Lost hikers could now be saved by drones
Drones are becoming ever more prevalent in our daily lives, even if you don’t quite realise it. As technology, artificial intelligence and the algorithms that power them improves, so too do the capabilities of these magnificent flying machines. However, before we inevitably take robotics advancement too far and go full Terminator, there are a lot of noble applications these technological advancements can be used for.
Of these, the most recent comes from researchers at MIT who have been redeveloping drones for successful search and rescue missions in thickly forested environments. To do this, the team had to redefine how drones navigate when under a dense canopy of trees.
READ NEXT: How will drones reshape our cities?
The process of search and rescue over thickly wooded areas has remained a difficult task for humans. From the sky it’s nearly impossible to see through the treetops; from the ground, GPS signals aren’t completely reliable and the operational demand on humans is great. Recently the use of autonomous drones has been discussed, however until now the issue of GPS signal has befallen them, too. What’s more, current drone programming limitations means distinguishing trees from one another is troublesome – to a drone, all trees are similarly circular, and this gives them a headache.
MIT researchers have developed a solution, though. By using the same laser systems found in driverless cars, the drones move around scanning the area before them, allowing them to create a 3D map of the vicinity they’re searching. The research team then created a new algorithm for the drones, allowing them to view the spatial data they’ve retrieved in terms of recognisable patterns. Individually, trees are tricky characters for the drones to understand, but a single cluster of trees will project a pattern different to another cluster, and the algorithm allows the drone to interpret this and gain a bearing from it.
These developments mean the drones are now able to move from place to place while interpreting their surroundings. This means they no longer run the risk of going in circles around the same tree.
These rescue drones are also able to work simultaneously, sending information back to an off-board ground station which fuses all of the data together, producing a readable map.
The final piece to the puzzle is equipping these drones with an object detection system to help identify missing hikers. This system would allow the drones to tag a missing person’s location, sending it back to the off-board ground station and pinning it to the overall map. Thereafter, human teams can begin to plan an effective rescue mission by using the location of the missing person alongside an accurate terrain map produced by the drone.
There’s still a little way to go with the object detection system, and the MIT team would prefer if drones needn’t rely on an off-board ground station – instead hoping for immediate communication and mapping between drones in real time. But, so far, the researchers have successfully taken the necessary steps towards a revolutionised search and rescue procedure – and possibly the postponement of judgement day.