Morellas, Vassilios

This report summarizes conclusions and recommendations regarding the Magnetic Lateral Indication System. It analyzes results and conclusions that were derived by 3M and Honeywell, which conducted a feasibility study of a lateral position indication system for vehicles.

This report summarizes the work performed during the 18-month period ending in December 1997. Researchers investigated the use of differential global positioning systems (GPS), inertial measurement, and other sensing technologies as the basis of a system that would prevent crashes. Such a system attempts to control the vehicle if it leaves the lane because the driver is incapacitated. The report includes in its appendices related work on driver fatigue and a bibliography on the effect of drugs and alcohol on driving behavior. The long-term goal of this research involves development of a "driver-centered" vehicle control system capable of providing lane-keeping feedback to the driver, and, if necessary, of imposing aggressive intervention strategies to take over control of the vehicle, steer it to a safe position on the shoulder, and stop it. This research also targets the development of "driver assistive" technologies--such as Heads Up Display and torque feedback supplied by the steering wheel--which provide information to the driver without necessarily requiring computer control of the vehicle. The highlight achievement during this funding period has been the successful demonstration of a GPS-based automated lane-keeping mode of a tractor-trailer on the Minnesota Road Research Project (Mn/ROAD) test track. The report concludes with a strategy for pursuing future deployment.

The SAFETRUCK program focuses on preventing accidents on rural highways, especially those associated with run-off-the-road incidents and driver fatigue, by giving the vehicle the ability to steer to the side of the road and come to a safe stop if the driver falls asleep or is otherwise incapacitated. Researchers have equipped a Navistar 9400 series class 8 truck tractor with the sensors and control computers necessary to perform this task. Designing the controller that will steer the truck requires a mathematical model of the lateral response of the truck to steering inputs. In this project, researchers developed a lateral dynamic model by incorporating second order dynamics into the steering axle tires. Simulation of the resulting models indicated dynamic behavior that was close to the experimental data for speeds between 15 and 30 miles per hour. This is the first time that a lateral dynamic model of a truck has been experimentally verified. Both models, however, resulted in experimentally determined values for steering axle cornering stiffness that were considerably smaller than published values for the Goodyear G 159 tires on the truck.

An ongoing research project examines guidance systems, which can take over control of a vehicle if the driver becomes incapacitated. Part of this project includes an evaluation of a Differential Global Positioning System (DGPS) for vehicle-based lane sensing. This report documents the results of tests of the 5 Hz NovAtel RT20 DGPS receiver. A series of 32 static tests found the overall mean and standard deviation for the offset errors within specifications. In a series of dynamic tests, in which the vehicle was driven around the track at speeds of 20-35 miles per hour, after removing the effect of the GPS receiver's latency, the DGPS determined position exhibited a mean offset error of -17.3 cm (-6.82 in) and a mean standard deviation of 25.5 cm (10.1 in) in the direction of vehicle motion. In the direction perpendicular to vehicle motion, the mean offset was 4.57 cm (1.8 in) with a mean standard deviation of 39.6 cm (15.6 in). With no overhead obstructions in these tests, continuous satellite lock was possible. Tests at higher speeds based on a more accurate methodology are planned for the future.

The use and creation of combined high-occupancy vehicle/high-occupancy toll (HOV/HOT Lanes) have become more common in urban areas since all types of road users can take advantage of the lane either as a high-occupancy vehicle or opting in to pay a congestion adjusted free. However; to maintain working integrity of the lanes for all users; stepped enforcement to discourage cheating has been needed as more lanes are added. This study evaluated the capability of a novel image sensor device to automate detection of in-vehicle occupants to flag law enforcement of HOV/HOT lane violators. The sensor device synchronously captures three co-registered images; one in the visible spectrum and two others in the infrared bands. The key idea is that the infrared bands can enhance correct occupancy detection through known phenomenological spectral properties of objects and humans residing inside the vehicle. Several experiments were conducted to determine this capability across varied conditions and scenarios to assess detection segmentation algorithms of vehicle passengers and drivers. Although occupancy detection through vehicle glass could be achieved in many cases; improvements must be made to such a detection system to increase robustness and reliability as a law enforcement tool. These improvements were guided by the experimental results; as well as suggested methods for deployment if this or similar technologies were to be deployed in the future.

The objective of the project is to analyze existing technologies used for the process of generating counts of bicycles and pedestrians in transportation facilities such as walk and bicycle bridges, urban bicycle routes, bicycle trails etc. The advantages and disadvantages of each existing technology which is being applied to counting has been analyzed and some commercially available products were listed. A technical description of different methods that were considered for vision based object recognition is also mentioned along with the reasons as to why such methods were overlooked for our problem. Support Vector Machines were used for classification based on a vocabulary of features built using interest point detectors. After finalizing the software and hardware, five sites were picked for filming and about 10 hours of video was acquired in all. A portion of the video data was used for training and the remainder was used for testing the algorithm's accuracy. Results of counts are provided and an interpretation of these results is provided in this report. Upon detailed analysis the reasons for false counts and undercounting in some cases have been identified and current work concerns dealing with these issues. Changes are being made to the system to improve the accuracy with the current level of training and make the system available for practitioners to perform counting.

This research applied wave band and computer vision methods to automatically count vehicle occupants in the High Occupancy Vehicle (HOV) lane at a high level of accuracy. The research showed that use of near-infrared bandwidth offers potential as a method for developing an automatic vehicle occupant counting system. Near-infrared only can produce images when looking through glass, but not metal or heavy clothes, which limits its accuracy in counting children or occupants resting in vehicles. The mid-infrared camera did not produce clear images at highway speeds. The next step involves additional research into a working device that can count vehicle occupants reliably, including analysis of device performance with more types of vehicles, passengers in the back seats, children in car seats, and passengers lying down.