GIST develops AI drone technology that lands while avoiding obstacles

-

Concept diagram of drone technology that finds a secure place and lands mechanically (Photo = GIST)

Gwangju Institute of Science and Technology (President Lim Ki-cheol) announced on the twenty first that Professor Lee Jong-ho's research team within the Department of Mechanical Engineering developed a drone technology that uses image information captured by a camera and distance information measured by a LiDAR sensor to search out a secure place by itself and land mechanically. revealed.

Images captured by cameras are divided into areas where landings could be made and areas where landings can’t be made, reminiscent of roads, grass, and water, using deep learning technology.

Since the drone may fall if it lands on a tilted ground, the research team installed a LiDAR sensor that measures distance on the drone's two-axis gimbal. Presently, the drone can measure the peak of the bottom and calculate the slope of the bottom based on this to search out a flat surface that is not going to fall when landing.

The research team confirmed that the drone could land safely by itself through experiments in quite a lot of environments, including natural environments with trees, grass, water, and hills, in addition to rooftops of buildings with obstacles in the town, bushes, ponds, and sloping places.

Drone that automatically avoids water and lands in a safe place (Photo = GIST)
Drone that mechanically avoids water and lands in a secure place (Photo = GIST)

The outcomes of this research could be utilized in the long run smart mobility unmanned aerial vehicle industry, including drone delivery that lands by itself in various places and environments.

Particularly, it is anticipated to beat geographical limitations and enable missions in various environments, thereby reducing transportation costs and stopping safety accidents.

Professor Jong-ho Lee said, “Using this research result, secure landing of unmanned aerial vehicles reminiscent of drones is feasible even without prior details about the encompassing environment.” He added, “Future smart mobility unmanned aerial vehicles will likely be utilized in various application fields reminiscent of drone delivery, national defense, and public safety.” “It is anticipated that it can be utilized in industry,” he said.

This research, led by Professor Jong-ho Lee and conducted by Dr. Jeong-geun Lim as the primary creator, was published online on March 13, 2024, in 'IEEE/ASME Transcations on Mechatronics', a wonderful journal within the engineering and mechanical fields.

Reporter Oh Deok-hwan odh@aitimes.com

ASK ANA

What are your thoughts on this topic?
Let us know in the comments below.

0 0 votes
Article Rating
guest
0 Comments
Oldest
Newest Most Voted
Inline Feedbacks
View all comments

Share this article

Recent posts

0
Would love your thoughts, please comment.x
()
x