
56.25%
View original evidence
其中，在 T-Rex 控制 Sharpa Wave 拧瓶盖的任务中，不使用触觉时的成功率为 56.25%，直接输入传感器原始信号时为 62.5%，接入 LingBot-Touch 的触觉表征后，成功率达到 90%。
Open source S15Reported success rate
90%
View original evidence
其中，在 T-Rex 控制 Sharpa Wave 拧瓶盖的任务中，不使用触觉时的成功率为 56.25%，直接输入传感器原始信号时为 62.5%，接入 LingBot-Touch 的触觉表征后，成功率达到 90%。
Open source S15
Dataset details reported by the source
- Modalities
- tactile Open source S3
- paper: 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.
蚂蚁灵波 LingBot-Touch 触觉基础模型开源，为通用大脑接入“手感”
Open source S1
IT之家从官方介绍获悉，基于近 5000 小时真实触觉数据预训练，LingBot-Touch 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 ，让积累的“手感”能够 跨传感器、跨灵巧手、跨模型 和 跨任务 复 用。
Open source S3
在 26 项真机测试中，接入这一表征后，四种动作模型的平均任务成功率较无触觉时提高约 14 至 26 个百分点。
Open source S4
其中，在 T-Rex 控制 Sharpa Wave 拧瓶盖的任务中，不使用触觉时的成功率为 56.25%，直接输入传感器原始信号时为 62.5%，接入 LingBot-Touch 的触觉表征后，成功率达到 90%。
Open source S15
接入 LingBot-VLA、π0.5 和 T-Rex 后，模型参数量仅增加约 0.13% 至 0.16%。
Open source S22
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：IT Home — Robotics · ithome.com