This post is also available in:
עברית (Hebrew)
Three engineers from the University of Glasgow designed and built an AI-based drone system to help search efforts for hikers lost in the wilderness.
While hiking around Scotland’s natural landscape is an extremely popular activity, such hiking can also be dangerous- hikers can get lost or injured and many find themselves in need of assistance. This is why Scottish emergency teams use both traditional and modern techniques to find those who are lost or need immediate assistance to evacuate.
In recent years searchers have begun to use drones because of their higher vantage point, which enables them to cover more land quicker than searching on foot. They also help spot signs and clues that searchers may not be able to see from the ground, like disturbed vegetation indicating the passage of hikers. The team of researchers reportedly considered all of these facts and wondered if adding AI to drone technology could improve the search for lost hikers.
According to Techxplore, the researchers created an AI model using data sets showing the paths taken by people who were lost and then found by search parties worldwide. They then added pertinent data about the hiker like their age, reason for hiking, whether they were alone, walking, or on horseback or another type of transport. They noted geographical information about the path taken by those who were lost and information about where they were found (rivers, streams, roads, or open ground). Lastly, they added data that was specific to Scotland’s geography.
The researchers ran the model millions of times (each representing a simulated search) until it narrowed down the most probable paths a lost hiker would take and instructed the drone to search those paths first.
When testing the system against approaches that are traditionally used to find lost hikers, the new approach found them way more—19% of the time as compared to 8–12% of the time. The researchers stated that the more data they add, the more accurate the system will be, and that it will eventually result in a tool that could be used to save lives.
