-

Mitsubishi Electric Develops Behavioral-analysis AI that Analyzes Manual Tasks Without Requiring Training Data

Reduces time for analyzing manual work on production sites by up to 99%

TOKYO--(BUSINESS WIRE)--Mitsubishi Electric Corporation (TOKYO: 6503) announced today that it has developed a behavioral-analysis AI that analyzes the efficiency of manual tasks performed on production sites in just a few minutes without requiring operators to prepare AI-training data in advance, by adopting a probabilistic generative model. This new addition to the company's Maisart AI lineup quickly analyzes videos of people performing repetitive tasks and then visualizes how tasks can be performed more efficiently for greater productivity.

This is believed to be the world's first application of a probabilistic generative model that modeled cyclical (repetitive) physical actions performed during factory work. The technology, first announced by Mitsubishi Electric on February 13, 2019, has been shown in tests to reduce the time conventionally required for work analysis by up to 99%.

Commercialization is targeted for the fiscal year ending in March 2026, or later.

The technology will be exhibited and demonstrated at IIFES 2024 (Innovative Industry Fair for E x E Solutions 2024), which will be held at Tokyo Big Sight from January 31.

For the full text, please visit: www.MitsubishiElectric.com/news/

Contacts

Customer Inquiries
Advanced Technology R&D Center
Mitsubishi Electric Corporation
Fax: +81-6-6497-7289
www.MitsubishiElectric.com/ssl/contact/company/rd/form.html
www.MitsubishiElectric.com/en/about/rd/index.html

Media Inquiries
Takeyoshi Komatsu
Public Relations Division
Mitsubishi Electric Corporation
Tel: +81-3-3218-2346
prd.gnews@nk.MitsubishiElectric.co.jp
www.MitsubishiElectric.com/news/

Mitsubishi Electric Corporation

TOKYO:6503

Release Versions

Contacts

Customer Inquiries
Advanced Technology R&D Center
Mitsubishi Electric Corporation
Fax: +81-6-6497-7289
www.MitsubishiElectric.com/ssl/contact/company/rd/form.html
www.MitsubishiElectric.com/en/about/rd/index.html

Media Inquiries
Takeyoshi Komatsu
Public Relations Division
Mitsubishi Electric Corporation
Tel: +81-3-3218-2346
prd.gnews@nk.MitsubishiElectric.co.jp
www.MitsubishiElectric.com/news/

More News From Mitsubishi Electric Corporation

Mitsubishi Electric Completes Full Acquisition of Nozomi Networks

TOKYO--(BUSINESS WIRE)--Mitsubishi Electric Corporation (TOKYO: 6503) announced today the completion of its acquisition of all outstanding shares of Nozomi Networks Inc., following the announcement on September 9, 2025 regarding its plan to make Nozomi a wholly-owned subsidiary. Overview of the Subsidiary Being Transferred Name Nozomi Networks Inc. Location Suite 3650, 575 Market St, San Francisco CA 94105 President & CEO Edgard Capdevielle Description of business Development and sales of O...

Mitsubishi Electric’s ME Innovation Fund Invests in Lucend, U.S. Startup Driving Data Center Operational Optimization

TOKYO--(BUSINESS WIRE)--Mitsubishi Electric Corporation (TOKYO: 6503) announced today that its ME Innovation Fund has invested in Lucend, a U.S.-based startup that provides an AI platform to optimize data center operations. This is the fund’s fourteenth investment to date. The rapid advancement of digitalization, including the widespread adoption of generative AI, has accelerated capital investment in data centers worldwide. Meanwhile, data center operators are being increasingly required to en...

Mitsubishi Electric Confirms World’s First Self-recovery Property of Highly Oriented Pyrolytic Graphite

TOKYO--(BUSINESS WIRE)--Mitsubishi Electric Corporation (TOKYO: 6503) announced today that it has confirmed the world’s first self-recovery property of highly oriented pyrolytic graphite (HOPG), a van der Waals (vdW)-layered material, in joint research with the Solid Mechanics Laboratory (Hirakata Laboratory) of Kyoto University's Graduate School of Engineering. This achievement is expected to extend the operational lifetime of micro electro mechanical systems (MEMS) by utilizing vdW-layered ma...
Back to Newsroom