Expanding collaboration with NVIDIA to strengthen agent-based AI and robotics.
SOURCE: MOOMOO.COM
JUL 16, 2026
Tokyo Electron Limited (TEL; Minato-ku, Tokyo; President: Toshiki Kawai) is advancing a collaboration with NVIDIA as part of its solution development initiatives involving agent-based AI and robotics. Specifically, within TEL’s Digital Transformation (DX) solution concept “Epsira,” the company will leverage the NVIDIA Agent Toolkit—which includes the NVIDIA NeMo, NVIDIA NIM, and NVIDIA NemoClaw blueprints—as well as NVIDIA Isaac, an open robotics development platform. Utilizing the Isaac platform enables integration with NVIDIA Omniverse libraries (for simulation), allowing designs to be implemented directly into digital twins. While robot maintenance often requires diverse tool configurations, the use of digital twins significantly reduces the time needed for robot training and performance optimization. Regarding AI agents, NeMo accelerates agent training, fine-tuning, and evaluation, while NemoClaw simplifies deployment and enhances the security of agent operations.
TEL’s “Epsira” aims to enhance customer productivity by improving field productivity, yield, and equipment utilization rates. It delivers technologies such as AI-driven MTBWC (Mean Time Between Wet Cleaning) extension analysis, high-precision robotic maintenance, and troubleshooting analytics, thereby enabling substantial reductions in scheduled maintenance. Through this DX infrastructure, customers can harness data to achieve higher productivity and skill-free operation, minimize variability, maximize equipment stability, and ultimately move toward autonomous equipment operation. Through such close collaboration, TEL contributes to the advancement of a more promising society by combining cutting-edge technology with reliable service.
Keiichi Matsushima, Executive Officer and General Manager of Corporate Product Development Division at TEL, stated, “We are delighted that our collaboration with NVIDIA, a global leader in the AI era, has deepened further. This advancement will significantly broaden the applicability of our Epsira program. Through robotic maintenance and AI-powered troubleshooting analytics, our customers’ manufacturing capabilities will be strengthened, leading to even greater productivity.”
Amit Goel, Senior Director of Robotics and Edge AI Ecosystem at NVIDIA, commented, “Semiconductor manufacturing is entering a new era of automation. Production environments in semiconductor fabs are becoming increasingly complex across all dimensions, but robotics offer significant potential to improve uptime, precision, and resilience. TEL will leverage NVIDIA’s agent-based AI and physical AI models and frameworks to advance robotic maintenance, AI-driven troubleshooting, and further intelligentization of fab operations.”
For more information about Epsira, please visit .
For details on NVIDIA Isaac and NVIDIA Omniverse, please visit (in English) and .
Epsira is a registered trademark or trademark of the Tokyo Electron Group in Japan and other countries.
LATEST NEWS
Machine Learning
Machine Learning Identifies Predictors of Weight Loss in Adolescents With Obesity
AUG 15, 2026
WHAT'S TRENDING
Data Science
5 Imaginative Data Science Projects That Can Make Your Portfolio Stand Out
OCT 05, 2022
SOURCE: CXOTODAY.COM
AUG 05, 2026
SOURCE: ASISONLINE.ORG
AUG 01, 2026
SOURCE: YNETNEWS.COM
JUL 26, 2026
SOURCE: JAPANTIMES.CO.JP
JUL 16, 2026
SOURCE: ERP.TODAY
JUL 08, 2026