Forward Collision Avoidance Systems (FCAS) are a type of active safety system which have great potential for rear-end collision avoidance. These systems use either radar, lidar, or cameras to track objects in front of the vehicle. In the event of an imminent collision, the system will warn the driver, and, in some cases, can autonomously brake to avoid a crash. However, driver acceptance of the systems is paramount to the effectiveness of a FCAS system. Ideally, FCAS should only deliver an alert or intervene at the last possible moment to avoid nuisance alarms, and potentially have drivers disable the system. A better understanding of normal driving behavior can help designers predict when drivers would normally take avoidance action in different situations, and customize the timing of FCAS interventions accordingly. The overall research object of this dissertation was to characterize normal driver behavior in car following events based on naturalistic driving data. The dissertation analyzed normal driver behavior in car-following during both braking and lane change maneuvers. This study was based on the analysis of data collected in the Virginia Tech Transportation Institute 100-Car Naturalistic Driving Study which involved over 100 drivers operating instrumented vehicles in over 43,000 trips and 1.1 million miles of driving. Time to Collision in both braking and lane change were quantified as a function of vehicle speed and driver characteristics. In general, drivers were found to brake and change lanes more cautiously with increasing vehicle speed. Driver age and gender were found to have significant influence on both time to collision and maximum deceleration during braking. Drivers age 31-50 had a mean braking deceleration approximately 0.03 g greater than that of novice drivers (age 18-20), and female drivers had a marginal increase in mean braking deceleration as compared to male drivers. Lane change maneuvers were less frequent than braking maneuvers. Driver-specific models of TTC at braking and lane change were found to be well characterized by the Generalized Extreme Value distribution. Lastly, driver's intent to change lanes can be predicted using a bivariate normal distribution, characterizing the vehicle's distance to lane boundary and the lateral velocity of the vehicle. This dissertation presents the first large scale study of its kind, based on naturalistic driving data to report driver behavior during various car-following events. The overall goal of this dissertation is to provide a better understanding of driver behavior in normal driving conditions, which can benefit automakers who seek to improve FCAS effectiveness, as well as regulatory agencies seeking to improve FCAS vehicle tests. / Ph. D.

There is growing interest in the application of high-resolution radars in autonomous vehicles due to their affordability and high angular resolution. However, the azimuth ambiguity caused by the large physical distance between radar antennas relative to the signal wavelength is a challenge for its application. The problem of multiple extended target tracking using high-resolution radar measurements with azimuth ambiguity is considered. A novel pseudo-3D assignment (P3DA) method based on the pseudo measurement set (PMS) is proposed to resolve the azimuth ambiguity. This method can resolve mono (single) and split (duplicated) azimuth ambiguities common in extended target tracking. The Lagrangian relaxation based on a flexible search (LR-FS) algorithm is proposed to solve the P3DA-PMS problem efficiently. Simulation and experiment results show that the proposed algorithm outperforms conventional methods that do not address the azimuth ambiguity of extended target tracking. Since data association with only one data frame will lose information about target evolution and cannot change an association later based on subsequent measurements, a novel two-step multiframe assignment method is proposed to resolve split and azimuth ambiguity separately. In the first step, the split ambiguity is resolved by the PMS-to-PMS association, resulting in a merged PMS (MPMS). In the second step, the azimuth ambiguity is resolved by the Track-to-MPMS association. Numerical results show that the proposed method performs better than the P3DA-PMS-based method. The vehicles tracking with high-resolution radars need to provide information about their orientation and shape to achieve lidar-like performance. Due to self-occlusion, the L-shape model is frequently utilized to depict the structure of a typical vehicle. Since the measurement accuracy of high-resolution radars is not as high as that of lidars, radar measurement noise cannot be ignored. Moreover, as a side effect of using large wavelengths, multiple measurements may be produced per time step due to multipath effects. As a result, more outliers and inliers can be generated in high-resolution radar measurements. A novel lognormal likelihood-aided L-shape model is proposed to approximate the distribution of high-resolution radar measurements of vehicles. Numerical results evaluated on simulation data and the KITTI dataset show that the proposed algorithm achieves smaller orientation and position errors and larger generalized intersection over union (GIoU) compared to existing L-shape fitting algorithms for lidar measurements. / Dissertation / Doctor of Philosophy (PhD)

