-

Mitsubishi Electric and Inria Commence Joint Technology Development to Ensure AI Trustworthiness Using Formal Methods

Will deliver next-generation AI technology and help to realize a society where AI can be used with peace of mind

TOKYO--(BUSINESS WIRE)--Mitsubishi Electric Corporation and Inria, France’s National Institute for Research in Digital Science and Technology (Institut national de recherche en sciences et technologies du numérique), announced today that they have launched a joint research project titled “Formal Reasoning applied to AI for Methodological Engineering” (FRAIME) with the aim of realizing trustworthy AI systems. This project will be one part of Inria’s DÉFI, a large-scale industry-academia collaboration program, to achieve trustworthy AI systems and establish next-generation AI technology by integrating Formal Methods technologies, a mathematical approach, with AI technologies.

With the rapid development and global spread of AI, companies that develop and provide AI systems are required to manage risks appropriately. In particular, systems that require a high level of safety, such as infrastructure systems and cybersecurity systems, can cause significant damage in the event of any malfunction, making it extremely important to guarantee the reliability of AI output. In theory, AI reliability assessment requires exhaustive testing, thoroughly verifying output results for all possible inputs. However, it is a challenging task that takes an enormous amount of time and incurs huge cost.

Mitsubishi Electric’s European subsidiary, Mitsubishi Electric R&D Centre Europe, and Inria have been collaborating through joint research on advanced verification technologies utilizing Formal Methods since 2015. This cutting-edge initiative is aimed at developing a technology that theoretically verifies the reliability of AI output by combining Formal Methods technologies with AI technologies such as large-scale language models, leveraging the expertise of both parties and building on their long-standing track record and trust-based relationship. The goal is to further expand the scope of AI application towards systems that require high levels of trustworthiness.

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

Contacts

Mitsubishi Electric Corporation
Public Relations Department
prd.gnews@nk.MitsubishiElectric.co.jp

National Institute for Research in Digital Science and Technology
nathalie.lacaux@inria.fr

Customer Inquiries
Mitsubishi Electric R&D Centre Europe
1 Allée de Beaulieu, 35700 Rennes, France
info@fr.merce.mee.com

National Institute for Research in Digital Science and Technology
nathalie.lacaux@inria.fr

Mitsubishi Electric Corporation

TOKYO:6503

Release Versions

Contacts

Mitsubishi Electric Corporation
Public Relations Department
prd.gnews@nk.MitsubishiElectric.co.jp

National Institute for Research in Digital Science and Technology
nathalie.lacaux@inria.fr

Customer Inquiries
Mitsubishi Electric R&D Centre Europe
1 Allée de Beaulieu, 35700 Rennes, France
info@fr.merce.mee.com

National Institute for Research in Digital Science and Technology
nathalie.lacaux@inria.fr

More News From Mitsubishi Electric Corporation

Mitsubishi Electric Announces Dividend for Fiscal 2026 (April 1, 2025 – March 31, 2026) and Dividend Forecast for Fiscal 2027 (April 1, 2026 – March 31, 2027)

TOKYO--(BUSINESS WIRE)--Mitsubishi Electric Corporation (TOKYO: 6503) announced today that the Board of Directors has resolved to pay a year-end dividend of 30 yen per share for fiscal 2026, as of the record date of March 31, 2026. Mitsubishi Electric has a basic policy in dividend payment of approximately 3% in adjusted DOE1 to ensure consistency from the perspective of providing appropriate returns to shareholders in line with the level of Mitsubishi Electric Corporation stockholders’ equity...

Mitsubishi Electric Technology Estimates Organic Carbon in Farmland Using Optical Measurements and Soil Organic Carbon Dynamics Models

TOKYO--(BUSINESS WIRE)--Mitsubishi Electric Corporation (TOKYO: 6503) announced today that it has developed a technology to accurately estimate the amount of soil organic carbon (SOC) in agricultural land by combining optical measurements with two SOC dynamic models: a root biomass model1 and a microbially mediated organic matter decomposition model.2 The new technology will enable the efficient, low-cost, large-scale monitoring of SOC by eliminating the need for soil sampling and laboratory ch...

Mitsubishi Electric Announces Consolidated Financial Results for Fiscal 2026

TOKYO--(BUSINESS WIRE)--Mitsubishi Electric Corporation (TOKYO: 6503) announced today its consolidated financial results for fiscal 2026 (April 1, 2025 - March 31, 2026). The full document on Mitsubishi Electric’s financial results can be viewed at the following link: www.MitsubishiElectric.com/en/pr/ Consolidated Financial Results Revenue:   5,894.7   billion yen   (7% increase year-on-year) Operating profit:   433.0   billion yen   (11% increase year-on-year) Profit before income taxes:   526...
Back to Newsroom