The increasing worldwide demand for software systems involved in society has led to the need where not only functionality is fundamental and addressed, but end-user satisfaction in terms of availability, throughput, and response time is essential and should be preserved. Thus, systems must be evaluated at preset load levels to assess the non-functional quality problems from the closest perspective of real application use. In this context, where the problem involves a high and complex search space, a search-based approach for load test generation is required. This thesis proposes and evaluates an evolutionary search-based approach for load test generation using multi-objective optimization methods consisting of selection, crossover, and mutation operators. In this thesis, load testing is addressed as a multi-objective optimization problem by using four different evolutionary algorithms: Non-dominated Storing Genetic Algorithm II (NSGA-II), Pareto Archived Evolution Strategy (PAES), The Strength Pareto Evolutionary Algorithm 2 (SPEA2), Multi-Objective Cellular Genetic Algorithm (MOCell) as well as a Random Search algorithm. Additionally, this study demonstrates the applicability of the proposed approach by running several experiments, aiming to compare the algorithms’ efficiency based on different quality indicators such as hypervolume, spread, and epsilon. Experimental results show that evolutionary search-based methods can be used to generate effective workloads. Since, all algorithms have found the optimal workload, having the hypervolume values to zero, we believe that the objectives of the problem could be combined as a single objective, hence scalarization techniques can be applicable. Based on the other quality indicators (Spread and Epsilon respectively), NSGA-II and MOCell tend to perform better compared to other algorithms. Finally, the study concludes that multi-objective evolutionary algorithms can be used for load testing purpose, obtaining better results in generating optimal workloads than an existing (adapted) model-free reinforcement learning approach.

Veículo autônomo inteligente (ou apenas veículo autônomo VA) é um tipo de sistema embarcado que integra componentes físicos (hardware) e computacionais (software). Sua principal característica é a capacidade de locomoção e de operação de modo semi ou completamente autônomo. A autonomia cresce com a capacidade de percepção e de deslocamento no ambiente, robustez e capacidade de resolver e executar tarefas lidando com as mais diversas situações (inteligência). Veículos autônomos representam um tópico de pesquisa importante e que tem impacto direto na sociedade. No entanto, à medida que esse campo avança alguns problemas secundários aparecem como, por exemplo, como saber se esses sistemas foram suficientemente testados. Uma das fases do teste de um VA é o teste de campo, em que o veículo é levado para um ambiente pouco controlado e deve executar livremente a missão para a qual foi programado. Ele é geralmente utilizado para garantir que os veículos autônomos mostrem o comportamento desejado, mas nenhuma informação sobre a estrutura do código é utilizada. Pode ocorrer que o veículo (hardware e software) passou no teste de campo, mas trechos importantes do código nunca tenham sido executados. Durante o teste de campo, os dados de entrada são coletados em logs que podem ser posteriormente analisados para avaliar os resultados do teste e para realizar outros tipos de teste offline. Esta tese apresenta um conjunto de propostas para apoiar a análise do teste de campo do ponto de vista do teste estrutural. A abordagem é composta por um modelo de classes no contexto do teste de campo, uma ferramenta que implementa esse modelo e um algoritmo genético para geração de dados de teste. Apresenta também heurísticas para reduzir o conjunto de dados contidos em um log sem diminuir substancialmente a cobertura obtida e estratégias de combinação e mutação que são usadas no algoritmo. Estudos de caso foram conduzidos para avaliar as heurísticas e estratégias e são também apresentados e discutidos. / Intelligent autonomous vehicle (or just autonomous vehicle - AV) is a type of embedded system that integrates physical (hardware) and computational (software) components. Its main feature is the ability to move and operate partially or fully autonomously. Autonomy grows with the ability to perceive and move within the environment, robustness and ability to solve and perform tasks dealing with different situations (intelligence). Autonomous vehicles represent an important research topic that has a direct impact on society. However, as this field progresses some secondary problems arise, such as how to know if these systems have been sufficiently tested. One of the testing phases of an AV is the field testing, where the vehicle is taken to a controlled environment and it should execute the mission for which it was programed freely. It is generally used to ensure that autonomous vehicles show the intended behavior, but it usually does not take into consideration the code structure. The vehicle (hardware and software) could pass the field testing, but important parts of the code may never have been executed. During the field testing, the input data are collected in logs that can be further analyzed to evaluate the test results and to perform other types of offline tests. This thesis presents a set of proposals to support the analysis of field testing from the point of view of the structural testing. The approach is composed of a class model in the context of the field testing, a tool that implements this model and a genetic algorithm to generate test data. It also shows heuristics to reduce the data set contained in a log without reducing substantially the coverage obtained and combination and mutation strategies that are used in the algorithm. Case studies have been conducted to evaluate the heuristics and strategies, and are also presented and discussed.

