Driverless cars working together can speed up traffic by 35%

Driverless cars working together can speed up traffic by 35%
Cooperative driving. Credit: Sarah Collins (Cambridge University)

A fleet of driverless cars working together to keep traffic moving smoothly can improve overall traffic flow by at least 35 percent, researchers have shown.

The researchers, from the University of Cambridge, programmed a small fleet of miniature to drive on a multi-lane track and observed how the changed when one of the cars stopped.

When the cars were not driving cooperatively, any cars behind the stopped car had to stop or slow down and wait for a gap in the traffic, as would typically happen on a real road. A queue quickly formed behind the stopped car and overall traffic flow was slowed.

However, when the cars were communicating with each other and driving cooperatively, as soon as one car stopped in the inner lane, it sent a signal to all the other cars. Cars in the outer lane that were in immediate proximity of the stopped car slowed down slightly so that cars in the inner lane were able to quickly pass the stopped car without having to stop or slow down significantly.

Additionally, when a human-controlled driver was put on the 'road' with the and moved around the track in an aggressive manner, the other cars were able to give way to avoid the aggressive driver, improving safety.

The results, to be presented today at the International Conference on Robotics and Automation (ICRA) in Montréal, will be useful for studying how autonomous cars can communicate with each other, and with cars controlled by human drivers, on real roads in the future.

"Autonomous cars could fix a lot of different problems associated with driving in cities, but there needs to be a way for them to work together," said co-author Michael He, an undergraduate student at St John's College, who designed the algorithms for the experiment.

Driverless cars working together can speed up traffic by 35%
Credit: Sarah Collins (Cambridge University)

"If different automotive manufacturers are all developing their own autonomous cars with their own software, those cars all need to communicate with each other effectively," said co-author Nicholas Hyldmar, an undergraduate student at Downing College, who designed much of the hardware for the experiment.

The two students completed the work as part of an undergraduate research project in summer 2018, in the lab of Dr. Amanda Prorok from Cambridge's Department of Computer Science and Technology.

Many existing tests for multiple autonomous driverless cars are done digitally, or with scale models that are either too large or too expensive to carry out indoor experiments with fleets of cars.

Starting with inexpensive scale models of commercially-available vehicles with realistic steering systems, the Cambridge researchers adapted the cars with motion capture sensors and a Raspberry Pi, so that the cars could communicate via wifi.

They then adapted a lane-changing algorithm for autonomous cars to work with a fleet of cars. The original algorithm decides when a car should change lanes, based on whether it is safe to do so and whether changing lanes would help the car move through traffic more quickly. The adapted algorithm allows for cars to be packed more closely when changing lanes and adds a safety constraint to prevent crashes when speeds are low. A second algorithm allowed the cars to detect a projected car in front of it and make space.

They then tested the fleet in 'egocentric' and 'cooperative' driving modes, using both normal and aggressive driving behaviours, and observed how the fleet reacted to a stopped car. In the normal mode, cooperative driving improved traffic flow by 35% over egocentric driving, while for aggressive driving, the improvement was 45%. The researchers then tested how the fleet reacted to a single car controlled by a human via a joystick.

"Our design allows for a wide range of practical, low-cost experiments to be carried out on autonomous cars," said Prorok. "For autonomous cars to be safely used on real roads, we need to know how they will interact with each other to improve safety and flow."

In future work, the researchers plan to use the fleet to test multi-car systems in more complex scenarios including roads with more lanes, intersections and a wider range of vehicle types.


Explore further

Researchers develop a fleet of 16 miniature cars for cooperative driving experiments

More information: A Fleet of Miniature Cars for Experiments in Cooperative Driving, 2019 International Conference on Robotics and Automation (ICRA).
Citation: Driverless cars working together can speed up traffic by 35% (2019, May 20) retrieved 18 October 2019 from https://techxplore.com/news/2019-05-driverless-cars-traffic.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
761 shares

Feedback to editors

User comments

May 20, 2019
Once manufacturers reach this stage
All cars will be driverless
Then, there will not be aggressive drivers

May 20, 2019
As long as driverless cars are forced to drive at the speed limit they will make congestion much worse during rush hour conditions. Also once human drivers know that driverless will always yield to avoid following to close drivers will cut in front of them at will. Many highways have so many cars entering them during peak hours that stop and go results unless the cars per hour capacity is raised by drivers exceeding the speed limit.

May 20, 2019
MR166
If as you say
"As long as driverless cars are forced to drive at the speed limit they will make congestion much worse"
Being as you say, As long as driverless
how can driverless cars, be driven by humans, so as to speed and cut in
because when cars drive at 20mph
fuel consumption drops
cars drive at a steady 20mph
the queues dissipate
everyone is calmer
the cars can drive closer
on roads that have exceeded their capacity
A win, win situation

May 20, 2019
"cars drive at a steady 20mph
the queues dissipate
everyone is calmer
the cars can drive closer"

Gran lets say that a given road can handle 100 cars/minute at 20 MPH. That works our perfectly well during off peak hours when traffic is light. But what happens during rush hour when there are 200 cars/minute entering the same highway. Unless the cars speed up there will be terrible stop and go as more cars enter the road than exit. Think of the problem as an hourglass and it becomes clear.

May 20, 2019
This secret is to keep this traffic flowing

There reaches a point where there are too many cars on the road
As once 20mph is reached, no further gains are possible
Put any more cars on the road and you have gridlock
I do not have "no" in my vocabulary
But unfortunately, when gridlock is reached, the solution is no, no more cars

A car park attendant, when the car park is full to over capacity
This car park attendant turns these cars away

As in the case of roads exceeding their capacity
if there is nowhere for these cars to go but forward
at rush time these car are filtered through slowly, so even if the speed drops to 5mph
this traffic keeps flowing
as
this secret
is
to keep this traffic flowing
because
if you let it stop, gridlock ensues
But moving at 10mph gets you to your destination faster than gridlock

May 21, 2019
It would be interesting to see if an AI experiment generates coercive behavior on the part of the connected self-driving vehicles to frustrate the human driven cars and dissuade them from gaining the system. What if they all ganged up and just pushed the human driver off the road?

I can see where speed limits could become flexible (they have already in some areas) to safely push through as many cars per hour as possible. Really it make more sense to organize society's work routines to where commuting is spread out through the day. That would require a lot of buy-in from employers but if their employees are happier and better rested for not having to spend 2 hours a day in traffic they should be willing participants. If employees can live further away and buy/ rent cheaper homes then employers can pay them less. Minimizing travel lanes saves everyone a lot of unnecessary taxation and leaves more land for alternate transportation systems.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more