Ā
|
The project started about five years ago and was funded by the Defense Advanced Research Projects Agency (DARPA). Since its launch, the augmented cognition research team has conducted actual experiments on European roadways. Kevin Dixon, Principal Investigator on the team, said they utilized data that already existed on the carās computer to collect a wide range of physical data such as brake pedal force, acceleration, steering wheel angle, and turn signaling. He said that specialized sensors were embedded in the carās systems, including a pressure sensitive chair and an ultrasonic six-degree-of freedom head tracking system that measured the driverās posture.
In one of the experiments, five drivers wore caps with electrodes connected to an electroencephalogram (EEG) that monitored their brainwave patterns. The researchers collected information of the electrical activity of the driversā brains in various simulations of driving situations, or āclassifiersā ā for example, approaching a slow-moving vehicle or changing lanes. The system was able to detect the level of stress and difficulty of a task the driver was attempting and modified the tasks and/or environment to improve specified performance parameters accordingly.
Ā
|
āThe beauty of this is that we arenāt doing anything new or different to the car,ā Dixon says. āAll the software that can make the determination of ādangerousā or āsafeā driving situations would all be placed in the computer that already exists in the car. Itās almost like there is another human in the car.ā Recently, Sandia researchers conducted several experiments at Camp Pendleton with Marine Corps personnel using a modified military vehicle. During a difficult driving maneuver, the software classifier instructed the car to modify some of its systems. For example, radio signals were controlled in order to not distract the driver. āEvery year tens of thousands of people die in car crashes, many caused by driver distraction,ā Dixon says. āIf our algorithms can identify dangerous situations before they happen and alert drivers to them, we will help save lives.ā
A lot of attention has recently been drawn to robotic vehicles ā cars that drive and park by themselves, armed with radar sensors and cameras. Among other projects, DARPA is funding the prestigious annual āGrand Challengeā, where teams from all over the world compete in building vehicles that do not require a driver at all. TFOT recently covered āRobocarā ā one of the contenders of DARPAās 2007 Challenge (known as urban challenge) which was developed by a team of students at MIT.
More information on the project at Sandia Laboratories can be found here. More general information about the āurban challengeā could be found on DARPAās official website.