Swarm intelligence for autonomous cars explained

By Ash Westerman, 27 Oct 2016 Car Advice

Buying new? We'll match you to the lowest dealer quote, get the best price for your trade-in and the lowest rate finance. Save thousands. Get started here.
Buying new? Get the lowest dealer quote, best price for your trade-in and lowest rate finance. Save thousands. Start here.
cars driving in highway traffic

Car-to-x services and swarm intelligence are poised to reshape our motoring lives

Autonomous cars may be our motoring future, but there will be some key steps toward this transition that will impact our regular old driver-in-charge motoring world almost immediately.

One term you’ll start hearing much more frequently is ‘swarm intelligence’. Now, if this makes you think of bees around a hive, then well done, because this is precisely the phenomenon in nature that inspired the term. Basically it involves the sharing and use of complex information in a large group. The first practical application of this will come as premium manufacturers add so called ‘car-to-x’ services to cars in certain markets late this year.

The first applications involve traffic sign information and hazard information. With car-to-x, vehicles equipped with ‘e-SIMs’ – dedicated, embedded SIM cards handling all vehicle communications –  can exchange relevant traffic information in real time via the mobile-phone network. The benefits of car-to-x communication are clear: improved road safety, reduced congestion, a cut in delays, and smoother, more economical motoring. It’s also a fundamental element of future models capable of the aforementioned autonomous driving.

The new online services of traffic sign information and hazard information are available for specific Audi, BMW, and Mercedes-Benz models. In Europe, cars equipped with e-SIMS have been gathering information since the middle of this year, and it has been used to steadily build up a database. The new traffic-sign information service expands on the traffic sign information stored in the navigation module and takes the camera-based recognition of traffic signs to new levels of effectiveness. The on-board traffic sign recognition identifies temporary speed limits, for example, and reports them to a cloud-based server. Once a sufficient number of cars have sent the identical message, it’s considered as ‘verified’ and can be sent out to other drivers.

Mazda2 in traffic

SHARING HAZARD WARNINGS = LESS DANGER

The second production-ready car-to-x communication application is the new hazard information service. Here, cars networked over the cloud server warn one another of hazards on the road: accidents and breakdowns, slippery road surfaces, or impaired visibility due to fog. The system evaluates multiple parameters to verify cloud-based hazard information: for example, poor visibility ascertained via data from rain and light sensors, as well as the operating mode of the windscreen wipers. An accident or breakdown is reported via an emergency call being placed by the car’s onboard system or an airbag activation. Only after information about a hazard site is verified does the system actually report the hazard to the cloud in order to warn other drivers, who know about the hazard before arriving on the scene, or have sufficient warning to choose a new route, as suggested by the navigation.

THE ROCK-STAR PARK, EVERY TIME

Ever driven around a congested urban centre, searching fruitlessly for an on-street parking spot, swearing so hard you nearly cracked the windscreen?

Cars equipped with car-to-x technology are poised to solve the problem. Suitable equipped vehicles automatically report when they enter and leave a parking spot via the cloud-based servers. The system identifies parking manoeuvres based on a number of parameters, such as the quickly changing position of the gear selector, steering angles and speed. As a car leaves, you’re alerted of this nearby vacancy.

In the future, predictive parking tech will also be able use the information from the ultrasound sensors or the car’s cameras to recognise free parking spaces while driving. It will calculate the number of free parking spaces on the side of the road based on statistical models that consider factors such as the time of day, and be able to show drivers the probability of finding a free parking spot, saving valuable time, and potentially, relationships.