The navigation and control of an autonomous vehicle is a highly complex task. Making a vehicle intelligent and able to operate "unmanned" requires extensive theoretical as well as practical knowledge. An autonomous vehicle must be able to make decisions and respond to situations completely on its own. Navigation and control serves as the major limitation of the overall performance, accuracy and robustness of an autonomous vehicle. This thesis will address this problem and propose a unique navigation and control scheme for an autonomous lawn mower (ALM). Navigation is a key aspect when designing an autonomous vehicle. An autonomous vehicle must be able to sense its location, navigate its way toward its destination, and avoid obstacles it encounters. Since this thesis attempts to automate the lawn mowing process, it will present a navigational algorithm that covers a bounded region in a systematic way, while avoiding obstacles. This algorithm has many applications including search and rescue, floor cleaning, and lawn mowing. Furthermore, the robustness and utility of this algorithm is demonstrated in a 3D simulation. This thesis will specifically study the dynamics of a two-wheeled differential drive vehicle. Using this dynamic model, various control techniques can then be applied to control the movement of the vehicle. This thesis will consider both open loop and closed loop control schemes. Optimal control, path following, and trajectory tracking are all considered, simulated, and evaluated as practical solutions for control of an ALM. To design and build an autonomous vehicle requires the integration of many sensors, actuators, and controllers. Software serves as the glue to fuse all these devices together. This thesis will suggest various sensors and actuators that could be used to physically implement an ALM. This thesis will also describe the operation of each sensor and actuator, present the software used to control the system, and discuss physical limitations and constraints that might be encountered while building an ALM. / Master of Science

This thesis describes the current state of development of the Flexible Low-cost Automated Scaled Highway (FLASH) laboratory at the Virginia Tech Transportation Institute (VTTI). The FLASH lab and the scale model cars contained therein provide a testbed for the small scale development stage of intelligent transportation systems (ITS). In addition, the FLASH lab serves as a home to the prototype display being developed for an educational museum exhibit. This thesis also gives details of the path following lateral controller implemented on the FLASH car. The controller was developed using the kinematic model for a wheeled robot. The global model is converted into the path coordinate model so that only local variables are needed. then the path coordinate model is converted into chained form and a controller is given to perform path following. The path coordinate model introduces a new parameter to the system: the curvature of the path. Thus, it is necessary to provide the path's curvature value to the controller. Because of the environment in which the car is operating, the curvature values are known a priori. Several online methods for determining the curvature are developed. A MATLAB simulation environment was created with which to test the above algorithms. The simulation uses the kinematic model to show the car's behavior and implements the sensors and controller as closely as possible to the actual system. The implementation of the lateral controller in hardware is discussed. The vehicle platform is described and the harware and software architecture detailed. The car described is capable of operating manually and autonomously. In autonomous mode, several sensors are utilized including: infrared, magnetic, ultrasound, and image based technology. The operation of each sensor type is described and the information received by the processor from each is discussed. / Master of Science

Recent advances in technology have enabled the development of truly autonomous ground vehicles capable of performing complex navigation tasks. As a result, the demand for practical unmanned ground vehicle (UGV) systems has increased dramatically in recent years. Central to these developments is maturation of emerging mobile robotic intelligent and autonomous capability. While the progress UGV technology has been substantial, there are many challenges that still face unmanned vehicle system developers. Foremost is the improvement of perception hardware and intelligent software that supports the evolution of UGV capability. The development of a Next-generation Experimentation Robotic Vehicle (NERV) serves to provide a small UGV baseline platform supporting experimentation focused on progression of the state-of-the-art in unmanned systems. Supporting research and user feedback highlight the needs that provide justification for an advanced small UGV research platform. Primarily, such a vehicle must be based upon open and technology independent system architecture while exhibiting improved mobility over relatively structured terrain. To this end, a theoretical kinematic model is presented for a novel two-body multi degree-of-freedom, four-wheel drive, small UGV platform. The efficacy of the theoretical kinematic model was validated through computer simulation and experimentation on a full-scale proof-of-concept mobile robotic platform. The kinematic model provides the foundation for autonomous multi-body control. Further, a modular system level design based upon the concepts of the Joint Architecture for Unmanned Systems (JAUS) is offered as an open architecture model providing a scalable system integration solution. Together these elements provide a blueprint for the development of a small UGV capable of supporting the needs of a wide range of leading-edge intelligent system research initiatives. / Master of Science

The wireless technology of today provides combat systems with the potential to communicate mission critical data to every asset involved in the operation. In such a dynamic environment, the network must be able maintain communication by adapting to subsystems moving relative to each other. A theoretical and experimental foundation is developed that allows an autonomous ground vehicle to serve as an adaptive communication node in a larger network. The vehicle may perform other functions, but its primary role is to constantly reposition itself to maintain optimal link quality for network communication. Experimentation with existing wireless network hardware and software led to the development, implementation, and analysis of two main concepts that provided a signal optimization solution. The first attracts the communication ground vehicle to the network subsystems with weaker links using a vector summation of the signal-to-noise ratio and network subsystem position. This concept continuously generates a desired waypoint for repositioning the ground vehicle. The second concept uses a-priori GIS data to evaluate the desired vehicle waypoint determined by the vector sum. The GIS data is used primarily for evaluating the viewshed, or line-of-sight, between two network subsystems using elevation data. However, infrastructure and ground cover data are also considered in navigation planning. Both concepts prove to be powerful tools for effective autonomous repositioning for maximizing the communication link quality. / Master of Science

