Your Delivery Drones Could Soon Be Taking the Bus to Save Both Time and Fuel
Researchers from Stanford University have come up with a way for drones to use public transportation to reimagine how packages could efficiently be delivered in cities, reported VentureBeat Should their attempts succeed, the process may reduce delivery congestion, save energy usage, and extend a drone's potential travel distance.
Let's face it we haven't seen many drone deliveries in urban centers as the vehicles are still not permitted to fly freely through cities. But scientists are arguing using bus and even metros can increase a drone’s range up to 360% beyond travel with flight alone.
"Our approach strives to minimize the maximum time to complete any delivery,” the team writes in a paper published this week at the online 2020 IEEE International Conference on Robotics and Automation (ICRA). “By combining the strengths of both, we can achieve significant commercial benefits and social impact.”
The Stanford system claims it could coordinate up to 200 drones delivering up to 5,000 packages. It boasts an AI network specially created for cities with up to 8,000 stops.
Trials have been conducted in San Francisco and Washington, D.C. But paper coauthor Shushman Choudhury told VentureBeat in an email that simulations do not take into account any physical infrastructure, rather they focus on open source data on bus stops and drone package depot locations. And the model takes a two-layered approach.
“First, the upper layer assigns drones to package delivery sequences with a near-optimal polynomial-time task allocation algorithm. Then the lower layer executes the allocation by periodically routing the fleet over the transit network while employing efficient bounded-suboptimal multi-agent pathfinding techniques tailored to our setting,” the paper reads.
The study comes out of the Stanford Intelligent Systems Laboratory (SISL) and Autonomous Systems Lab and is titled “Efficient Large-Scale Multi-Drone Delivery using Transit Networks." The research was nominated by ICRA conference organizers for the best multi-robot systems paper.