The field of autonomous vehicle research is growing rapidly. The Congressional mandate for the military to use unmanned vehicles has, in large part, sparked this growth. In conjunction with this mandate, DARPA sponsored the Urban Challenge, a competition to create fully autonomous vehicles that can operate in urban settings. An extremely important feature of autonomous vehicles, especially in urban locations, is their ability to perceive their environment. The research presented in this thesis is directed toward providing an autonomous vehicle with real-time data that efficiently and compactly represents its forward environment as it navigates an urban area. The information extracted from the environment for this application consists of stop line locations, lane information, and obstacle locations, using a single camera and LIDAR scanner. A road/non-road binary mask is first segmented. From the road information in the mask, the current traveling lane of the vehicle is detected using a minimum distance transform and tracked between frames. The stop lines and obstacles are detected from the non-road information in the mask. Stop lines are detected using a variation of vertical profiling, and obstacles are detected using shape descriptors. A laser rangefinder is used in conjunction with the camera in a primitive form of sensor fusion to create a list of obstacles in the forward environment. Obstacle boundaries, lane points, and stop line centers are then translated from image coordinates to UTM coordinates using a homography transform created during the camera calibration procedure. A novel system for rapid camera calibration was also implemented. Algorithms investigated during the development phase of the project are included in the text for the purposes of explaining design decisions and providing direction to researchers who will continue the work in this field. The results were promising, performing the tasks fairly accurately at a rate of about 20 frames per second, using an Intel Core2 Duo processor with 2 GB RAM.

With all the advancements in autonomous and connected cars, there is a developing body of research around the security and robustness of driving automation systems. Attacks and mitigations for said attacks have been explored, but almost always solely in software simulations. For this thesis, I led a team to build the foundation for an open source platoon of scale semi-autonomous vehicles. This work will enable future research into implementing theoretical attacks and mitigations. Our 1/10 scale car leverages an Nvidia Jetson, embedded microcontroller, and sensors. The Jetson manages the computer vision, networking, control logic, and overall system control; the embedded microcontroller directly controls the car. A lidar module is responsible for recording distance to the preceding car, and an inertial measurement unit records the velocity of the car itself. I wrote the software for the networking, interprocess, and serial communications, as well as the control logic and system control.

<p dir="ltr">The growth of electric vehicles (EVs) offers several benefits for air quality improvement and emissions reduction. Nonetheless, EVs also pose several challenges in the area of highway transportation. These barriers are related to the limitations of EV technology, particularly the charge duration and speed of battery recharging, which translate to vehicle range anxiety for EV users. A promising solution to these concerns is V2V DWC technology (Vehicle to Vehicle Dynamic Wireless Charging), particularly mobile energy disseminators (MEDs). The MED is mounted on a large vehicle or truck that charges all participating EVs within a specified locus from the MED. However, current research on MEDs offers solutions that are widely considered impractical for deployment, particularly in urban environments where range anxiety is common. Acknowledging such gap in the literature, this thesis proposes a comprehensive methodological framework for optimal MED deployment decisions. In the first component of the framework, a practical system, termed “ChargingEnv” is developed using reinforcement learning (RL). ChargingEnv simulates the highway environment, which consists of streams of EVs and an MED. The simulation accounts for a possible misalignment of the charging panel and incorporates a realistic EV battery model. The second component of the framework uses multiple deep RL benchmark models that are trained in “ChargingEnv” to maximize EV service quality within limited charging resource constraints. In this study, numerical experiments were conducted to demonstrate the MED deployment decision framework’s efficacy. The findings indicate that the framework’s trained model can substantially improve EV travel range and alleviate battery depletion concerns. This could serve as a vital tool that allows public-sector road agencies or private-sector commercial entities to efficiently orchestrate MED deployments to maximize service cost-effectiveness.</p>

<p dir="ltr">Most road fatalities are caused by human error. To help mitigate this issue and enhance overall transportation safety, companies are turning to advanced driver assistance systems and autonomous vehicle development. Perception, a key module of these systems, mostly uses light detection and ranging (LiDAR) sensors and enables efficient obstacle detection and environment mapping. Extensive research on the use of LiDAR for autonomous driving has been documented in the literature. Yet still, several researchers and practitioners have advocated continued investigation of LiDAR placement alternatives. To address this research need, this thesis research begins with a comprehensive review of different sensor technologies – camera, radio detection and ranging, global positioning system, and inertial measurement units – and exploring their inherent strengths and limitations. Next, the thesis research developed a methodological multiple criteria framework and implemented it in the context of LiDAR placement optimization. Given the numerous criteria and placement alternatives associated with LiDAR placement, multi-criteria decision analysis (MCDA) was identified as an effective tool for LiDAR placement optimization. MCDA has been applied to some extent in decision-making regarding autonomous vehicle development. However, its application in LiDAR placement optimization remains unexplored. In evaluating the LiDAR placement alternatives, the research first established the placement alternatives and then developed a comprehensive yet diverse set of criteria – point density, blind spot regions, sensor cost, power consumption, sensor redundancy, ease of installation, and aesthetics. The data collection methods included the CARLA simulator, sensor datasheets, and questionnaire surveys. The relative importance among the evaluation criteria was established using weighting techniques such as respondent-assigned weighting, equal weighting, and randomly generated weighting. Then, to standardize the different measurement units, scaling was carried out using value functions developed for each criterion using data from the respondents. Finally, the weighted and scaled criteria measures were amalgamated to obtain the overall evaluation score for each alternative LiDAR placement design. This enabled the ranking of the placement designs and the identification of the best-performing and worst-performing designs. Hence, the optimization method used is the enumeration technique. The findings of this study serve as a reference for future similar efforts that seek to optimize LiDAR placements based on select criteria. Further, it is expected that the thesis’s framework will contribute to an enhanced understanding of the overall impact of LiDAR placement on autonomous vehicles, thus enabling the cost-effective design of their placement and, ultimately, improving AV operational outcomes, including traffic safety.</p>

<p dir="ltr">State estimation is a type of an <i>inverse problem</i> in which some amount of observed data needs to be processed using computer algorithms (which are designed using analytical techniques) to infer or reconstruct the underlying model that produced the data. Due to the ubiquity of data and interconnected control systems in the present day, many engineering domains have become replete with inverse problems that can be formulated as state estimation problems. The interconnectedness of these control systems imparts the associated state estimation problems with distinctive structural properties that must be taken into consideration. For instance, the observed data could be high-dimensional and have a dependency structure that is best described by a graph. Furthermore, the control systems of today interface with each other and with the internet, bringing in new possibilities for large-scale collaborative sensor fusion, while also (potentially) introducing new sources of disturbances, faults, and cyberattacks. </p><p dir="ltr">The main thesis of this document is to investigate the unique challenges related to the issues of robustness, resilience (to faults and cyberattacks), and scalability of state estimation algorithms. These correspond to research questions such as, <i>"Does the state estimation algorithm retain its performance when the measurements are perturbed by unknown disturbances or adversarial inputs?"</i> and <i>"Does the algorithm have any bottlenecks that restrict the size/dimension of the problems that it could be applied to?".</i> Most of these research questions are motivated by a singular domain of application: autonomous navigation of unmanned aerial vehicles (UAVs). Nevertheless, the mathematical methods and research philosophy employed herein are quite general, making the results of this document applicable to a variety of engineering tasks, including anomaly detection in time-series data, autonomous remote sensing, traffic monitoring, coordinated motion of dynamical systems, and fault-diagnosis of wireless sensor networks (WSNs), among others.</p>

Autonomous vehicles are currently under study and one of the critical parts is the localization of the vehicle in the environment. Different localization methods have been studied over the years, such as the GPS sensor, commonly fused with other sensors such as the IMU. However, situations where the vehicle crosses a tunnel, a bridge, or there is simply traffic congestion, can cause the vehicle to get lost. Therefore, other methods such as point cloud registration have been used, where two point clouds are aligned, thus finding the pose of the vehicle on a precomputed map. Point cloud alignment, although a useful and functional method, is not free from errors that can lead to vehicle mislocalization. The intention of this work is to develop and compare different metrics capable of measuring in real time the performance of the point cloud alignment algorithm used, in this case Normal Distribution Transform (NDT). Therefore, it is important first of all to know if the position obtained meets the minimum requirements defined, just by knowing the input and output parameters of the algorithm. In addition to classifying the positioning as good or bad, the objective is to have a quality parameter that allows estimating the error committed in a complex environment where the uncertainty is very high. In addition, the influence of vehicle speed on the error made by the point cloud alignment algorithm will also be studied to determine whether there is any significant correlation between them. For this purpose, four different metrics have been studied, two of them being new contributions to this algorithm, called Error Propagation and CorAl, while the ones called Hessian and Score are obtained from the alignment algorithm itself. Data used was previously recorded and corrected, therefore obtaining ground truth data. Once the metrics were implemented, all of them were subjected to the same experiments, thus obtaining for each instant a quality measure that allowed a fair comparison to be made. These experiments were carried out on two different routes, being simulated 5 times each. In addition, from these simulations the speed was recorded, allowing the influence study to be carried out. The results show that the best performing metrics in terms of classification and estimation were the Error Propagation and the Hessian, while being impossible to determine a threshold value for the case of CorAl. Furthermore, they show that despite being functional, the error estimation is still far from perfect. It has also been shown that the error estimation of the lateral axis of the vehicle is more complex than in the case of the longitudinal axis. Finally, a strong and positive relationship between the vehicle speed and the error made by the alignment algorithm has been found. / Autonoma fordon studeras för närvarande och en av de kritiska delarna är lokaliseringen av fordonet i omgivningen. Olika lokaliseringsmetoder har studerats genom åren, t.ex. GPS-sensorn som ofta kombineras med andra sensorer, t.ex. IMU. Situationer där fordonet korsar en tunnel, en bro eller där det helt enkelt är trafikstockningar kan leda till att fordonet tappar uppfattningen om sin position. Därför har andra metoder utvecklats, t.ex. registrering av punktmoln, där två punktmoln justeras för att hitta fordonets position på en förinställd karta. Även om punktmolnsjustering är en användbar och funktionell metod, är den inte fri från fel som kan leda till felaktig lokalisering av fordonet. Syftet med detta arbete är att utveckla och jämföra olika mätmetoder som i realtid kan mätaprestandan hos den algoritm för punktmolnsjustering som används, i detta fall Normal DistributionTransform (NDT). Därför är det viktigt att först och främst veta om den erhållna tjänsten uppfyllerde fastställda minimikraven, bara genom att känna till algoritmens in- och utgångsparametrar.Förutom att klassificera positioneringen som bra eller dålig är målet att ha en kvalitetsparametersom gör det möjligt att uppskatta det fel som begåtts i en komplex miljö där osäkerheten är myckethög. Dessutom kommer fordonshastighetens inverkan på felet som görs av algoritmen för justeringav punktmoln också att studeras för att avgöra om det finns någon signifikant korrelation mellandem. För detta ändamål har fyra olika mått studerats, varav två är nya bidrag till denna algoritm, kallade Error Propagation och CorAl, medan de som kallas Hessian och Score erhålls från själva anpassningsalgoritmen. Data har tidigare registrerats och korrigerats, vilket ger sanningsdata. När mätvärdena hade implementerats utsattes de alla för samma experiment, så att man för varje ögonblick fick ett kvalitetsmått som gjorde det möjligt att göra en rättvis jämförelse. Dessa experiment utfördes på två olika rutter, som simulerades 5 gånger vardera. Dessutom registrerades hastigheten från dessa simuleringar, vilket gjorde det möjligt att genomföra en påverkansstudie. Resultaten visar att de bäst presterande mätvärdena när det gäller klassificering och uppskattning var Error Propagation och Hessian. Dessutom visar de att feluppskattningen fortfarande är långt ifrån perfekt. Det har också visats att feluppskattningen av fordonets sidoaxel är mer komplex än i fallet med den längsgående axeln. Slutligen har ett starkt och positivt samband mellan fordonshastigheten och felet som görs av inriktningsalgoritmen hittats.

No description available.

For the past couple of years researchers around theworld have tried to develop fully autonomous vehicles. One of theproblems that they have to solve is how to navigate in a dynamicworld with ever-changing variables. This project was initiated tolook into one scenario of the path planning problem; overtakinga human driven vehicle. Model Predictive Control (MPC) hashistorically been used in systems with slower dynamics but withadvancements in computation it can now be used in systems withfaster dynamics. In this project autonomous vehicles controlledby MPC were simulated in Python based on the kinematic bicyclemodel. Constraints were posed on the overtaking vehicle suchthat the two vehicles would not collide. Results show that anovertake, that keeps a proper distance to the other vehicle andfollows common traffic laws, is possible in certain scenarios. / Under de senaste åren har forskare världen över försökt utveckla fullt autonoma fordon. Ett av problemen som behöver lösas är hur man navigerar i en dynamisk värld med ständigt förändrande variabler. Detta projekt startades för att titta närmare på en aspekt av att planera en rutt; att köra om ett mänskligt styrt fordon. Model Predictive Control (MPC) har historiskt sett blivit använt i system med långsammare dynamik, men med framsteg inom datorers beräkningskraft kan det nu användas i system med snabbare dynamik. I detta projekt simulerades självkörande fordon, styrda av MPC, i Python. Fordonsmodellen som används var kinematic bicycle model. Begränsningar sattes på det omkörande fordonet så att de två fordonen inte kolliderar. Resultaten visar att en omkörning, som håller avstånd till det andra fordonet samt följer trafikregler, är möjligt i vissa scenarion. / Kandidatexjobb i elektroteknik 2020, KTH, Stockholm

The emergence of unmanned aerial vehicles (UAVs) along with the implementation of 5G networks offers exciting opportunities in expanding wireless capabilities. Not only is improved wireless performance expected with traditional devices such as mobile phones, but new use cases such as the internet-of-things and autonomous vehicle operation will rely on 5G and future network generations. In such widespread applications, from transportation to vital business operation, reliable and often guaranteed connectivity is required for safety and commercial approval. Introducing UAVs into network processes has been explored and implemented in certain instances to take advantage of the flexibility drone devices offer in their mobility and control to address these evolving network possibilities. While practical UAV deployment in certain network cases has been demonstrated, including coverage restoration in disaster relief scenarios, more ambitious goals of 5G will have additional considerations. This includes autonomous vehicles (AVs) whose operation is defined by levels representing varying degrees of autonomy. With computational requirements exponentially increasing as a vehicle's autonomy level is increased, 5G is expected to play an integral role in offloading certain vehicle tasks to the cloud. This thesis then proposes UAV based measurement opportunities as a method to characterize 5G coverage as part of autonomous vehicle processes to identify the proper level of autonomy that can operate safely given the current RF environment. This thesis proposes an UAV based measurement system that would provide coverage verification employing a platform capable of precise RF measurements and enhanced spatial sampling of the environment. Methods employed to traditionally characterize available coverage, including cellular drive tests, do not result in accurate enough measurements for AV use cases. Where lack of coverage in common network processes and use cases can result in dropped calls and poor connectivity in mobile devices, autonomous systems proposed in evolving network generations that deal with safety and mission critical functions must have guaranteed and verified coverage. Data produced in this thesis demonstrates that the proposed UAV based measurement system will improve measurement accuracy and enhanced geographic performance over conventional automotive vehicle based measurement systems / Master of Science / Wireless networks have grown to support vital and everyday processes in modern society. The COVID-19 pandemic proved wireless communication means a necessity to limit daily disruptions, but networks had already been supporting a continuously increasing amount of mobile devices prior to this. Other demonstrations of wireless network capacity include the release of 5G technology, allowing improved performance with traditional devices like smartphones, along with additional use cases this technology enables including the internet-of-things (IoT) and artificial intelligence (AI) leveraged functions for commercial applications. While wireless network capabilities have demonstrated their success in supporting and maintaining some critical functions, it is important to continually look ahead and plan for future network implementations in order to develop and support all desired advancements. Current measurement methods that assist in verifying coverage for current use cases like mobile devices will fall short in verification for more stringent requirements characteristic of AV and other ambitious network goals. The results found in this work then support the need for continuing research of a UAV-leveraged platform in the scope of eventual practical and safe AV integration into society. The focus of this thesis is to then propose and provide initial evaluation of a UAV-leveraged measurement platform to verify the operability of autonomous vehicles (AVs), which are expected to be a major aspect of future network processes. The computational requirements to operate an autonomous vehicle exponentially increase as a vehicle's autonomy level is increased. 5G is then expected to play an integral role in offloading certain vehicle tasks to the cloud. This thesis paper then proposes UAV based measurement opportunities as a method to characterize 5G coverage as part of autonomous vehicle processes to identify the proper level of autonomy that can operate safely given the current RF environment.

<p dir="ltr">Autonomous vehicles require motion forecasting of their surrounding multiagents (pedestrians</p><p dir="ltr">and vehicles) to make optimal decisions for navigation. The existing methods focus on</p><p dir="ltr">techniques to utilize the positions and velocities of these agents and fail to capture semantic</p><p dir="ltr">information from the scene. Moreover, to mitigate the increase in computational complexity</p><p dir="ltr">associated with the number of agents in the scene, some works leverage Euclidean distance to</p><p dir="ltr">prune far-away agents. However, distance-based metric alone is insufficient to select relevant</p><p dir="ltr">agents and accurately perform their predictions. To resolve these issues, we propose the</p><p dir="ltr">Semantics-aware Interactive Multiagent Motion Forecasting (SIMMF) method to capture</p><p dir="ltr">semantics along with spatial information and optimally select relevant agents for motion</p><p dir="ltr">prediction. Specifically, we achieve this by implementing a semantic-aware selection of relevant</p><p dir="ltr">agents from the scene and passing them through an attention mechanism to extract</p><p dir="ltr">global encodings. These encodings along with agents’ local information, are passed through</p><p dir="ltr">an encoder to obtain time-dependent latent variables for a motion policy predicting the future</p><p dir="ltr">trajectories. Our results show that the proposed approach outperforms state-of-the-art</p><p dir="ltr">baselines and provides more accurate and scene-consistent predictions. </p>