AI-powered drone system reduces inspection time from 2 hours to 17 minutes, offering a safer, faster solution for subterranean infrastructure projects
by DRONELIFE Staff Writer Ian J. McNabb
This article published in collaboration with JUIDA, the Japanese UAS Industrial Development Association.
Japanese firm Toda Construction Co. has developed an innovative new application for UAVs- not in the sky, but deep under the ground. Toda, in collaboration with Spiral Co. and GreenBee Co., recently announced that they had successfully tested their AI-driven face analysis technology that used drones to analyze recently dug tunnel faces, a process that usually involves a painstaking analysis by teams of engineers. Toda hopes that its autonomous drone system will reduce personnel needs while making previously time-consuming inspections faster and easier, aiding in large project management and shortening timelines.
The overall system included a dust-proof charging canopy for the drone unit (a necessary addition in the debris-filled mountain tunnels the creators envision the system being deployed in), alongside a custom software solution to make the whole process both autonomous and simple to implement. The drone system features autonomous obstacle avoidance when it goes to take photos of the rock face, ensuring that it doesn’t run into construction vehicles, workers, or debris while it completes its missions.
Toda’s press release said, “In our mountain tunnel construction, we verified the effectiveness of a series of systems, including flight stability, image acquisition, and AI-powered evaluation, using an autonomous flight system equipped with an ‘obstacle avoidance function’ and ‘automatic detection function of cutting edge’. As a result, it was confirmed that the AI can select an appropriate photo for cutting-edge observation by selecting an appropriate photograph from hundreds of cutter photos, allowing AI to take off from the charging port autonomously, avoiding obstacles such as heavy machinery, shooting in the tunnel, and returning to the right position after shooting the cut area, and even allowing them to operate completely automatically until landing at the charging port.”
The total time to complete a face survey using engineers was around 2 hours. Use of the drone-based system reduced total inspection times down to 17 minutes, an impressive advancement that might make UAVs an important part of large underground infrastructure projects in future.
More information on the system is available here (in Japanese).
Want DRONELIFE news delivered to your inbox every weekday? Sign up here.
Read more:
- Japan’s Drone Industry Takes Flight: JUIDA’s New Model-Specific Pilot Licensure Program
- Japan’s Military Teams Up with Drone Industry for Disaster Response Training
- New Japanese Agriculture Spray Drone: 1.5 Hectares on 1 Battery
Miriam McNabb is the Editor-in-Chief of DRONELIFE and CEO of JobForDrones, a professional drone services marketplace, and a fascinated observer of the emerging drone industry and the regulatory environment for drones. Miriam has penned over 3,000 articles focused on the commercial drone space and is an international speaker and recognized figure in the industry. Miriam has a degree from the University of Chicago and over 20 years of experience in high tech sales and marketing for new technologies.
For drone industry consulting or writing, Email Miriam.
TWITTER:@spaldingbarker
Subscribe to DroneLife here.
Loving the direction Artificial intelligence is going. Great post!