Indiana University-Purdue University Indianapolis (IUPUI) / Gholamjafari, Ali MSECE, Purdue University, May 2015. A Genetic Algorithm Approach to Best Scenarios Selection for Performance Evaluation of Vehicle Active Safety Systems . Major Professor: Dr. Lingxi Li. One of the most crucial tasks for Intelligent Transportation Systems is to enhance driving safety. During the past several years, active safety systems have been broadly studied and they have been playing a significant role in vehicular safety. Pedestrian Pre- Collision System (PCS) is a type of active safety systems which is used toward pedestrian safety. Such system utilizes camera, radar or a combination of both to detect the relative position of the pedestrians towards the vehicle. Based on the speed and direction of the car, position of the pedestrian, and other useful information, the systems can anticipate the collision/near-collision events and take proper actions to reduce the damage due to the potential accidents. The actions could be triggering the braking system to stop the car automatically or could be simply sending a warning signal to the driver depending on the type of the events. We need to design proper testing scenarios, perform the vehicle testing, collect and analyze data to evaluate the performance of PCS systems. It is impossible though to test all possible accident scenarios due to the high cost of the experiments and the time limit. Therefore, a subset of complete testing scenarios (which is critical due to the different types of cost such as fatalities, social costs, the numbers of crashes, etc.) need to be considered instead. Note that selecting a subset of testing scenarios is equivalent to an optimization problem which is maximizing a cost function while satisfying a set of constraints. In this thesis, we develop an approach based on Genetic Algorithm to solve such optimization problems. We then utilize crash and field database to validate the accuracy of our algorithm. We show that our method is effective and robust, and runs much faster than exhaustive search algorithms. We also present some crucial testing scenarios as the result of our approach, which can be used in PCS field testing.

No description available.

No description available.

No description available.

No description available.

No description available.

Wild hogs (sus scrofa) have caused major damage to agricultural crops in the US due to their lack of natural predators and fast reproduction rates. Wild hogs change their behavior to evade capture. Thus, control methods are thwarted and may not result in sufficient mortality to keep pace with the reproduction of wild hogs. This study extends previous invasive species literature to include increasing costs due to adaptability in two settings: the presence of hogs is deterministic or stochastic. The analysis is limited to one farmer's objective function with varying degrees of adaptability for "smartness". The findings concluded the population and harvest of wild hogs does change when there is a higher level of adaptability to control methods or, "smartness". The net benefit of the farmer decreases as adaptability and the probability of hogs' present increase for deterministic and stochastic case, respectively.

