A team at MIT’s Computer Science and Artificial Intelligence Lab has released a paper showcasing a new method of transport. The drone/car hybrid prototypes use “path-planning” algorithms to choose between flight and driving depending on the situation. The concept offers a way to improve travel distance and efficiency in an urban context.
Inspiration from the natural world
MIT’s latest technology is an attempt to recreate something we are all familiar with from the natural world: the ability – shared by many birds and insects – to move both along the ground and in the air.
Programming robots to move with that level of versatility could have huge implications for future transport, search and rescue systems and much more besides.
MIT’s tiny prototypes have been scaled down for testing in a miniature urban environment. As well as switching between flight and drive as required, they work as part of a system, or swarm, enabling a constant awareness of each other’s movements.
“The ability to both fly and drive is useful in environments with a lot of barriers, since you can fly over ground obstacles and drive under overhead obstacles,” said PhD student Brandon Araki, lead author of the MIT paper.
“Normal drones can’t maneuver on the ground at all. A drone with wheels is much more mobile while having only a slight reduction in flying time.”
To test the technology in a real-world scenario, CSAIL researchers developed eight miniature quadcopter drones with ground-based drive systems. This allowed them to move through a tiny city, on wheels or flying depending on the circumstance. The maximum driving distance was 252 meters. Flying took more energy; the robots had a maximum flight distance of 90 meters.
The versatility offered by a dual transport system could be invaluable as autonomous drones are increasingly adopted in industries such as search and rescue, agriculture and inspection.
Fast, traffic-free transport
CSAIL Director Daniela Rus believes the technology offers a more sophisticated vision of future transport than simply “putting wings on cars.”
“As we begin to develop planning and control algorithms for flying cars, we are encouraged by the possibility of creating robots with these capabilities at small scale,” Rus says.
The most complex aspect of the technology is arguably ensuring that the vehicles don’t collide. “While there are obviously still big challenges to scaling up to vehicles that could actually transport humans, we are inspired by the potential of a future in which flying cars could offer us fast, traffic-free transportation.”