Robotiq has launched its TSF-85 tactile sensor fingertips for the 2F-85 Adaptive Gripper, giving Bodily AI programs the sense of contact wanted for real-world manipulation.
With built-in tactile sensing, Robotiq allows robots to not solely see the world, however to really feel, perceive, and reliably work together with it at scale. The Tactile Sensor Fingertips for the 2F-85 gripper can be found now.
Robots can’t study the bodily world by means of imaginative and prescient alone. Actual-world manipulation requires contact consciousness, power management, and suggestions from interplay.
With built-in tactile sensing, Robotiq expands its confirmed manipulation system past imaginative and prescient alone, enabling robots to really feel, perceive, and reliably work together with bodily objects at scale. The answer is designed for fast use in AI coaching labs, humanoid robotics, and industrial bodily AI functions.
Vincent Duchaine, CTO synthetic intelligence at Robotiq, says: “Bodily AI calls for greater than intelligent algorithms – it calls for dependable interplay with the true world.
“By combining adaptive gripping with high-frequency tactile sensing, we’re giving robots the sense of contact and management they should generalize throughout objects, duties, and environments with out the associated fee and complexity of anthropomorphic fingers.”
Adaptive gripping meets touch-enabled dexterity
Robotiq’s 2F-85 Adaptive Gripper is constructed on a patented mechanical design that goes past a conventional parallel gripper.
Whereas parallel grippers depend on exact positioning and inflexible alignment, the 2F gripper offers inherent adaptability by providing each pinch and encompassing grips, with stroke lengths of 85 mm and 140 mm.
This permits the gripper to adapt to object form, cut back grasp planning complexity, and reduce reliance on excellent imaginative and prescient, making it properly suited to general-purpose bodily AI programs designed to deal with all kinds of objects.
The brand new tactile fingertips add a strong sensing layer:
- A 4×7 static taxel grid to watch power distribution
- Micro-slip detection at 1000 Hz for secure, exact manipulation
- An built-in IMU for proprioceptive sensing and phone consciousness
Collectively, these capabilities enable robots to know contact geometry, detect incipient slip, and enhance generalization throughout numerous objects, capabilities which are essential for bodily AI datasets.
Constructed for fleets, not simply demos
In contrast to fragile, custom-built tactile fingers that usually battle with sturdiness and operational limits, Robotiq’s options are designed for scalable, long-term deployment.
Hundreds of Robotiq grippers are already working globally in demanding industrial and analysis environments, delivering excessive uptime, constant efficiency, and low whole price of possession.
The tactile-enabled 2F grippers combine simply into present programs utilizing native RS-485 communication and a USB conversion board, enabling versatile deployment throughout robotic manufacturers and analysis platforms.
The tactile fingertips are designed to protect the gripper’s encompassing and pinch grip mechanics, with minimal affect on stroke and attain, and have strong cabling constructed for real-world operation.
With a decrease invoice of supplies and substitute price than anthropomorphic or DIY fingers, Robotiq offers a sensible path from lab prototype to large-scale robotic fleets.
Bodily AI-ready, from coaching to deployment
Robotiq helps fashionable AI workflows by delivering dependable, feature-dense {hardware} designed to work constantly from proof of idea by means of real-world deployment.
By offering secure sensing and repeatable interactions throughout environments, Robotiq affords a dependable base for manipulation for reinforcement studying (RL), vision-language-action (VLA) fashions, and imitation studying.
The TSF-85 tactile sensor fingertips construct on years of Robotiq analysis and subject expertise. Robotiq shares finest practices for tactile information dealing with, together with steering on bias administration, normalization, and outlier detection, to assist groups generate constant, high-quality information for mannequin coaching.
By standardizing {hardware} and tactile information throughout robotic fleets and analysis campuses, Robotiq reduces integration friction and accelerates experimentation. This decreased integration helps groups transfer quicker from lab validation to production-scale bodily AI programs.
Confirmed by the world’s main AI and robotics groups
The TSF-85 joins Robotiq’s portfolio of bodily AI-ready manipulation parts, constructing on a basis already confirmed at scale.
With greater than 23,000 grippers deployed worldwide, Robotiq’s know-how is trusted by main organizations and has demonstrated sturdy efficiency in AI coaching labs and humanoid robotics pilots.
Aleksei Filippov, head of enterprise growth at Yango Tech Robotics, says: “To construct bodily AI that actually works, you want {hardware} that may sense, reply, and study from each interplay.
“That’s why we selected Robotiq. With Robotiq precision power management and dependable suggestions, we seize wealthy sensory information from each grasp.”
In comparison with do-it-yourself (DIY) tactile fingers that take months to develop and keep, Robotiq delivers a ready-today, field-proven answer. And in comparison with anthropomorphic fingers which are costly and complicated, Robotiq achieves the vast majority of real-world manipulation duties at a fraction of the associated fee.
Enabling the way forward for bodily AI
By giving robots a dependable sense of contact that mixes with adaptive gripping and industrial-grade reliability, Robotiq allows the subsequent era of bodily AI programs to study quicker, function extra robustly, and scale past the lab.
Backed by a big community of native companions, Robotiq ensures that prospects have quick help for setup and ongoing service. This help helps groups get again up and working rapidly if challenges come up.
Important picture: The tactile fingertips permits robots to know contact geometry, detect incipient slip, and enhance generalization throughout numerous objects, capabilities which are essential for bodily AI datasets
