{"id":28073,"date":"2026-06-06T08:16:15","date_gmt":"2026-06-05T23:16:15","guid":{"rendered":"https:\/\/aireviewirush.com\/?p=28073"},"modified":"2026-06-06T08:16:15","modified_gmt":"2026-06-05T23:16:15","slug":"robotiq-releases-tsf-85-tactile-sensor-digital-twin-on-nvidia-isaac-sim","status":"publish","type":"post","link":"https:\/\/aireviewirush.com\/?p=28073","title":{"rendered":"Robotiq releases TSF-85 Tactile Sensor Digital Twin on NVIDIA Isaac Sim"},"content":{"rendered":"


\n<\/p>\n

\n

<\/p>\n

Additionally learn NVIDIA’s COMPUTEX protection<\/a>, the place Robotiq seems alongside the newest Isaac GR00T updates.<\/span><\/span><\/p>\n

<\/p>\n

\"TSF-85_IsaacSim_Gif-3\" <\/span><\/span><\/strong>\"\"<\/span><\/span><\/span><\/span><\/span><\/p>\n

Robotiq has launched the digital twin of its TSF-85 tactile sensor in NVIDIA Isaac Sim,\u00a0the primary industrial-grade tactile sensor digital twin transport on a industrial collaborative gripper. Tactile sensing guarantees to speed up robotics, however its adoption has been restricted by the dearth of knowledge from industry-ready {hardware} and correct simulations. Mannequin builders can now practice contact-rich manipulation insurance policies in simulation, then run them on the identical bodily sensor designed to function reliably on the manufacturing facility ground.<\/span><\/p>\n

Most tactile sensors depend on a deformable contact interface. The very property that offers them sensitivity can be what makes them tough to simulate. Deformable physique simulation\u00a0is technically demanding, and that’s one purpose correct tactile digital twins have lagged behind within the Bodily AI stack. The TSF-85 digital twin is constructed round that constraint. It generates artificial tactile maps by means of a customized Isaac Sim UI panel, visualizes them in actual time, runs knowledge era on the simulation refresh fee, and exports to HDF5 for downstream coaching pipelines.<\/span><\/p>\n


<\/span>\"\"<\/span><\/span> <\/span>\"TSF-85_Isaac-Sim-6\"<\/span><\/span><\/span><\/p>\n

\u00a0<\/p>\n

The TSF-85 digital twin was developed by the CoRo Lab (Laboratoire de commande et de robotique) at \u00c9cole de technologie sup\u00e9rieure (\u00c9TS) in Montr\u00e9al, a long-time analysis companion of Robotiq \u2014 a collaboration led by Affiliate Professor Jean-Philippe Roberge and doctoral researcher Berith Atemoztli De la Cruz S\u00e1nchez.<\/span><\/p>\n

The simulation technique behind the digital twin is documented in two peer-reviewed publications cited within the GitHub repo. The primary, printed in <\/span>Frontiers in Robotics and AI<\/span><\/u><\/span><\/a> <\/span>(2025), attracts on a dataset of 53,400 real-world tactile maps to coach, validate, and take a look at every simulation pipeline \u2014 attaining as much as 97% Structural Similarity Index Measure (SSIM) for the hyperelastic mannequin and 90% SSIM for the elastic mannequin on 12 unseen objects. <\/span>A companion paper at ICCRT 2025<\/span><\/u><\/a> releases an open dataset of 46,200 actual and artificial tactile samples, together with knowledge collected utilizing a 2F-85 Robotiq gripper and artificial samples generated in NVIDIA Isaac Lab.<\/span><\/p>\n

\u00a0<\/p>\n

\"TSF-85_IsaacSim_Gif-2\"<\/span><\/span>
<\/span>
<\/span><\/span><\/p>\n

Simulation accuracy issues, nevertheless it solely helps if the actual sensor stays steady over time. The TSF-85 has been examined by means of 2.3 million cycles at most gripper pressure, with no important variation within the output of the tactile alerts. This implies fashions skilled on its tactile knowledge can proceed to depend on constant alerts for edges, shapes, textures, and geometry even after demanding real-world use.<\/span><\/p>\n

Robotiq has been the go-to elements supplier for each educational analysis labs and industrial manufacturing for greater than a decade. That twin footprint is precisely the bridge Bodily AI requires: research-grade flexibility and industrial-grade reliability in the identical {hardware} platform.
<\/span><\/p>\n\n

The digital twin helps NVIDIA Isaac Sim 5.1<\/span> and is accessible now on GitHub: https:\/\/github.com\/Lab-CORO\/TSF-85<\/span><\/u><\/a>. Be taught extra about Robotiq’s bodily AI stack at https:\/\/robotiq.com\/physical-ai<\/span><\/a><\/span>
<\/p>\n\n

\n \"Talk <\/a>\n<\/div>\n

<\/span>\n <\/div>\n