In 2010, there were approximately 5.5 million automobile crashes in the United States—the majority caused by human error. That’s because humans make mistakes, especially when they try to do more than one thing at a time. Knowing this, engineers are taking a new approach to make the roads a safer place. In recent years, automotive research has moved from collision mitigation—reducing damage caused by accidents—to preventing accidents from happening in the first place.
Recently, Ford partnered with MIT and Stanford to develop what researchers are calling an “intelligent co-pilot” for cars. These self-driving cars won’t actually drive themselves – yet. Rather, the new technology is an extension of current car safety features, such as seat belts and airbags.
In current semi-autonomous cars, the driver is in control unless they make a dangerous maneuver, explains Sterling Anderson SM ’09 PhD ’13, who developed such a system with MIT’s Robotic Mobility Group and Department of Mechanical Engineering. If the driver tries to outside of the car’s “safety corridor”, the system intervenes.
Watch Anderson demonstrate the semi-autonomous driving system:
“Ford’s research with MIT uses advanced algorithms to help the vehicle learn to predict where moving vehicles and pedestrians could be in the future,” the company said. “This scenario planning provides the vehicle with a better sense of the surrounding risks, enabling it to plan a path that will safely avoid pedestrians, vehicles and other moving objects.”