The AAAI Spring Symposium on Embedded Reasoning: Intelligence in Embedded Systems

to be held at the 2010 AAAI Spring Symposium
March 22-24, 2010 at Stanford University, California

Home :: Important Dates :: Submission :: Organization :: Program

Assisted Highway Lane Changing with RASCL

Abstract:

Driving is one of the most ubiquitous aspects of modern life, yet it is also one of the most dangerous. According to the Na- tional Center for Health Statistics, motor vehicle traffic is the leading cause of unintentional injury and death among all Americans. In 2007 alone, 41,059 people were killed in motor vehicle crashes. One of the most dangerous and stressful parts of driving is lane changing. Indeed, 730,000 car crashes (1000 of them fatal) happened during “lane change, merging, and sideswipe” maneuvers.

In this paper, we describe RASCL, the Robotic Assis- tance System for Changing Lanes, an assistive lane changing system built on Junior’s platform. It is unique in a number of ways. RASCL combines state-of-the-art sensing and localiza- tion techniques with an accurate map describing road struc- ture to detect and track other cars, determine whether or not a lane change to either side is safe, and communicate these safety statuses to the user using a variety of audio and visual interfaces. The user can interact with the system through spe- cifying the size of their “comfort zone” (see Figure 1), engag- ing the turn signal, or by simply driving across lane dividers. Additionally, RASCL provides speed change recommenda- tions that are predicted to turn an unsafe lane change situation into a safe situation and increases communication with other vehicles by automatically controlling the turn signal when the driver attempts to change lanes without using the turn signal.