Semi-autonomous safety system acts as intelligent co-pilot for drivers

The brainchild of Sterling Anderson, a PhD student at MIT's Department of Mechanical Engineering, and Karl Iagnemma, a principal research scientist at MIT's Robotic Mobility Group, the system consists of an on-board camera and laser rangefinder, which identify hazards in a vehicle's environment. Unlike the technology behind self-parking cars, the system doesn't operate along pre-programmed paths, but rather identifies 'safe zones'. The researchers devised an algorithm that divides a vehicle's environment into triangles, with certain triangle edges representing an obstacle or a lane's boundary. The algorithm 'constrains' obstacle-abutting edges, allowing a driver to navigate across any triangle edge, except those that are constrained. If a driver is in danger of crossing a constrained edge - for instance, if they've fallen asleep at the wheel and are about to run into a barrier or obstacle - the system takes over, steering the car back into the safe zone. "The real innovation is enabling the car to share control with you," said Anderson. "If you want to drive, it'll just make sure you don't hit anything." So far, the team has run more than 1,200 trials of the system, with few collisions; most of these were said to occur when glitches in the vehicle's camera failed to identify an obstacle. The team is now looking to make the system simpler and cheaper to get it into mainstream production.