TOKYO, August 21, 2025 - (JCN Newswire) — NEC Corporation (NEC; TSE: 6701) has developed technology that utilizes AI to enable safe, efficient autonomous control of robot movement even in complex environments with many obstacles. NEC’s in-house demonstrations of this technology have confirmed that a robot's travel time can be reduced by up to 50% when compared to conventional methods (*).

This new technology utilizes NEC's proprietary AI, which has been trained with the knowledge of multiple AIs, to generate optimal travel paths in real time. NEC aims to commercialize this technology by the end of fiscal 2026.

In recent years, automation through the introduction of robots has been progressing in large logistics warehouses and factories due to a decrease in labor forces and the need to improve productivity. However, in existing small- and medium-sized logistics warehouses, where it is difficult to prepare a dedicated environment for robots, and in retail stores, where aisles are narrow and display shelves and products are obstacles, it is difficult to secure paths for robots to move, which has hindered their introduction.

Furthermore, in robot control technology, there has been a trade-off between the time required to predict a path and the quality of the estimated path, and it takes time to estimate optimal routes. Therefore, robot control technology has not been practical in complex environments with many obstacles.

Features of the robot control technology developed by NEC to address these issues include the following.

Proprietary AI that generates optimal routes in real time

Traditionally, autonomous robot navigation in environments with numerous obstacles has relied on a combination of AI technologies and methods that generate paths based on predefined rules and procedures. However, there have been challenges in achieving optimal path generation that balances safety and efficiency. Additionally, while combining multiple AI systems can generate more appropriate paths, increasing the number of AI systems tends to prolong processing time and make real-time control more difficult. NEC has developed a proprietary AI that can learn the paths generated by multiple AI systems and generate multiple paths at once. This enables the generation of safe and efficient optimal paths even in environments with irregularly placed obstacles, thereby realizing real-time robot control.

50% reduction in robot travel time

In simulations on a 50-meter-long test course with randomly placed obstacles, robots using this technology confirmed that the time required to run through the course could be reduced by up to 50% compared to conventional methods. This makes it possible to roughly double the efficiency of robot movement, while ensuring safety and contributing to further improvements in work efficiency on site.

(*) Reinforcement Learning-based Dynamic Window Approach (RL-based DWA)

About NEC

The NEC Group leverages technology to create social value and promote a more sustainable world where everyone has the chance to reach their full potential. NEC Corporation was established in 1899. Today, the NEC Group’s approximately 110,000 employees utilize world-leading AI, security, and communications technologies to solve the most pressing needs of customers and society.For more information, please visit https://www.nec.com, and follow us on Instagram, Facebook, and LinkedIn.

About NEC Corporation

NEC Corporation has established itself as a leader in the integration of IT and network technologies while promoting the brand statement of “Orchestrating a brighter world.” NEC enables businesses and communities to adapt to rapid changes taking place in both society and the market as it provides for the social values of safety, security, fairness and efficiency to promote a more sustainable world where everyone has the chance to reach their full potential. For more information, visit NEC at https://www.nec.com.

Copyright © 2025 ACN Newswire. All rights reserved. A division of Asia Corporate News Network.