Automotive

Volkswagen leads "AdaptIVe" research project into autonomous cars

View 2 Images
AdaptIVe will look at the best way for drivers and autonomous driving systems to interact
AdaptIVe will look at the best way for drivers and autonomous driving systems to interact

There’s more to putting self-driving cars on the road than technology and algorithms. There’s also some very basic thinking that needs to be done as to what autonomous vehicles are and what their implications are. Towards this end, Volkswagen has announced the start of Automated Driving Applications & Technologies for Intelligent Vehicles (AdaptIVe); a 42-month project by a consortium of 29 partners, including ten major automotive manufacturers, aimed at developing more efficient and safer autonomous systems.

The problem with autonomous vehicles is not just that they’re incredibly advanced pieces of hardware, or that they have to operate in the chaotic environment of the streets, they also have to interact with the driver. That wouldn't be much of an issue if it involved a switch that you flip between manual and automatic, but Volkswagen points out that autonomous driving involves several possible stages, plus the swap over point between mainly manual drive and mainly automatic drive. These vary from low-speed chores, such as parking assist, to taking over full control while driving at high speed on the motorway.

According to Volkswagen, the simplest and currently the most widely used stage is assisted driving. This is where the driver retains permanent control over the car with the automated system helping for tasks such as parking or reversing. The next level up is the partly automated stage, where the system monitors the driver and takes over only when needed, such as applying brakes when a pedestrian steps into the road, or preventing a dangerous lane change.

In the highly automated stage, the system takes over the actual driving, but the driver still has to remain alert because he has to be ready to reclaim control when requested. Then there’s the highest stage, which it fully automated. In this, the system drives the car and if the driver fails to retake control when requested, the system carries on by itself.

Using seven cars and a lorry, the AdaptIVe project is designed to study the different combinations of these stages. The idea is to work out the best way for the driver and the automated system to interact using advanced sensors and cooperative vehicle technologies. In this way, the system will be able to dynamically react depending on the situation and the autonomous driving stage.

The goals of AdaptIVe are to develop and test new autonomous functions for cars and trucks, investigate partially automated and highly automated driving, and study autonomous driving in cities where close-quarter driving is the norm. In addition, Volkswagen says that the project will look into the legal implications of autonomous systems for both manufacturers and drivers, with a special emphasis on liability and road laws.

"This complex field of research will not only utilize onboard sensors, but also cooperative elements such as vehicle-to-vehicle and vehicle-to-infrastructure communication," says Professor Jürgen Leohold, Executive Director of Volkswagen Group Research. "Therefore, I am glad that most European automotive companies are cooperating in this pre-competitive field to create new solutions for automated driving."

Source: Volkswagen

  • Facebook
  • Twitter
  • Flipboard
  • LinkedIn
3 comments
Mel Tisdale
There is no way that the highly automated stage will ever be adopted unless it operates in conditions where the only other road users will be driving vehicles operating under the same conditions and with no pedestrians within striking distance. We have to remember the designers' mantra: if it can happen, it will happen.
Furthermore, in the highly automated stage there still has to be a 'driver' who will be ultimately responsible for any accidents that the vehicle is involved in. With little or nothing to do, a tired driver will tend to fall asleep at the wheel. Enough said?
Goddard
@Mel not really. The truth of the matter is a computer can react faster then a human can. A pedestrian that either jumps, or walks into the road can be tested for over and over again under different situations. The system can be further improved by putting digital receivers/transmitters at cross-walks. With the help of GPS, Computer Vision, Infrared, and tons of other technologies and quality manufacturing processes/standards an autonomous car is absolutely possible with today's technology and after the initial investment it should show up in mid-range cars within the next 8 years if not 5. I think the largest concern I think anyone would have is that these vehicles react so quickly and so precisely that people that can't afford, or don't have one of these cars might not react as fast as the driver in front of them haha.
Dr_Bill_Marshall
I think this research project shows just how committed the automotive industry is to the task of developing a publicly acceptable driver-less car. They wouldn't bother if they believed it would be scuppered by a requirement for zero-risk. The argument may well become: 'Why did we ever think a human brain was superior to a computer in controlling complex machinery?'