Robbyant Releases Open-Source LingBot-Touch for Enhanced Tactile Sensor Integration
- Published
- Source
- HumanoidsDaily
Robbyant, part of Ant Group, has open-sourced LingBot-Touch, a tactile model that integrates signals from various touch sensors into a unified system. This model, available on GitHub and Hugging Face, has shown significant improvements in robotic task success rates during real-robot tests, enhancing performance by up to 24.8 percentage points.
The significance of LingBot-Touch lies in its ability to standardize data from different sensor types, addressing the challenges of small and siloed tactile datasets. By mapping sensor data into a shared 'canonical fingertip space,' the model allows for better learning and application across diverse robotic hands, which typically require retraining when sensor configurations change.
Robbyant's LingBot-Touch, with two model sizes, aims to improve tactile data utilization in robotics. The model's performance in various tasks highlights the need for more extensive demonstrations to effectively train policies on high-dimensional sensor data. No further timeline was disclosed at the time of publication.
Original report
Robbyant Open-Sources LingBot-Touch, One Tactile Model for Three Sensor Types
HumanoidsDaily · [email protected] (Humanoids Daily Staff)This briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
-
11
RobotToday Weekly November 2 – 6, 2026 RobotToday · 5 days ago
- 12
Related Suppliers
Robbyant 蚂蚁灵波科技
China
Ant Group's embodied intelligence unit building the R1 wheeled humanoid service robot and LingBot spatial-perception AI models.
NeoteAI 上海新智具身智能科技有限公司
China
Shanghai Fudan spin-out founded 2025 making InTac visuo-tactile sensors, a tactile gripper and touch datasets; raised a near-RMB100M angel round.
MoSense 模感科技
Hong Kong
MoSense is a Hong Kong tactile-sensing startup, incubated from an HKUST robotics team, building flexible electronic skin and the MOPENARM robotic arm.
Sensible Machines
United States
CMU Robotics spin-off providing autonomous sensing modules, system design, and integration for equipment awareness in industrial and field robotics.
Henki Robotics
Finland
Finnish ROS 2 robotics software consultancy offering navigation, SLAM, fleet management and AI integration services.
Dyna Robotics
United States
US startup building embodied AI foundation models for dual-arm commercial robots, achieving 99%+ success in 24/7 deployments in restaurants and laundromats.
Intelligence Factory
United States
New York startup founded 2026 (YC P26) training robot manipulation foundation models on human demonstration data recorded with custom sensing gloves.
Brighter Signals
Netherlands
Amsterdam startup making fabric-based multi-modal tactile sensors; partnered with Shanghai-listed Tier-1 CAIP in 2025 to manufacture them at scale.
Apex Sensing LLC
United States
Apex Sensing develops flexible tactile sensors and electronic skin for humanoid robots, plus industrial inspection, medical and battery sensing.
Dexta Robotics 德觉科技
China
Shenzhen, China robotics company founded 2014; builds the Dexmo wireless hand exoskeleton delivering 11-degree-of-freedom force feedback for VR and AR headsets.
Force Dimension
Switzerland
Swiss manufacturer of high-precision haptic devices and force-feedback interfaces for teleoperation, surgical robotics, space applications, and research.
AMI Labs
France
AMI Labs is a Paris AI startup founded by Yann LeCun in 2025, building JEPA-based world models trained on real-world sensor data, not language.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.
