Market
Robbyant open-sources LingBot-Touch, a tactile model trained on about 5,000 hours of touch data, with self-reported gains of 14 to 26 points across four policies
Ant Group’s Robbyant open-sources LingBot-Touch, trained on 4,983 hours of touch data. It reports 14–26 point gains across four policies on two robot hands.
Robbyant, Ant Group’s embodied-AI unit, open-sourced LingBot-Touch on November 10, a model that turns signals from three types of touch sensor into shared tactile tokens for robot policies. It was pretrained on about 4,983 hours of touch recordings, roughly two thirds from human operators wearing sensor gloves. Across 26 real-robot tasks on two dexterous hands, the company reports average success gains of about 14 to 26 percentage points over a no-touch baseline, spread over four policies and not for π0.5 alone.
The essentials
- The model: one encoder for magnetic, visuotactile and piezoresistive sensors, released under Apache 2.0, per Humanoids Daily.
- The data: about 4,983 hours of touch recordings, two thirds from human operators wearing sensor gloves, per Humanoids Daily.
- The result: 13.9 to 24.8 points of average success over a no-touch baseline for Diffusion Policy, π0.5, LingBot-VLA and T-Rex, per Humanoids Daily; the press release rounds to 14–26.
- The cost: the tokens add only about 0.13 to 0.16% to a policy’s parameter count, per Humanoids Daily.
How the numbers were produced
The 26 tasks were split between a dual-arm Sharpa Wave setup (20) and an XHand1 setup (6), per Humanoids Daily. Each policy was post-trained without touch, with raw tactile signals and with frozen LingBot-Touch tokens; raw signals gained at most about half as much and sometimes lowered success. The ranges are therefore an average over four policies and two hands, not a per-policy figure. Interesting Engineering reports a bottle-cap test where success rose from 56.25% to 90%.
Limits the authors state
Only two hands were tested on real robots, capacitive sensors were absent from pretraining, and coverage centers on fingertips, so palm and side contact is underrepresented, per Humanoids Daily. The results come from the developer’s own evaluation. Humanoids Daily also discloses that Robbyant paid it for a separate sponsored thread, while saying its article was produced independently.
What is not established
- Independent replication of the gains: none found.
- Performance on sensor types outside the three families, such as capacitive ones: not tested.
- How much of the 14–26 range holds for π0.5 alone: not separated in the sources read.
- Gains on robot hands other than the two tested: not shown.
Summary table
| Point | What is stated as of November 7, 2026 | Source |
|---|---|---|
| Release | Open-sourced November 10, 2026, Apache 2.0, code and weights on GitHub and Hugging Face | Humanoids Daily |
| Training data | About 4,983 hours of touch recordings, two thirds from sensor gloves | Humanoids Daily |
| Real-robot tests | 26 tasks, two dexterous hands, four policies | Humanoids Daily |
| Reported gain | About 14 to 26 points on average (13.9 to 24.8 in precise figures) | Interesting Engineering |
| Model size | Tiny version of about 5.3 to 5.5 million parameters; reports differ slightly | Interesting Engineering |
FAQ
Does LingBot-Touch improve π0.5 by 14 to 26 points?
Not by itself: the range covers average gains across four policies and two hands, π0.5 among them.
Is the data real or simulated?
The 4,983 hours are touch recordings, two thirds from human operators wearing sensor gloves and the rest from teleoperated robots.
Can anyone use it?
Code and weights are released under Apache 2.0 on GitHub and Hugging Face.
Method and limits
Checked on November 16, 2026. We read the Humanoids Daily page directly; Interesting Engineering and the Korea Newswire press release were seen through search excerpts. We did not read the technical report.
Sources
- Humanoids Daily: Robbyant Open-Sources LingBot-Touch, One Tactile Model for Three Sensor Types (verified 2026-11-08)
- Interesting Engineering: Robots gain touch with China dataset (verified 2026-11-08)
- Korea Newswire: Robbyant open-sources LingBot-Touch (Business Wire release) (verified 2026-11-08)
Spotted an error in this article? Report it · Our corrections policy