AI based system helps drones navigate without GPS
In this blog, we are going to talk about, an AI based system helps drones navigate without GPS. Japanese researchers have developed a real-time drone-locating system that uses an onboard laser sensing device and artificial intelligence that enables it to operate even where GPS fails.
GPS navigation systems use stored map information for determining optimal route selection based on the shortest path algorithm. This technique is quite successful in getting you to where you want to go in a reasonable time and is fault-tolerant in the sense that it can automatically reroute in case of error.
One disadvantage of this approach is that it does not have any memory. It does not automatically remember the actual time it took you to get there nor does it learn from that experience and use the actual measurements to improve future route selection.
The accuracy of GPS, the current go-to location technology for drones, can drop considerably when the vehicle is flying between high-rise buildings and in mountains where signals from satellites tend to be randomly deflected or blocked so to change this approach AI based system helps drones navigate without GPS. Under the system, data on the geographical features from the onboard sensor is compared with existing data in a geographical database to determine the drone’s position.
The new system was developed to address this problem so a drone can remain on the right path in such areas.
Companies like Deepmind, before the millennials were born, people had to drive in their cars without any form of GPS navigation. If you wanted to go someplace new you used a paper map. DeepMind had to come up with a way to train AI to do, basically, the same thing. Around this time last year, the company developed a way to turn Google Street View imagery into a training environment for AI.