Autonomous vehicles are typically equipped with LIDAR or other similar sensors to detect obstacles in the surrounding environment. LIDAR also provides a means to detect and track other vehicles around the autonomous car. The main goal of this proposed study is to estimate traffic flow parameters along the path of the autonomous car from the point-cloud data generated by the LIDAR. The specific goals of the proposed research are:

1. Collect sample LIDAR data under different traffic conditions on freeways and urban arterials in Hampton Roads
2. Develop algorithms to detect vehicles around a LIDAR-equipped car and classify them based on vehicle size.
3. Develop algorithms to track other vehicles while within the LIDAR range
4. Estimate macroscopic traffic flow parameters based on the detected vehicles along the path of the LIDAR-equipped vehicle

Expected benefits and impacts:

1. New algorithms and methods will be developed to extract traffic flow information from raw LIDAR data
2. The developed methods will make it possible to gather massive and detailed data on traffic flow and driving behavior (e.g., car following). This can benefit a variety of applications including microscopic simulation model development and calibration, safety studies, estimation of temporal and spatial traffic flow conditions, etc.

The algorithms will be implemented on real-world data collected in Hampton Roads
The research methods and findings will be disseminated through professional conferences, journal publications, and technical reports.

http://www.tri-odu.org/autonomous-vehicles.html

Final Report (Received 12/2017): http://www.matsutc.org/wp-content/uploads/2018/01/Exploring-the-use-of-LIDAR-data-from-Autonomous-Cars-for-Estimating-Traffic-Flow-Parameters-and-Vehicle-Trajectories.pdf