This thesis describes the design of an inexpensive autonomous vehicle system using a small scaled model vehicle. The system is capable of operating in two different modes: telerobotic manual mode and automated driving mode. In telerobotic manual mode, the model vehicle is controlled by a human driver at a stationary remote control station with full-scale steering wheel and gas pedal. The vehicle can either be an unmodified toy remote-control car or a vehicle equipped with wireless radio modem for communication and microcontroller for speed control. In both cases the vehicle also carries a video camera capable of transmitting video images back to the remote control station where they are displayed on a monitor. In automated driving mode, the vehicle's lateral movement is controlled by a lateral control algorithm. The objective of this algorithm is to keep the vehicle in the center of a road. Position and orientation of the vehicle are determined by an image processing algorithm identifying a white middle marker on the road. Two different algorithm for image processing have been designed: one based on the pixel intensity profile and the other on vanishing points in the image plane. For the control algorithm itself, two designs are introduced as well: a simple classical P-control and a control scheme based on H-Infinity. The design and testing of this autonomous vehicle system are performed in the Flexible Low-cost Automated Scaled Highway (FLASH) laboratory at Virginia Tech. / Master of Science

Despite the advancements in the development of autonomous vehicles (AVs), there are still numerous complex situations in which AVs may encounter challenges. In recent years, the concept of teleoperation, which entails establishing a connection between a remote operator and the AV, has garnered substantial attention from both AV companies and governmental bodies as a viable safety backup method. However, a research gap is apparent when it comes to the remote manipulation of AVs positioned at a considerable distance. This gap involves a) AV with a temporal delay through real-time direct control within the constraints of current wireless communication technology in an unpredictable road environment, and b) enhancing the AV's inherent detection capabilities to augment its autonomous control abilities, thereby reducing the operator's workload. To address this research gap, this dissertation introduces an innovative teleoperation system. Initially, we devise a control system utilizing the wave variable approach as a communication method to alleviate the impact of signal latency. And Radial Basis Function Networks (RBFN) are employed to effectively manage the uncertain nonlinear dynamics of the vehicle. Subsequently, a saliency-based object detection (OD) algorithm, named SalienDet, is proposed to identify objects not present in the training sample set. SalienDet incorporates saliency maps generated without prior information into the neural network, enhancing image features for unfamiliar objects. This augmentation significantly aids the OD algorithm in detecting previously unknown objects, thereby empowering the AV to possess an improved perception ability. This advancement is particularly valuable when the operator imparts driving advice to the AV instead of exercising direct control. In conclusion, this dissertation makes a noteworthy contribution to AV teleoperation by furnishing a comprehensive solution that spans various aspects of AV teleoperation. / Doctor of Philosophy / This dissertation revolves around the teleoperation of autonomous vehicles (AVs), with the objective of formulating a comprehensive teleoperation system that encompasses two critical aspects: direct control and indirect control. In the initial segment of the dissertation, we introduce a real-time teleoperation direct control system based on neural networks. This framework plays a pivotal role in assisting operators in navigating AVs efficiently, especially in the face of challenges such as communication delays and complex external environments. Following this, we present a novel saliency-based object detection (OD) algorithm. This algorithm empowers the AV to recognize potential objects beyond its prior knowledge, thereby enhancing its level of autonomous control, particularly when operators opt not to exercise direct control over the remote AV. Our research findings delve into the essential facets of AV teleoperation. The developed teleoperation system serves as a valuable reference for future researchers and engineers dedicated to advancing autonomous vehicle technology.

This manuscript includes an investigation of decision making in alternative modes of transportation in order to understand consumers' decision in different contexts. In essay 1 of this study, the motives for participation in situated ridesharing is investigated. The study proposes a theoretical model that includes economic benefits, time benefits, transportation anxiety, trust, and reciprocity either as direct antecedents of ridesharing participation intention, or mediated through attitude towards ridesharing. Essay 2 of this study, focuses on self-driving vehicles as one of the recent innovations in transportation industry. Using a survey approach, the study develops a conceptual model of consumers' anticipated motives. Both essays use partial least square- structural equation modeling for assessing the proposed theoretical models.

As autonomous vehicle (AV) technology evolves and matures, automated public transit (APT) is gaining attention due to its flexibility, cost-effectiveness, and efficiency. This report explores various algorithms for allocating vehicles to passengers within APT systems. It aims to organize and propose effective allocation strategies and validate them through comparative analyses on test networks. Overall, the paper introduces several algorithms, with six specifically compiled and tested using the VIPSim simulator across four traffic networks. Two of these networks are basic, while the other two are more complex and represent real-world scenarios. Through these numerical experiments, the algorithm that maximizes network operational efficiency was identified, and several instructive conclusions were drawn from the comparative analysis.