🚀 Introducing the Next Generation of TouchTronix Robotics FusionX— and our new Vision-Tactile Datasets
We’re excited to introduce the latest generation of FusionX, our multimodal data collection system built for robotic learning and Physical AI.
This release brings major upgrades across sensing, perception, synchronization, and data annotation:
🔹 State-of-the-art tactile sensors
A newly developed thin-film tactile sensor architecture and hot-pressing manufacturing technique delivers significantly improved sensitivity, stability (especially addressing “grasp-free” baseline signal drift), and pixel-to- pixel consistency.
🔹 Three-view visual perception
FusionX now combines stereo vision with dual wrist-mounted cameras, capturing manipulation from three complementary perspectives.
🔹 Highly aligned vision-tactile data
Tactile signals and visual observations are tightly synchronized and aligned (<5 ms lantency), enabling models to better connect what happens visually with the underlying physical contact.
🔹 In-house hand pose estimation algorithm
Our proprietary hand-pose pipeline provides structured hand kinematics alongside tactile and visual observations.
🔹 High-precision natural-language annotations
Each dataset can include detailed semantic annotations describing actions, objects, interactions, and manipulation processes — making the data more directly usable for robot learning and multimodal model training.
But the most important part is the data.
We have already collected thousands of hours of real-world vision-tactile manipulation data, and are scaling toward 10,000+ hours in the coming weeks.
Both the complete FusionX system and our vision-tactile datasets are now commercially available. (Product/Datasets contact: [email protected])
We are building the data infrastructure that connects vision, touch, hand motion, gaze, semantics and more— so robots can learn not only what the physical world looks like, but how it feels and how to interact with it.
Vision + Touch → Robotic Intelligence.
#PhysicalAI #Robotics #EmbodiedAI #RobotLearning #TactileSensing #MultimodalAI #DexterousManipulation #RoboticsData #TouchTronix #FusionX
Fused Hand Pose Tracking+ Tactile Force Distribution in Physical 3D youtu.be/Q4P6cpfVglQ?si=wnai… via @YouTube
2
66
TouchTronix Robotics Pro Portable Data Collection System for Robotic Tra... youtu.be/ye9c8EP0Tfs?si=37A1… via @YouTube
3
52
📢New FusionX Human-Centric Tactile-Vision Sample Datasets 𝄜(V2.0) Alert! huggingface.co/datasets/touc…
In human-centric data collection for robotic learning🤖, the quality of data is highly relied on the calibration of tactile and bending sensors, as the baseline of sensor signal may vary from user to user considering different size, shape, and rigidity of human hands ✋. For conducting fabrics-based tactile gloves 🧤, specifically, strain effect due to the stretchability of gloves is the main headache resulting in such baseline drift.
In our newly released FusionX V2.0 datasets, significant improvements have been made through our new software development:
1. 📏Calibration of tactile and bending sensors on data gloves through built-in calibration function.
2. 📸More stabilized vision data with improved frame rate consistency
3. 🛣️Improved depth data via better algorithm.
4. 🤝Enhanced synchronization via streamlined data pipeline for vision-tactile data alignment.
FusionX Beta Pre-Sales with Exclusive Early-Bird Pricing Are Still Live! 🎉📄 Explore the full product details in our brochure: static1.squarespace.com/stat…
#AI #Robotics #MachineLearning #MultimodalAI #DataCollection #ImitationLearning #EmbodiedAI #Robotics #RoboBusiness #TactileSensing #AIData #HumanRobotInteraction #Humanoid #VisionTactileAction #FoundationModel #MotionCapture #HumanIntention #MachineLearning #Manufacturing
🚀 Introducing TouchTronix Robotics's new product: FusionX – A Human-Centric Multimodal Data Acquisition System
Take a sneak peek at our new wearable human-centric data collection solution featuring tactile sensing gloves, synchronized vision capture, and modular head and chest camera mounting for stable first-person data recording.
FusionX is engineered for:
🤖 Robotics manipulation learning
🧠 Imitation & behavior cloning
📊 Foundation model training
🦾 Human-object interaction research
By synchronizing touch and vision in real time, FusionX enables the creation of high-fidelity multimodal datasets designed for next-generation embodied AI systems. If you're building AI models that learn from human interaction, we’ve made sample datasets available for download.
🔗 Access the sample datasets here: touchtronix.io/data-factory
Feel free to reach out via direct message or email ([email protected]) for product information.
Let’s build smarter machines — together.
#AI #Robotics #MachineLearning #MultimodalAI #DataCollection #ImitationLearning #EmbodiedAI #Robotics #RoboBusiness #TactileSensing #AIData #HumanRobotInteraction #Humanoid #VisionTactileAction #FoundationModel #MotionCapture #HumanIntention #MachineLearning #Manufacturing
2
45
After months' of efforts, we’re excited to share that TouchTronix Robotics SensX tactile array sensors are now available on @digikey ! 🎉🎉🎉 This big step makes our product accessible to a broader R&D community (robotics, healthcare, manufacturing, etc.) with faster, easier procurement🚀🚀🚀
We’re excited to share our human-centric #multimodal data collection solution designed to bridge human skills and robotic intelligence 🤖🤝 Our system synchronizes #tactile sensing, #motioncapture gloves, and a #vision stack (RGB + Depth) to capture how humans see, move, and feel during real-world interactions.
By recording fine-grained contact forces, touch patterns, hand kinematics, and visual context in a synchronized and unified framework, we enable high-quality datasets for robotic #manipulation, #physicalAI, and #worldmodel training.

