There aren’t flying cars just yet, but a team of researchers at MIT has developed software that can optimize routes for vehicles that both drive on roads and soar in the air.

Computer Science and Artificial Intelligence Laboratory Director Daniela Rus, graduate student Brandon Araki, and their team used eight small drones to test the system, which directed the drones around a playmat featuring two ground routes with an obstacle between them. The software decides when it would be most optimal to switch the drones from ground mode to flying mode based on the travel time saved and the battery life required. The drones may be small, but they also have their own interesting development: wheels, which allow that much more efficient type of travel on land.

“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 said in a statement. “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.”