Autonomous Vehicles are complex modular systems with various inter-dependent safety critical modules, the failure of which leads to failure of the overall system. The Localization system, which estimates the pose of the vehicle in the global coordinate frame with respect to a map, has a drift in error, when operated only based on data from proprioceptive sensors. Current solutions to the problem are computationally heavy SLAM algorithms. An alternate system is proposed in the thesis which eliminates the drift by resetting the global coordinate frame to the local frame at every motion planning update. The system replaces the mission planner with a user interface(UI) onto which the User provides local navigation inputs, thus eliminating the need for maintenance of a Global frame. The User Input is considered in the decision framework of the behavioral planner, which selects a safe and legal maneuver for the vehicle to follow. The path and trajectory planners generate a trajectory to accomplish the maneuver and the controller follows the trajectory until the next motion planning update. A prototype of the system has been built on a wheeled robot and tested for the feasibility of continuous operation in Autonomous Vehicles. / Master of Science / Autonomous Vehicles are complex modular systems with various inter-dependent safety critical modules, the failure of which leads to failure of the overall system. One such module is the Localization system, that is responsible for estimating the pose of the vehicle in the global coordinate frame, with respect to a map. Based on the pose, the vehicle navigates to the goal waypoints, which are points in the global coordinate frame specified in the map by the route or mission planner of the planning module. The Localization system, however, consists of a drift in position error, due to poor GPS signals and high noise in the inertial sensors. This has been tackled by applying computationally heavy Simultaneous Localization and Mapping based methods, which identify landmarks in the environment at every time step and correct the vehicle position, based on the relative change in position of landmarks. An alternate solution is proposed in this thesis, which delegates navigation to the passenger. This system replaces the mission planner from the planning module with a User Interface onto which the passenger provides local Navigation input, which is followed by the vehicle. The system resets the global coordinate frame to the vehicle frame at every motion planning update, thus eliminating the error accumulated between the two updates. The system is also designed to perform default actions in the absence of user Navigation commands, to reduce the number of commands to be provided by the passenger in the journey towards the goal. A prototype of the system is built and tested for feasibility.

Development of unmanned vehicles will increase as the need to save lives rises. In both military and civilian applications, humans can be taken out of the loop through the implementation of safe and intelligent autonomous vehicles. Although hardware and software development continue to play a large role in the autonomous vehicle industry, validation of these systems will always be necessary. The ability to test these vehicles thoroughly and efficiently will ensure their proper and flawless operation. On November 3, 2007 the Defense Advanced Research Projects Agency held the Urban Challenge to drive the development of autonomous ground vehicles for military use. This event required vehicles built by teams across the world to autonomously navigate a 60 mile course in an urban environment in less than 6 hours. This thesis addresses the testing aspect of autonomous ground vehicles that exhibit the advanced behaviors necessary for operating in such an event. Specifically, the experiences of Team Victor Tango and other Urban Challenge teams are covered in detail. Testing facilities, safety measures, procedures, and validation methods utilized by these teams provide valuable information on the development of their vehicles. Combining all these aspects results in a proposed testing strategy for autonomous ground vehicles. / Master of Science

Autonomous ground vehicle operations, such as those found in the 2007 DARPA Urban Challenge, require a reliable and capable vehicle platform. To meet this requirement, an autonomous ground vehicle platform based on a 2005 Ford Escape Hybrid was developed for operations in urban environments. The vehicle conversion, dubbed Odin, contains a drive-by-wire system that is highly integrated with the OEM systems, providing throttle, steering, shifting, and braking actuation. The vehicle also includes a controller that provides low-level longitudinal using a map-linearized PI controller and lateral curvature control using a bicycle model. The control algorithms proved capable of controlling the vehicle at a level acceptable for autonomous operations. Communications are implemented using the Joint Architecture for Unmanned Systems (JAUS) using custom messages to enhance interoperability potential. The net result is a highly capable autonomous vehicle platform that was validated when Odin successfully completed the 60 mile Urban Challenge. / Master of Science

