Search

This thesis deals with the problem of online motion planning for a vehicle when the available environmental information is limited. It is expected that the car moves within a lane using only the ego information (global x; y; z position and roll, pitch and yaw angles) and the information from a camera mounted in the windshield without previous knowledge of the road (like a map). The images obtained from the camera are used to obtain the optical flow, i.e., the measure of the apparent motion of the environment ahead of the moving vehicle.The continuously changing optical flow allows recognizing some features on the road, which are then used for a road artificial potential field computation. That field is used to generate an online reference trajectory (desired orientation) for the vehicle.Then, a gradient tracking control based on sliding mode is used to make the vehicle move along the prescribed trajectory determined by the gradient lines. A regular sliding mode controller is used for the longitudinal tracking of speed. Carla simulator is used for deployment and testing, and some different weathers are tested to evaluate the performance of the proposed approach.

Motor vehicle crashes involving novice drivers are significantly higher than matured drivers' incidents as reported by the National Highway Traffic Safety Administration Fatality Analysis Reporting System (NHTSA-FARS). There is ongoing research on how to decrease the number of crashes for this driver demographic group in the Unites States and Europe. Novice drivers usually complete driver education classes as a pre-requisite for full licensure to improve overall knowledge and safety. However, compiled statistics still indicate a need for more in-depth training after full licensure. This thesis introduces classroom and virtual training modules to improve the driving skills, attitudes, knowledge, and behavior of 'high-risk' young adult participants. The approach was to design two training modules for classroom instruction and establish a framework for a Public Service Announcement (PSA) seminar. In addition, a case study was performed using three automotive simulators exploring their potential use as a driver training resource. One of the driving simulators was subsequently used to complete a feasibility study examining the use of simulators as a driver training tool. The instructional modules covered vehicle maintenance, vehicle safety systems, and general automotive operations. The vehicle maintenance material included topics such as operating fluids, tires, brakes, windshield wipers, light bulbs, batteries, and warning lights. The second module focused on the basic operation of the vehicle and several key safety features (e.g., anti-lock braking system, electronic stability control, traction control system, seatbelts, and airbags). The PSA seminar introduced driving strategies such as avoiding driver distractions, seatbelt usage, and speed management using video campaigns produced by national and international organizations. Three simulators (DriveSafety Simulator, STISIM Drive Simulator, CU-Steering Simulator) were evaluated at North Carolina A&T University and Clemson University for their possible use in driver education programs. The overall performance was considered in nine general areas: ease of use, user-interface, motion/vision agreement, vehicle dynamics, haptic feedback, traffic scenarios, realism, mobility, and programmability. The DriveSafety simulator was determined the best option, since it provided the greatest number of characteristics ideally required for a training simulator. Based on the favorable results of this study, the opportunity to improve the driving skills of novice drivers using a DriveSafety automotive simulator was examined. Training test scripts for 'Following Etiquette' and 'Situational Awareness' were developed to introduce these key driving techniques. The training modules were administered in a pilot study using Clemson University students (ages 18-25). Students received little verbal instruction from the examiner; the majority of information was delivered by custom training videos and embedded driving simulator instructions. The 'Following Etiquette' module taught a basic timing method that allowed drivers to maintain a recommended following distance: 58% passed and 42% failed. The 'Situational Awareness' module allowed students to practice obstacle avoidance techniques and emergency maneuvers: 25% passed out right, 58% conditionally passed, and 17% failed. The classroom and virtual training modules were developed for possible implementation in a safe driving program. The automotive driving simulator proved to be a feasible option for facilitating automotive safety lessons, followed immediately by driving exercises to practice and reinforce the educational concept. Recommendations for additional classroom modules and virtual training modules are put forth for future study.