Hands-off auto drive BMW

Google has been dabbling with driverless cars and in the cold climes of Scandinavia Volvo has been playing with car 'platooning'. Now BMW has shown off a new auto-drive system travelling down the busy A9 motorway from Munich, with a somewhat smug looking ‘driver’ relaxing, hands off, behind the 5 Series sedan's steering wheel.

The man behind the unused wheel is Dr. Nico Kämpchen, Project Manager of Highly Automated Driving at BMW Group Research and Technology, and his confidence in letting the car negotiate the heavy traffic by itself comes from having already completed some 5000 test kilometres utilising the technology involved.

Much of this testing was performed on the race track as part of the development of BMW TrackTrainer program, the aim of which was to provide electronic co-pilots armed with super accurate GPS data and predefined race lines to aid in the further development of systems such as adaptive cruise control and Emergency Stop Assist.  The constant comparison of GPS and video data with the digital maps and internal vehicle data was used to automatically guide a vehicle around the legendary North Loop of the Nürburgring on 21 October 2009. Then on 25 May 2011, the second generation version of the BMW TrackTrainer performed a similar feat at the Laguna Seca Raceway in California, demonstrating that fast and dynamic automated driving is indeed possible.

The next step was to take to the motorways.  BMW combined intelligent software algorithms with a range of sensors to further research into advanced driver assistance systems.  Redundant fusion of various sensor technologies such as lidar (visible Light Detection and Ranging), radar, ultra sound and video cameras monitor the environment around the automobile.   Redundant does not mean “superfluous”. To ensure that the vehicle situation is precisely assessed, at least two different measurement methods must be used in every direction.  In this way the developers at BMW Group Research and Technology can be sure that a potential weakness in one method is counterbalanced by the strength of the other method. 

Negotiating the challenges of a car-infested motorway is somewhat more challenging than controlling a single vehicle on a closed race track. 

“This is an entirely new situation and experience for the driver – it is a strange feeling handing over complete control of the car to an autonomous system,” says Kämpchen. “But after a few minutes of experiencing the smooth, sovereign and safe driving style, drivers and passengers begin to relax somewhat and trust the independent system. Nevertheless, the driver is still responsible for the situation at all times and must constantly keep an eye on traffic and the surroundings.”

To ensure that the automated research vehicle functions smoothly and with agility in real traffic, the car must be endowed with strategies to react appropriately in daily traffic situations. The basis for these strategies is comprised of two parts: first, pinpointing the position of the vehicle in its own lane is essential and second, the car must be able to clearly recognize all vehicles and objects in its immediate surroundings.

By accessing digital maps, the camera and the localisation data of the extremely precise GPS, the automated vehicle prototype can determine its location in its own lane, and it also receives exact information about the characteristics of the route ahead, including the number of lanes that section of the motorway has. This information is supplemented by data from the forward-looking camera integrated in the lane departure warning system. Objects in front of the vehicle are detected by the radar sensors of the adaptive cruise control system with the Stop&Go function and by a laser scanner as well. The same is true for objects at the sides or rear of the vehicle.

The system can autonomously control acceleration and breaking, and most importantly assess and react to other vehicles in the vicinity, allowing merging and overtaking with adequate safety distance and the ability to change lanes when necessary. Performance wise the system has been tested up to 130km/h, however, via both data and reading real-world signs, the system also obeys all speed and passing restriction zones along the way.

So is it just a matter of time before control is removed entirely from the driver? Not for the foreseeable future was the theme stressed by local BMW representatives when talking about how this technology will be integrated into production line vehicles. 

“Our motto at BMW remains ‘Sheer driving pleasure’, and we would never take away the simple fun of driving a vehicle from our customers, we would never seek to make the driver redundant”.

This research is aimed at boosting the level of driver assistance systems, enhancing features such as Emergency Stop Assistance where the car will, via various means and sensors, detect a problem with the driver, such as loss of consciousness and begin to safely slow the car, steer around bends and appropriately avoid traffic to get the car to stop on the side of the road, with hazard lights flashing.

BMW’s stated intention is to design car systems to mimic the human body, taking information from a number of sources (sensors as senses) to advise intelligent options for the driver. BMW has also uploaded an explanatory video to YouTube for viewing.

Read the latest news and reviews on your mobile, iPhone or PDA at carsales' mobile site...