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Future wireless networks are envisioned to support a wide range of novel use cases, and connect a massive number of people and devices in an energy efficient way. Several key enabling technologies were considered to support this vision including Internet of Things (IoT) networks, aerial and stratospheric platforms, and reconfigurable intelligent surfaces (RIS). In this dissertation, we study different problems related to the integration between these technologies. First, we propose a cost-effective framework for data collection from IoT sensors using multiple unmanned aerial vehicles (UAVs). This is achieved by effcient clustering of the sensors and optimized deployment of cluster heads (CHs). Then, the number of deployed UAVs and their trajectories will be optimized to minimize the data collection flight time. The impacts of the trajectory approach, environment type, and UAVs' altitude as well as the fairness of UAVs trajectories on the data collection process are investigated. Given that IoT nodes might have different priorities and time deadlines, and respecting the limited battery capacity of UAVs, we enhance the data collection framework to account for these practical constraints. First, an algorithm for finding the minimal number of CHs and their best locations is proposed. Then, the minimal number of UAVs and their trajectories are obtained by solving the associated capacitated vehicle routing problem. The results investigate the impacts of the selected trajectory approach, the battery capacity and time deadlines on the consumed energy, number of visited CHs, and number of deployed UAVs. Next, given the energy issue on aerial platforms, we present our vision for integrating RIS in aerial and stratospheric platforms to provide energy-efficient communications. We propose a control architecture for such integration, discuss its benefits and identify potential use cases and associated research challenges. Then, to substantiate our vision, we study the link budget of RIS-assisted communications under the specular and the scattering reflection paradigms. Specifically, we analyze the characteristics of RIS-equipped stratospheric and aerial platforms and compare their communication performance with that of RIS-assisted terrestrial networks, using standardized channel models. In addition, we derive the optimal aerial platforms placements under both reflection paradigms. The obtained results provide important insights for the design of RIS-assisted communications. For instance, given that a HAPS has a large RIS surface, it provides superior link budget performance in most studied scenarios. In contrast, the limited RIS area on UAVs and the large propagation loss in low Earth orbit (LEO) satellite communications make them unfavorable candidates for supporting terrestrial users. Then, motivated by the demonstrated potential of HAPS equipped with RIS (HAPS-RIS), we propose a solution to support the stranded users in terrestrial networks through a dedicated control station (CS) and HAPS-RIS. We refer to this approach as "beyond-cell" communications. We demonstrate that this approach works in tandem with legacy terrestrial networks to support uncovered or unserved users. Optimal transmit power and RIS unit assignment strategies for the users based on different network objectives are introduced. Furthermore, to increase the percentage of admitted users in an efficient manner, a novel resource-efficient optimization problem is formulated that maximizes the number of connected UEs, while minimizing the total power consumed by the CS and RIS. Since the resulting problem is a mixed-integer nonlinear program (MINLP), a low-complexity two-stage algorithm is developed. Finally, given the different applications and various options of HAPS payload, we envision the use of a multi-mode HAPS that can adaptively switch between different modes so as to reduce energy consumption and extend the HAPS loitering time. These modes comprise a HAPS super macro base station (HAPS-SMBS) mode for enhanced computing, caching, and communication services, a HAPS relay station (HAPS-RS) mode for active communication, and a HAPSRIS mode for passive communication. This multi-mode HAPS ensures that operations rely mostly on the passive communication payload while switching to an energy-greedy active mode only when necessary. We illustrate the envisioned multi-mode HAPS, and discuss its benefits and challenges. Then, we validate the multi-mode efficiency through a case study. At the end of the dissertation, several future research directions are proposed including hybrid orthogonal and non-orthogonal multiple access (OMA/NOMA) beyond-cell communications assisted by HAPS-RIS, configuration of RIS units on stratospheric platforms, energy management for HAPS-RIS, and supporting aerial users through terrestrial RIS.

There has been remarkable progress in the field of robotics over the past few years, whether it is stationary robots that perform dynamically changing tasks in the manufacturing sector or automated guided vehicles for warehouse management or space exploration. The use of artificial intelligence (AI), especially reinforcement learning (RL), has contributed significantly to the success of various robotics tasks, proving that the shift toward intelligent control paradigms is successful and feasible. A fascinating aspect of RL is its ability to function both as low-level controller and as a high-level decision-making tool at the same time. An example of this is the manipulator robot whose task is to guide itself through an environment with irregular and recurrent obstacles. In this scenario, low-level controllers can receive the joint angles and execute smooth motion using the Joint Trajectory controllers. On a higher level, RL can also be used to define complex paths designed to avoid obstacles and self-collisions. An important aspect of successful operation of an AGV is the ability to make timely decisions. When Convolutional Neural Networks (CNN) based networks are incorporated with RL, agents can decide to direct AGVs to the destination effectively, which is mitigating the risk of catastrophic collisions. Even though many of these challenges can be addressed with classical solutions, devising such solutions takes a great deal of time and effort, making this process quite expensive. With an eye on different categories of RL applications to robotics, this study will provide an overview of the use of RL in robotic applications, examining the advantages and disadvantages of state-of-the-art applications. Additionally, we provide a targeted comparative analysis between classical robotics methods and RL-based robotics methods. Along with drawing conclusions from our analysis, an outline of the future possibilities and advancements that may accelerate the progress and autonomy of robotics in the future is provided.