Autonomous vehicle development is a rapidly growing field that has vast possibilities for both military and commercial applications. Removing people from dangerous tasks will save lives. Continued research is necessary in order to build these new technologies and mature those already established. One area of potential in the unmanned vehicle community is that of fully autonomous cooperation. This area of research will allow multiple unmanned platforms to perform new functions on a larger scale by combining their capabilities in a coordinated manner. This thesis addresses the emerging need of research related to fully autonomous cooperation between a heterogeneous team of vehicles, by taking a system level approach and integrating the necessary technologies. Software was developed and then tested that combines an unmanned ground vehicle and an unmanned aerial vehicle in order to perform a task that utilizes the strengths of each platform. The ground vehicle is programmed with a route for which it sends look-ahead waypoints to the aircraft. As it traverses the route, the aircraft searches for possible targets. If a target is detected, the approximate coordinates are sent over the network and the ground vehicle then further localizes and inspects the target. Once the inspection is completed, the ground vehicle continues on its previous route. This thesis demonstrates that pairing ground and aerial vehicles in a fully autonomous target localization problem can indeed provide a team functioning more efficiently than either alone. / Master of Science

The Indiana Department of Transportation (INDOT) manages and maintains over 3,000 miles of interstates across the state. Assessing lane marking quality is an important part of agency asset tracking and typically occurs annually. The current process requires agency staff to travel the road and collect representative measurements. This is quite challenging for high volume multi-lane facilities. Furthermore, it does not scale well to the additional 5,200 centerline miles of non-interstate routes. <div><br></div><div>Modern vehicles now have technology on them called “Lane Keep Assist” or LKA, that monitor lane markings and notify the driver if they are deviating from the lane. This thesis evaluates the feasibility of monitoring when the LKA systems can and cannot detect lane markings as an alternative to traditional pavement marking asset management techniques. This information could also provide guidance on what corridors are prepared for level 3 autonomous vehicle travel and which locations need additional attention. </div><div><br></div><div>In this study, a 2019 Subaru Legacy with LKA technology was utilized to detect pavement markings in both directions along Interstates I-64, I-65, I-69, I-70, I-74, I90, I-94 and I-465 in Indiana during the summer of 2020. The data was collected in the right most lane for all interstates except for work zones that required temporary lane changes. The data was collected utilizing two go-pro cameras, one facing the dashboard collecting LKA information and one facing the roadway collecting photos of the user’s experience. Images were taken at 0.5 second frequency and were GPS tagged. Data collection occurred on over 2,500 miles and approximately 280,000 images were analyzed. The data provided outputs of: No Data, Excluded, Both Lanes Not Detected, Right Lane Not Detected, Left Lane Not Detected, and Both Lanes Detected. </div><div><br></div><div>The data was processed and analyzed to create spatial plots signifying locations where markings were detectable and locations where markings were undetected. Overall, across 2,500 miles of travel (right lane only), 77.6% of the pavement markings were classified as both detected. The study found</div><div><br></div><div>• 2.6% the lane miles were not detected on both the left and right side </div><div>• 5.2% the lane miles were not detected on the left side </div><div>• 2.0% the lane miles were not detected on the right side 8 </div><div><br></div><div>Lane changes, inclement weather, and congestion caused 12.5% of the right travel lane miles to be excluded. The methodology utilized in this study provides an opportunity to complement the current methods of evaluating pavement marking quality by transportation agencies. </div><div><br></div><div>The thesis concludes by recommending large scale harvesting of LKA from a variety of vendors so that complete lane coverage during all weather and light conditions can be collected so agencies have an accurate assessment of how their pavement markings perform with modern LKA technology. Not only will this assist in identifying areas in need of pavement marking maintenance, but it will also provide a framework for agencies and vehicle OEM’s to initiate dialog on best practices for marking lines and exchanging information.</div>

