Cars saving pedestrians' lives?

Cars saving pedestrians' lives?

Summary: It's well known that many pedestrians and cyclists are victims of road accidents. This is why the EU-funded SAVE-U project was launched. This system combines sensors such as radar, vision and infrared camera, as well as sensor fusion and actuators to increase safety for pedestrians.

TOPICS: Emerging Tech

It's well known that many pedestrians and cyclists are victims of road accidents. In the European Union alone, there are over 9,000 deaths and 200,000 injured victims every year. This is why a 8-million euro and 3-year long project was launched in 2002 to build a sensing system which would save many lives. The SAVE-U system "combines sensors such as radar, vision and infrared camera, as well as sensor fusion and actuators to increase safety for pedestrians." Unfortunately for them, and even if prototype vehicles have already been successfully demonstrated, it will be a long time before such systems become a standard device in the average car.

The SAVE-U project (which stands for "Sensors and system Architecture for VulnerablE road Users protection") involved several large European research institutions or industrial companies, such as DaimlerChrysler or Volkswagen. Here is a short description given by IST Results.

The project, which officially ended in August, set out to develop an innovative pre-impact sensing platform that operates three different technologies of sensors simultaneously, and then fuses their data to protect cyclists and pedestrians under different weather and light conditions. The system comprises a radar network composed of several 24 GHz sensors working in parallel and an imaging system composed of passive infrared and colour video cameras.

Below is a photo of the Volkswagen demonstrator vehicle with its visible sensors mounted on the roof (Credit: IST -- Information Society Technologies).

The SAVE-U Volkswagen demonstrator vehicle

And here you can see the control panel and display inside a Mercedes-Benz E-class limousine demonstrator vehicle (Credit: IST -- Information Society Technologies).

Inside a SAVE-U Mercedes-Benz demonstrator vehicle

But does the system work?

A prototype vehicle incorporating the new system has already been successfully tested in the United Kingdom. Installed on the car are two cameras -- one video and one infrared -- as well as the radar device. The system calculates in a matter of seconds the movement of pedestrians within the 'capture zone,' which can be anything up to 30 metres away from the vehicle. From that point on, [the system can] identify any pedestrian or cyclist coming within the trajectory of the vehicle and after analysing the situation, warn the driver or apply automatic braking if there is a risk of collision.

In fact, vulnerable road users (VRUs) -- as they are called -- are protected in several ways.

The project partners opted to tackle the problem of protecting cyclists and pedestrians in three distinct stages: firstly, detection of VRUs at sufficient distance covering a relevant set of scenarios; second, definition and implementation of driver warning and vehicle control strategies to avoid, or at least minimise, the impact of a crash; and finally, defining vehicle-mounted VRU protection strategies in case the crash cannot be avoided.

But what is the future of such a system? Let's switch to an article from New Scientist, "Clever car keeps an eye on stray pedestrians" for the answer.

Traffic safety expert Chris Wright from Middlesex University, UK, says that the prototype could be a sign of dramatic things to come. He notes that many manufacturers are working on ever more sophisticated technologies to make cars more autonomous. These include systems to automatically steer a vehicle and maintain a safe distance from the vehicle ahead, as well as impact avoidance features.
"This has a very big future and it's much bigger than it might at first seem," Wright told New Scientist. "In 10 or 20 years cars will be robots."

Anyway, for a variety of legal and financial reasons, these kinds of systems will not be standard in your next car before many years, as explains Dr Marc-Michael Meinecke of Volkswagen to IST Results.

"For a start, the sensors have to be shrunk further in size and price to enable them to be integrated in serial cars. The sensor costs will also have to be decreased dramatically to have a chance to make the systems cost effective. And, last but not least, the software components are still not fulfilling the requirements for serial production. I think in the area of pedestrian protection these pedestrian recognition systems will be the main focus of research activities in coming years," he says.

In the mean time, you can read this informative and technical paper about the SAVE-U demonstrator vehicles (PDF format, 35 pages, 1.89 MB). The above illustrations were extracted from this document.

Sources: IST Results, January 12, 2006; Will Knight, New Scientist, January 12, 2006; and various web sites

You'll find related stories by following the links below.

Topic: Emerging Tech

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.


Log in or register to join the discussion
  • Quick thoughts

    If a vehicle with one of these systems may brake or swerve unexpectedly it might be necessary to only have vehicles which share the same system using the roads, so that if one is going to brake it can warn the others. Or there could be all sorts of ramifications following one of them changing its course, with vehicles with solely human drivers (or other automated systems) also involved. They mention the difficulty of establishing liability. Apart from liability for a collision not avoided, there could also liability for additional collisions.

    The task of making a system that will work well enough in every respect, everywhere, any time, should not be underestimated. E.g. across the whole of Europe, town and country, large roads and small, winter and summer, day and night?

    To the extent that the systems mainly warned about possible collisions, there might be an increase in the stress on drivers. A permanent, unceasing, back seat driver. But then airliner pilots are aided by warning buzzers and artificial voice warnings etc.

    I am sceptical that the AI will be good enough and fast enough for some time to come. E.g. as I drive along I often have "VRU?s" in my "trajectory", in the ordinary course of steering amongst them. This problem could be eased if the situation on the roads was simplified - e.g. by more segregation of cars etc, from cyclists and pedestrians. And by more standardisation of rules, and reduction in the number of permitted options in various situations. Making the roads more like railways. I get the impression that it is not easy (or totally possible) to automate even just railway safety. But a lot could be done. But all roads? All of the time? There would be a significant loss of flexibility. And the irony of having reduced the need for the technology. But we might have taken a big step towards automating all driving, which would free up a lot of time both as regards transporting ourselves, and goods. Perhaps have "automation" and "non-automation" zones.

    Any delay in achieving a working system may be in some ways be good because "Robot cars will eventually be much safer than those with human drivers," is very likely, given long enough. But if such systems are so capable we may well be into Asimov etc. territory, worrying about whether the robots will take over and seek to enslave or wipe us out. A high price, even for road safety.
  • RE: Cars saving pedestrians' lives?

    using these innovative <a href="">nissan parts</a> (and other car manufacturer parts) such as sensors should be implemented earlier, along with gps, both products are helpful in saving pedestrian and the driver's life also.