Veículo autônomo inteligente (ou apenas veículo autônomo VA) é um tipo de sistema embarcado que integra componentes físicos (hardware) e computacionais (software). Sua principal característica é a capacidade de locomoção e de operação de modo semi ou completamente autônomo. A autonomia cresce com a capacidade de percepção e de deslocamento no ambiente, robustez e capacidade de resolver e executar tarefas lidando com as mais diversas situações (inteligência). Veículos autônomos representam um tópico de pesquisa importante e que tem impacto direto na sociedade. No entanto, à medida que esse campo avança alguns problemas secundários aparecem como, por exemplo, como saber se esses sistemas foram suficientemente testados. Uma das fases do teste de um VA é o teste de campo, em que o veículo é levado para um ambiente pouco controlado e deve executar livremente a missão para a qual foi programado. Ele é geralmente utilizado para garantir que os veículos autônomos mostrem o comportamento desejado, mas nenhuma informação sobre a estrutura do código é utilizada. Pode ocorrer que o veículo (hardware e software) passou no teste de campo, mas trechos importantes do código nunca tenham sido executados. Durante o teste de campo, os dados de entrada são coletados em logs que podem ser posteriormente analisados para avaliar os resultados do teste e para realizar outros tipos de teste offline. Esta tese apresenta um conjunto de propostas para apoiar a análise do teste de campo do ponto de vista do teste estrutural. A abordagem é composta por um modelo de classes no contexto do teste de campo, uma ferramenta que implementa esse modelo e um algoritmo genético para geração de dados de teste. Apresenta também heurísticas para reduzir o conjunto de dados contidos em um log sem diminuir substancialmente a cobertura obtida e estratégias de combinação e mutação que são usadas no algoritmo. Estudos de caso foram conduzidos para avaliar as heurísticas e estratégias e são também apresentados e discutidos. / Intelligent autonomous vehicle (or just autonomous vehicle - AV) is a type of embedded system that integrates physical (hardware) and computational (software) components. Its main feature is the ability to move and operate partially or fully autonomously. Autonomy grows with the ability to perceive and move within the environment, robustness and ability to solve and perform tasks dealing with different situations (intelligence). Autonomous vehicles represent an important research topic that has a direct impact on society. However, as this field progresses some secondary problems arise, such as how to know if these systems have been sufficiently tested. One of the testing phases of an AV is the field testing, where the vehicle is taken to a controlled environment and it should execute the mission for which it was programed freely. It is generally used to ensure that autonomous vehicles show the intended behavior, but it usually does not take into consideration the code structure. The vehicle (hardware and software) could pass the field testing, but important parts of the code may never have been executed. During the field testing, the input data are collected in logs that can be further analyzed to evaluate the test results and to perform other types of offline tests. This thesis presents a set of proposals to support the analysis of field testing from the point of view of the structural testing. The approach is composed of a class model in the context of the field testing, a tool that implements this model and a genetic algorithm to generate test data. It also shows heuristics to reduce the data set contained in a log without reducing substantially the coverage obtained and combination and mutation strategies that are used in the algorithm. Case studies have been conducted to evaluate the heuristics and strategies, and are also presented and discussed.

In recent years, there have been remarkable advancements in automated driving systems. Consumer protection organizations, such as Euro NCAP, play a pivotal role in enhancing the overall safety of these modern vehicles. While previous emphasis has been on passive safety, the significance of active safety systems has surged in recent years. Evaluating the performance of these systems now relies on standardized test scenarios designed to simulate real-world accidents. Addressing this challenge, the future necessitates the incorporation of virtual methods to supplement traditional track tests. Given the complex nature of high-dimensional test cases, an exhaustive grid search is exceedingly time-consuming. In light of this challenge, we present a novel testing method utilizing search-based testing with Bayesian Optimization to efficiently navigate and explore the expansive search space of Euro NCAP CCR scenarios to identify the performance-critical scenarios. The methodology incorporates the Brake Threat Number as a robust criticality metric within the fitness function, providing a reliable indicator for assessing the inevitability of collisions. Furthermore, the research utilizes a surrogate model derived from the evaluation points used by the optimization algorithm to determine the performance-critical boundary that separates the critical and the non-critical scenarios. Additionally, this approach leverages the surrogate model for conducting sensitivity analysis, explaining the impact of individual parameters on the system’s output.