<p>  </p> <p>The transportation sector is witnessing rapid development of autonomous vehicle (AV) technology. While an AV can be more energy efficient than a conventional human-driven vehicle, their environmental impacts at the fleet and city level could be either significantly better or worse than the traditional systems, depending on how people use them – adopting AVs as privately-owned AVs (PAV) or centrally-managed shared AVs (SAV) will result in very different fleet size, vehicle-miles-travelled (VMT), and carbon emissions. To understand the environmental impacts of AVs at the city level, it is critical to consider who are likely to adopt which types of AVs, their travel demands, and the associated AV operation. Previous studies evaluating the potential impacts of AVs on the environment are limited by the existing travel demand models, which do not have sociodemographic information linked to the travel demands to support modeling of AV adoption or only generate trip origin and destination at the zonal level that is insufficient to support modeling of shared AV use. Additionally, existing research mainly focused on SAV systems and did not consider the potential competition between SAV and PAV. It is necessary to compare the system performance between the privately-owned AV system and the centrally-managed shared AV system and under the scenarios that both systems co-exist to inform AV system development. Furthermore, although AVs can help reduce fleet size through shared use, each vehicle will be used more intensively due to empty VMT, resulting in acceleration of vehicle replacement and increased need for vehicle production. To fully quantify the environmental impacts of a city’s AV system, it is also important to take a life-cycle perspective, considering not only vehicle use but also upstream vehicle manufacturing and downstream vehicle disposal with fleet replacement. </p> <p>To address these gaps, this work proposed an integrated agent-based model to quantify the environmental impacts of PAV and SAV. The integrated model includes four key components: 1) a travel demand generation model that links high resolution individual and household travel demand with socio-demographics information, 2) an AV adoption model that evaluates individual’s and household’s likelihood to accept AV and preference to use PAV, SAV or conventional vehicle, 3) an AV operation model to simulate the system performance of different AV fleets, and 4) an AV life cycle model that assesses different AV systems’ emissions considering vehicle replacement. Applying the proposed integrated model to a case study of Miami, the results have presented that the existing studies may overestimate AV systems’ environmental benefits, due to lack of travel demand data that can support the proposed integrated modeling, inconsideration of individual and household AV adoption decisions, and/or biased evaluation that does not account for all phases in AV system’s life-cycle. Case study results have showed that SAVs are more environmentally beneficial than PAVs but are less likely to be adopted by travelers and households, due to low cost of PAV use based on existing AV survey findings and current AV pricing knowledge. To promote SAV adoption to gain more positive environmental impacts, it is crucial to optimize SAV’s vehicle and system design to reduce service fee, waiting time, and in-vehicle value of time. The case study also found that due to more frequent vehicle replacement resulted from more intensively vehicle utilization, an AV systems’ environmental benefits from the operation phase can be counterbalanced by the impacts from other life-cycle phases. To achieve a life-cycle emission breakeven point, SAVs and PAVs need to improve fuel efficiency during the operation phase by 5% and 16% or reduce per-vehicle manufacture and disposal emissions by 36% and 5%. The proposed models and findings of this work can inform decision making for SAV operators, policy makers, and transportation planners. </p>

Connected Autonomous Vehicles require intelligent autonomous intersection management for safe and efficient operation. Given the uncertainty in vehicle trajectory, intersection management techniques must consider a safety buffer among the vehicles, which must also account for the network and computational delay, queue and determine the best solution to avoid traffic congestions (smart intersection management), in this paper we model traffic by using Poisson distribution method then add a birth-death processes for each state and combine both two in one queuing system (The Markovian chain) to model the traffic.Also, this paper will compare some autonomous vehicles communication techniques in intersections to draw the best scenario for autonomous vehicle network communication in order to reduce the traffic congestion in an intersection.The Connected Autonomous Vehicles and a normal autonomous vehicle, as well from the third line of the intersection a mix between the both will be provided into the intersection.The last section is about applying the results from the first and second research question into a simulator and compare the simulation results to approve the advantage of using the next generation of transportation technology (The connected autonomous vehicles) over the normal conventional vehicles.

This thesis deals with a new robust control design for autonomous vehicles. The goal is to perform lane keeping under various constraints, mainly actuator saturation of the steering system, lateral wind force, incident obstacles and unknown curvatures. To reach this goal, we propose an improved formulation of Parallel Distributed Compensation (PDC) law since it is a nonlinear system feedback state controller. A direct Lyapunov method to ensure the stability and the stabilization of the discrete-time Takagi-Sugeno (T-S) model representing the autonomous vehicle dynamics is suggested. We derived necessary and sufficient stability and stabilization conditions from the quadratic Lyapunov function. These conditions are expressed in terms of strict Linear Matrix Inequalities (LMIs) extracted from the linearization of the Bilinear Matrix Inequalities (BMIs). The vector state is measured entirely by the Luenberger multi-observers to be used in the feedback control. The results of Autonomous vehicle control are presented in this thesis to show the effectiveness of the proposed approach. Simulations are used to validate the theoretical results.

Artificial intelligence research is ushering in an era of sophisticated, mass-market transportation technology. While computers can fly a passenger jet better than a human pilot, people still face the dangerous yet tedious task of driving. Intelligent Transportation Systems (ITS) is the field focused on integrating information technology with vehicles and transportation infrastructure. Recent advances in ITS point to a future in which vehicles handle the vast majority of the driving task. Once autonomous vehicles become popular, interactions amongst multiple vehicles will be possible. Current methods of vehicle coordination will be outdated. The bottleneck for efficiency will no longer be drivers, but the mechanism by which those drivers' actions are coordinated. Current methods for controlling traffic cannot exploit the superior capabilities of autonomous vehicles. This thesis describes a novel approach to managing autonomous vehicles at intersections that decreases the amount of time vehicles spend waiting. Drivers and intersections in this mechanism are treated as autonomous agents in a multiagent system. In this system, agents use a new approach built around a detailed communication protocol, which is also a contribution of the thesis. In simulation, I demonstrate that this mechanism can significantly outperform current intersection control technology-traffic signals and stop signs. This thesis makes several contributions beyond the mechanism and protocol. First, it contains a distributed, peer-to-peer version of the protocol for low-traffic intersections. Without any requirement of specialized infrastructure at the intersection, such a system would be inexpensive and easy to deploy at intersections which do not currently require a traffic signal. Second, it presents an analysis of the mechanism's safety, including ways to mitigate some failure modes. Third, it describes a custom simulator, written for this work, which will be made publicly available following the publication of the thesis. Fourth, it explains how the mechanism is "backward-compatible" so that human drivers can use it alongside autonomous vehicles. Fifth, it explores the implications of using the mechanism at multiple proximal intersections. The mechanism, along with all available modes of operation, is implemented and tested in simulation, and I present experimental results that strongly attest to the efficacy of this approach. / text

Haul truck drivers frequently have difficulties spotting beside shovels. This is typically a combination of reduced visibility and poor mining conditions. Based on first-hand data collected from the Goldstrike Open Pit, it was learned that, on average, 9% of all spotting actions required corrective movements to facilitate loading. This thesis investigates an automated solution to haul truck spotting that does not rely on the use of the satellite global positioning system (GPS), since GPS can perform unreliably. This thesis proposes that if spotting was automated, a significant decrease in cycle times could result. Using conventional algorithms and techniques from the field of mobile robotics, vehicle pose estimation and control algorithms were designed to enable autonomous shovel-truck spotting. The developed algorithms were verified by using both simulation and field testing with real hardware. Tests were performed in analog conditions on an automation-ready Kubota RTV 900 utility truck. When initiated from a representative pose, the RTV successfully spotted to the desired location (within 1 m) in 95% of the conducted trials. The results demonstrate that the proposed approach is a strong candidate for an auto-spot system. / Thesis (Master, Mining Engineering) -- Queen's University, 2013-01-28 09:49:20.584