Haptic feedback support for MANUS is now available in NVIDIA Isaac Teleop. In Isaac Lab teleoperation workflows, contact signals from the simulated robot hand can now be translated into per-finger vibrotactile feedback on the operator’s glove. The MANUS integration receives haptic commands through Isaac Teleop and drives the glove’s five finger vibration motors via the MANUS SDK. This adds haptic feedback to the existing high-fidelity hand tracking integration and provides operators with an additional feedback channel during teleoperation and demonstration recording. We appreciate the @NVIDIARobotics team’s continued work on the MANUS integration and the close collaboration that made this possible. Read the @nvidia documentation:

MANUS Metagloves Pro Haptic combines EMF-based fingertip tracking with a 25-DoF anatomical hand model to reproduce the complete hand pose in real time. Thumb and index fingertip pinch the lid and rotate in opposite directions to break the initial resistance, then continually shift contact points along the ridges to keep turning without ever losing grip. It is a precise two-finger negotiation. For robotics, teleoperation, and embodied AI research, this level of hand data helps capture the subtle finger movements that influence grasping, manipulation, and control. Integrated haptic feedback also provides operators with tactile cues during interaction. Learn more:

$AAPL HIT WITH RECORD $5.7B PATENT VERDICT A federal jury found Apple’s Taptic Engine, used for haptic feedback in iPhones and Apple Watches, infringed two Taction patents. Taction first sued Apple in 2021. Reuters says it’s the largest U.S. patent verdict to date. Apple denies using Taction’s technology and could ultimately have to pay more than $5.7B, though it says it will appeal.

Cybercab’s motorized seat belts do more than tighten themselves. They can vibrate or pulse to provide haptic feedback and get the passenger’s attention. They can also proactively tighten when Cybercab anticipates or detects harsh braking, loss of traction or another sudden road event.

Robotics basics straight from Stanford! 😮‍💨 This free from Stanford University is a great starting point to kinematics, dynamics, control, motion planning, trajectory generation, and design. There is no better way to get into robotics than through a legend like Oussama Khatib from Stanford Robotics Center. Oussama Khatib is one of robotics founding legends. He was reseaching human-centered robotics when the field was still obsessed with industrial cages and safety barriers. His work on haptic feedback and dynamic control made robots safe to work alongside humans. 16 lectures grounded in the actual mathematics robots need to move safely and work with people. That's what you can find inside: → Spatial transformations → Forward & inverse kinematics → Jacobians, velocity propagation, and singularities → Trajectory generation → Motion planning → Newton-Euler and Lagrangian methods → Manipulation, and compliance, → Applications in vision-based robotics and whole-body control Access it here for free and recommend to your robotics buddy: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Meta just open-sourced its dexterity stack! 🪬 Most physics simulators were built for things that move through space. Walking robots, drones, cars. Contact is the part they approximate worst, and obviously dexterous manipulation is nothing but contact. Project SuperDex, from Meta Reality Labs Research, is built the other way around, a contact-first physics engine with the whole platform stacked on top of it. The cool part is that it's on GitHub. The engine runs one solver across rigid bodies, soft bodies, rods and tendons, shells and cloth, in the same model. → Non-convex collision with accurate contact force distributions, so a multi-finger grasp gets simulated rather than approximated → Tactile sensors and soft contact as first-class primitives → Numerical stability without the tight time-step limits explicit solvers force on you → Constraint-aware inverse kinematics running on the same optimization core as the forward dynamics Then the data layer. Put on a Quest 3, teleoperate the simulated hand with haptic feedback, and generate demonstration datasets without touching real hardware. They show a shape-sorting policy trained entirely in simulation and deployed zero-shot on a real robotic hand. Robot hands are getting good. Data for them isn't that fast. Meta is betting the cheapest way to collect contact-rich demonstrations is a headset people already own, pointed at a simulator instead of a game. 🔗 Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →