This thesis presents an algorithm for collision detection for an autonomous articulated vehicle following pregenerated paths in a mining environment. Two types of vehicles are studied. The tricycle vehicle and the articulated vehicle. The characteristics of the mine is presented. A way of using these characteristics is studied. An algorithm for collision detection using the swept area of the vehicle following a pregenerated path is given. As proof of concept a small implementation is also given along, with a few examples. / Validerat; 20101217 (root)

The area of autonomous vehicles is an interesting research topic, which is popular in both research and industry worldwide. Linköping university is no exception and some of their research is based on using Model Predictive Control (MPC) for autonomous vehicles. They are using MPC to plan a path and control the autonomous vehicles. Additionally, they are using different methods (for example deep learning or likelihood) to calculate collision probabilities for the obstacles. These are very complex algorithms, and it is not always easy to see how they work. Therefore, it is interesting to study if a visualization tool, where the algorithms are presented in a three-dimensional way, can be useful in understanding them, and if it can be useful in the development of the algorithms.  This project has consisted of implementing such a visualization tool, and evaluating it. This has been done by implementing a visualization using a 3D library, and then evaluating it both analytically and empirically. The evaluation showed positive results, where the proposed tool is shown to be helpful when developing algorithms for autonomous vehicles, but also showing that some aspects of the algorithm still would need more research on how they could be implemented. This concerns the neural networks, which was shown to be difficult to visualize, especially given the available data. It was found that more information about the internal variables in the network would be needed to make a better visualization of them.

Wide spread consumer adoption of self-driving cars (SDC) is predicated on a level of trust between humans and the autonomous vehicle. Despite advances being made in the technical abilities of SDCs, recent studies indicate that people are negatively predisposed toward utilizing autonomous vehicles. To bridge the gap between consumer skepticism and adoption of SDCs, research is needed to better understand the evolution of trust between humans and growing autonomous technologies. The question of mainstream acceptance and requisite trust is explored through integration of virtual reality SDC simulator, an electroencephalographic (EEG) recorder, and a new approach for real-time trust measurement between passengers and SDCs. An experiment on fifty human subjects was conducted where participants were exposed to scenarios designed to induce positive and negative trust responses. Emotional state was quantified by the EEG beta wave to alpha wave power ratio, and participants self-reported their levels of trust in the SDC after each segment. / Includes bibliography. / Thesis (M.S.)--Florida Atlantic University, 2018. / FAU Electronic Theses and Dissertations Collection

Automotive manufacturers are competing to be the first to introduce customer-ready autonomous vehicles. Some manufacturers are claiming to launch their first self-driving cars as early as 2020. Which all sounds very good and futuristic; however, the question arises, are customers even ready to adopt this new technological advancement? Therefore, this pilot study is aimed at finding out the answer to this question in the Austrian market. This study discovers the standpoint of Austrian consumers concerning the acceptance of self-driving cars for daily usage and gives an overview of the current point of view regarding autonomous vehicles (AVs). The data for this study was collected using an online, user-friendly, Likert scale survey. The collected data were processed and analyzed for empirical significance in SPSS using Spearman's rank correlation and the Mann-Whitney U test supported by descriptive analysis. The results of the study indicate that Austrian consumers are well aware of autonomous vehicles and their technology. However, they have specific concerns about reliability, cybersecurity, and futuristic car-sharing models. Therefore, these concerns about AVs should be addressed by auto manufactures in order to gain consumers' trust and sell them a new form of mobility.

New underwater passive sonar techniques are developed for enhancing target localization capabilities in shallow ocean environments. The ocean surface and the seabed act as acoustic mirrors that reflect sound created by boats or subsurface vehicles, which gives rise to echoes that can be heard by hydrophone receivers (underwater microphones). The goal of this work is to leverage this "multipath" phenomenon in new ways to determine the origin of the sound, and thus the location of the target. However, this is difficult for propeller driven vehicles because the noise they produce is both random and continuous in time, which complicates its measurement and analysis. Further, autonomous underwater vehicles (AUVs) pose additional challenges because very little is known about the sound they generate, and its similarity to that of boats. Existing methods for localizing propeller noise using multiple hydrophones have approached the problem either purely theoretically, or empirically such as by analyzing the interference patterns between multipath arrivals at different frequencies, however little has been published on building localization techniques that directly measure and utilize the time delays between multipath arrivals while simultaneously accounting for relevant environmental parameters. This research develops such techniques through a combination of array beamforming and advanced ray-based modeling that account for variations in bathymetry (seabed topography) as well as variations of the sound speed of the water. The basis for these advances come from several at-sea experiments in which different configurations of passive sonar systems recorded sounds emitted by different types of targets, including small boats and an autonomous underwater vehicle. Ultimately, these contributions may reduce the complexity and cost of passive systems that need to be deployed close to shore, such as for harbor security applications. Further, they also create new possibilities for applying passive sonar in remote ocean regions for tasks such as detecting illegal fishing activity. This dissertation makes three key contributions: 1. Analysis of the aspect-dependent acoustic radiation patterns of an underway autonomous underwater vehicle (AUV) through full-field wave modeling. 2. A two-hydrophone cross-correlation technique that leverages multipath as well as bathymetric variations to estimate the range and bearing of a small boat, supported by a mathematically rigorous performance analysis. 3. A multi-target localization technique based on directly measuring multipath from multiple small surface vessels using a small hydrophone array mounted to the nose of an AUV, which operates by cross-correlating two elevation beams on a single bearing.

Apesar da expressiva quantidade de trabalhos relacionados aos veículos autônomos, poucos são aqueles encontrados sobre a coexistência de veículos autônomos e convencionais no sistema viário. O comportamento dos veículos autônomos é abordado majoritariamente visando analisar a tecnologia envolvida para a comunicação entre os veículos ou a segurança destes dispositivos. Desta forma, o objetivo da pesquisa é avaliar o impacto, do ponto de vista logístico, no comportamento do tráfego em vias com veículos convencionais e autônomos simultaneamente. Através de simulação computacional utilizando ferramentas tradicionais e de código aberto, este trabalho analisa, como a inclusão crescente de veículos autônomos em algumas vias da malha viária da cidade de São Paulo afeta o comportamento dinâmico dos veículos. Cenários de tráfego foram modelados e considerados neste estudo, e sobre eles se concluiu, que a simples inserção de veículos autônomos no sistema não reflete na melhoria uniforme do tráfego, ou seja, algumas rotas, dependendo da sua extensão, volume de veículos e número de semáforos podem sofrer melhorias pouco representativas com relação à velocidade média, tempo de espera em fila e tempo médio de viagem. / Despite the abundance of research related to autonomous vehicles, few papers are found on the coexistence of autonomous and conventional. The behavior of the autonomous vehicles is often approached to analyze aspects such as the technology involved for the communication between the vehicles or the safety of these devices. This research has the objective of evaluating the impact, from the logistic point of view, of the traffic behavior in routes with conventional and autonomous vehicles simultaneously. Through computer simulation using traditional and open source tools, this paper analyzes the dynamic behavior of vehicles, as the growing inclusion of autonomous vehicles in some of the streets of the city of São Paulo. Traffic scenarios were modeled and considered in this study, and it was concluded that the simple insertion of autonomous vehicles into the system does not reflect the uniform improvement of traffic, ie some routes, depending on their extension, traffic volume and number of traffic lights may undergo minor improvements in relation to the average speed, waiting time in queue and average travel time.

Automated Electric Transportation (AET) proposes a system of automated platooning vehicles electrically powered by the roadway via wireless inductive power transfer. This has the potential to provide roadway transportation that is less congested, more flexible, cleaner, safer, and faster than the current system. The focus of this research is to show how platooning can be accomplished in a safe manner and what capacities such an automated platooning system can achieve. To accomplish this, first two collision models are developed to show the performance of automated platoons during an emergency braking scenario: a stochastic model coded in Matlab/Simulink and a deterministic model with closed-form solutions. The necessary parameters for safe platooning are then defined: brake variances, communication delays, and maximum acceptable collision speeds. The two collision models are compared using the Student's t-test to show their equivalence. It is shown that while the two do not yield identical results, in most cases the results of the deterministic model are more conservative than and reasonably close to the results of the deterministic model. The deterministic model is then used to develop a capacity model describing automated platooning flow as a function of speed and platoon size. For conditions where platooning is initially unsafe, three amelioration protocols are evaluated: brake derating, collaborative braking, and increasing the maximum acceptable collision speed. Automated platooning flow is evaluated for all of these scenarios, compared both with each other and with traditional roadway flow patterns. The results of these models show that when platooning is initially safe, very high vehicle flows are possible: for example, over 12,000 veh/hr for initial speeds of 30 m/s and 10 vehicle platoons. Varying system paramaters can have large ramifications for overall capacity. For example, autonomous (non-platooning) vehicles do not promise anywhere near this level, and in many cases struggle to approach the capacity of traditional roadways. Additionally, ensuring safety under an emergency braking standard requires very small communication delays and, most importantly, tight braking variances between the vehicles within a platoon. As proposed by AET, a single type of electric vehicle, combined with modern wireless communications, can make platooning safer than was previously possible without requiring amelioration. Both brake derating and collaborative braking can make platooning safer, but they reduce capacity and may not be practical for real-world implementation. Stricter versions of these, cumulative brake derating and exponential collaborative braking, are also evaluated. Both can degrade capacity to near current roadway levels, especially if a large degree of amelioration is required. Increasing maximum acceptable collision speed, such as through designing vehicles to better withstand rear-end collisions, shows more promise in enabling safe intraplatoon interactions, especially for scenarios with small communication delays (i.e. under 50 ms).

For decades, Remotely Operated underwater Vehicles (ROVs) have been helping mankind explore the depths of the ocean, and build and maintain infrastructure on the seafloor. Since the first ROV was developed in 1953, the number of uses for these vehicles has exploded. They are now an essential part of maintaining the world's energy resources, collecting scientific data about our oceans, and performing underwater search and recovery. This research will discuss guidance, navigation, and control algorithms for use as a low-level position controller for ROVs, which will enable semi-autonomous behaviour for the vehicle. Semi-autonomous behaviour is when the pilot issues high-level position commands and the low-level controller handles station keeping and maneuvering between the commanded positions. In this configuration, the low level controller compensates for the environmental disturbances and unknown dynamics (such as current and tether dynamics), allowing the pilot to focus on other aspects of the task (such as manipulator control). In this work, the design,implementation,and testing of a complete guidance, navigation, and control system is presented. A Saab Sea-Eye Falcon ROV is augmented with a suite of navigation instruments. The augmented vehicle is characterized and a dynamic model is developed. This model is used in an extended Kalman filter, which will be shown to produce a position estimate for the vehicle with an error of less than ±6 cm. The navigation system is combined with a guidance system and adaptive controller to enable semi-autonomous behaviour. With this suite of software, the ROV can operate semi-autonomously. The resulting ROV system is a research platform, from which the underwater community can continue research into algorithms for optimal control, remote operations, and other performance enhancing technologies. / Graduate / 0771 / 0547 / allycin2@gmail.com

Robots require high-quality maps - internal representations of their operating workspace - to localise, path plan, and perceive their environment. Until recently, these maps were restricted to sparse, 2D representations due to computational, memory, and sensor limitations. With the widespread adoption of high-quality sensors and graphics processors for parallel processing, these restrictions no longer apply: dense 3D maps are feasible to compute in real time (i.e., at the input sensor's frame rate). This thesis presents the theory and system to create large-scale dense 3D maps (i.e., reconstruct continuous surface models) using only sensors found on modern autonomous automobiles: 2D laser, 3D laser, and cameras. In contrast to active RGB-D cameras, passive cameras produce noisy surface observations and must be regularised in both 2D and 3D to create accurate reconstructions. Unfortunately, straight-forward application of 3D regularisation causes undesired surface interpolation and extrapolation in regions unexplored by the robot. We propose a method to overcome this challenge by informing the regulariser of the specific subsets of 3D surfaces upon which to operate. When combined with a compressed voxel grid data structure, we demonstrate our system fusing data from both laser and camera sensors to reconstruct 7.3 km of urban environments. We evaluate the quantitative performance of our proposed method through the use of synthetic and real-world datasets - including datasets from Stanford's Burghers of Calais, University of Oxford's RobotCar, University of Oxford's Dense Reconstruction, and Karlsruhe Institute of Technology's KITTI - compared to ground-truth laser data. With only stereo camera inputs, our regulariser reduces the 3D reconstruction metric error between 27% to 36% with a final median accuracy ranging between 4 cm to 8 cm. Furthermore, by augmenting our system with object detection, we remove ephemeral objects (e.g., automobiles, bicycles, and pedestrians) from the input sensor data and target our regulariser to interpolate the occluded urban surfaces. Augmented with Kernel Conditional Density Estimation, our regulariser creates reconstructions with median errors between 5.64 cm and 9.24 cm. Finally, we present a machine-learning pipeline that learns, in an automatic fashion, to recognise the errors in dense reconstructions. Our system trains on image and laser data from a 3.8 km urban sequence. Using a separate 2.2 km urban sequence, our pipeline consistently identifies error-prone regions in the image-based dense reconstruction.

With autonomous trucks on the road where the driver is absent requires new diagnostic methods. The driver possess several abilities which a machine does not. In this thesis, the use of machine learning as a method was investigated. A more concrete problem description was formed where the main objective was detecting anomalies in wheel configurations. More specifically, the machine learning model was used to detect incorrect wheel settings. Three different algorithms was used, SVM, LDA and logistic regression. Overall, the classifier predicts with high accuracy supporting that machine learning can be used for diagnosing autonomous vehicles.