Here's a sobering statistic to keep in mind when you're behind the wheel of your car: Since 2000, there have been 110 million car accidents in the United States, and more than 443,000 of them have been fatal. That's an average of 110 fatalities per day.
To improve driving safety, engineers have developed a number of safety systems aimed at preventing collisions, such as:
- Automated cruise control, a radar- or laser-based sensor system that slows a car when approaching another vehicle.
- Blind-spot warning systems, which use lights or beeps to alert the driver to the presence of a vehicle he or she can't see.
- Traction control and stability assist, which automatically apply the brakes if they detect skidding or a loss of steering control.
Still, more progress must be made to achieve the long-term goal of "intelligent transportation," in which cars will "see" and communicate with other vehicles on the road, making them able to prevent crashes virtually 100 percent of the time.
Even if such an intelligent transportation system, or ITS, could be perfected, it will have to allow for the reality that there will be a transition period in which ITS-enabled cars will share the road with cars without ITS. Those cars will still be prone to human driving errors, which will put the occupants of the ITS-enabled cars at risk of accidents.
To address this issue, MIT mechanical engineers are working on a new algorithm that takes into account models of human driving behavior to warn drivers of potential collisions, and ultimately takes control of the vehicle to prevent a crash.
The theory behind the algorithm and some experimental results will be published in the journal IEEE Robotics and Automation Magazine. Rajeev Verma and Domitilla Del Vecchio of MIT based their model on the idea that driving actions fall into two main modes: braking and accelerating. Depending on which mode a driver is in at a given moment, there is a finite set of possible places the car could be in the future, whether a tenth of a second later or a full 10 seconds later.
This set of possible positions, combined with predictive models of human behavior - when and where drivers slow down or speed up around an intersection, for example - all went into building the new algorithm.
The result is a program that is able to compute, for any two vehicles on the road nearing an intersection, a "capture set," or a defined area in which two vehicles are danger of colliding. The ITS-equipped car then engages in a sort of game-theoretic decision, in which it uses information from its on-board sensors as well as roadside and traffic-light sensors to try to predict what the other car will do, reacting accordingly to prevent a crash.
Eventually, the researchers also hope to build in sensors for weather and road conditions to help their algorithm make even better informed decisions.
Until then, an early version of an intelligent transportation system may help prevent a large number of crashes.
According to research described in the scientific journal Computer Networks, researchers from the University of Bologna have developed an automatic accident detection system that, in computer simulations, reduces the number of vehicles involved in pile-ups by up to 40 percent.
The system is being tested this year on the streets and highways of Los Angeles, around the campus of the University of California, where UCLA scientists and Toyota engineers are working on the system hardware.
Ultimately, the researchers predict that, if an accident happens on the road ahead of you, other cars connected to the system will tell your car to stop in a split-second. As Marco Roccetti, professor of Internet architecture at the University of Bologna ,explains, "Basically, what we are doing is placing cars in peer to peer communication."
The system includes more than just the accident-prevention software. While the system monitors road safety, the passengers in the car will be able to use the Internet to send e-mail, download music, or use social networking sites.