For the past hundred years, innovation within the automotive sector has created safer, cleaner, and more affordable vehicles, but progress has been incremental.
The industry now appears close to substantial change, engendered by autonomous, or "self-driving," vehicle technologies.
RAND reports present research findings and objective analysis that address the challenges facing the public and private sectors.
All RAND reports undergo rigorous peer review to ensure high standards for research quality and objectivity.
Permission is given to duplicate this electronic document for personal use only, as long as it is unaltered and complete.
Copies may not be duplicated for commercial purposes. We are a group of graduate students, researchers, and corporate partners who are working to develop new algorithms and techniques for autonomous driving in unpredictable urban settings.Since our successful efforts in the DARPA Grand Challenge and the DARPA Urban Challenge, we have been creating and testing a variety of AI solutions to important problems in autonomous driving.The authors decompose the path planning problem into three steps.In the first step, A* algorithm is applied to obtain the positive and negative samples.GRNN-FSVM can reduce the effects of outliers and maximize the safety margin for driving, the generated path is smooth and safe, while satisfying the constraint of vehicle kinematic. Eerie as it may seem to drive alongside a car with no one behind the wheel, autonomous vehicles are poised to hit the roads in the next few years.For instance, our friends down the road at Google are using several of our techniques on their self-driving vehicles.Please take a look at our research papers, watch a few movies of our autonomous car in action, and peruse some media coverage about our program and our team. The simulations are designed to verify the parameters of the path planning algorithm.The method is implemented on autonomous vehicle and verified against many outdoor scenes. https://doi.org/10.1108/IR-11-2016-0301 Download as .