'Ghost Vehicles' Show How Autonomous Cars Can Save Energy

Mechanical engineering professor Ardalan Vahidi and his team at Clemson University  have found a way to help self-driving vehicles anticipate the behavior of other vehicles to reduce braking. Their research shows that the less a vehicle brakes, the less energy it wastes through heat and the more energy efficient it becomes. The algorithms the team has created resulted in energy savings ranging from 8-23%. The team tested its algorithms on two separate autonomous cars, a gas-powered Mazda and an electric Nissan, both connected to the same wireless network, allowing them to send and receive data, such as speed and heading. The researchers used computer simulations to create “ghost vehicles" in front of and behind the Mazda and Nissan, making them think they were in traffic. The Mazda and Nissan saved more energy when following autonomous ghost vehicles than the ghost vehicles driven by simulated human drivers.

Transcript

00:00:02 I just noticed that there are very few universities or doing experimental research and autonomous cars real autonomous cars full-size and that report mentions us in particular Clemson project on energy-efficient driving of autonomous course and I believe that's significant in in a crowded domain you will see two cars that they're steering accelerator and pedaled and braking

00:00:29 pedal positions are automated and they would drive on a test track using control algorithms that we have devised in order to save energy in them while they're driving on a test track you will see these two cars but you will you will not see a bunch of ghost cars that surrounds them those are simulated cars the idea is that by having simulated cars around

00:00:53 here we can test very difficult traffic situations in a safe manner the big pictures that we think with autonomous and connected cars that talk to each other into the infrastructure we have more opportunities to save energy in particularly connectivity you have more information from the future events down the road if alex is coming out or when driving among other vehicles you

00:01:18 can have a better prediction of what's going to happen in the future so you can adjust your velocity for example more anticipated li and reduce your braking events one of the things that was interesting and first we thought maybe we make a mistake is that we saw not only their automated cars will benefit but the human driven cars that are surrounding them see a benefit in energy

00:01:40 efficiency in particular in high traffic volumes we see that is a lot and then we found the reason that a reason is that that automated vehicles by driving more energy efficiently pub smooth and harmonized the traffic behind them we used stop and go behavior phantom traffic jams as they say and as a result their energy efficiency entire traffic flow will improve

00:02:07 we expect to continue research but people on the way we also contribute to the state of art of automated driving [Music] you