No description available.

No description available.

This thesis is concerned with the problem of situational awareness in autonomous vehicles. In this context, situational awareness refers to the ability of an autonomous vehicle to perceive the road layout ahead, interpret the implied semantics and gain an awareness of its surrounding - thus reading the road ahead. Autonomous vehicles require a high level of situational awareness in order to operate safely and efficiently in real-world dynamic environments. A system is therefore needed that is able to model the expected road layout in terms of semantics, both under normal and roadwork conditions. This thesis takes a three-pronged approach to this problem: Firstly, we consider reading the road surface. This is formulated in terms of probabilistic road marking classification and interpretation. We then derive the road boundaries using only a 2D laser and algorithms based on geometric priors from Highway Traffic Engineering principles. Secondly, we consider reading the road scene. Here, we formulate a roadwork scene recognition framework based on opponent colour vision in humans. Finally, we provide a data representation for situational awareness that unifies reading the road surface and reading the road scene. This thesis therefore frames situational awareness in autonomous vehicles in terms of both static and dynamic road semantics - and detailed formulations and algorithms are discussed. We test our algorithms on several benchmarking datasets collected using our autonomous vehicle on both rural and urban roads. The results illustrate that our road boundary estimation, road marking classification, and roadwork scene recognition frameworks allow autonomous vehicles to truly and meaningfully read the semantics of the road ahead, thus gaining a valuable sense of situational awareness even at challenging layouts, roadwork sites, and along unknown roadways.

Pesquisadores de diversas áreas estão estudando o desenvolvimento do que chamamos de Cidades Inteligentes: a integração de Sistemas de Informação e Comunicação com tecnologias de Internet das Coisas para utilizar os recursos de uma cidade de forma mais inteligente. Um dos principais objetivos das cidades inteligentes é solucionar os problemas relacionados à mobilidade urbana, que afeta significativamente a qualidade de vida da população. Um problema observável nas grandes metrópoles é a qualidade dos seus serviços de transporte público, especialmente quando nos referimos ao modal ônibus. A falta de informações confiáveis, associada à baixa qualidade dos serviços de transporte coletivo disponibilizados, leva o usuário a não optar pela utilização desse recurso, o que agrava problemas urbanos sociais e ambientais. Para reverter esse cenário, as iniciativas em cidades inteligentes propõem o uso de Sistemas de Transportes Inteligentes que podem utilizar diversos sensores e equipamentos para coletar diferente tipos de dados referente aos serviços de transporte público. A captura e processamento desses dados permite, em tese, permite que o cidadão possa utilizar o transporte público com confiabilidade e previsibilidade. Contudo, esses dados podem ser insuficientes ou de baixa qualidade para uso em tempo real. Neste trabalho de mestrado investigamos o uso de dados obtidos via colaboração coletiva (crowdsourcing) como complemento dessas informações. Para mitigar as incertezas introduzidas pelo uso de crowdsourcing, este trabalho propõe a utilização de técnicas de aprendizado de máquina para criação de métodos de análise de confiabilidade dos dados coletados para o sistema de transporte público (por ônibus) do município de São Paulo. Para mitigar as incertezas introduzidas pelo uso de crowdsourcing, este trabalho propõe e compara o uso de diferentes técnicas de aprendizado de máquina para criar um modelo de análise de confiabilidade para os dados coletados, especializado no sistema de transporte coletivo (por ônibus) da cidade de São Paulo. Os resultados demostram, que os algoritmos de Árvore de Decisão e Gaussian Naive Bayes foram mais eficazes e eficientes na realização da atividade de classificação dos dados obtidos com crowdsourcing. O algoritmo de Árvore de Decisão, apresentou os melhores indicadores de desempenho em termos de acurácia (94,34\\%) e F-score (99\\%), e o segundo melhor tempo de execução (0,023074 segundo). Já o algoritmo de Gaussian Naive Bayes foi o mais eficiente, com tempo médio de execução de 0,003182 segundos e foi o quarto melhor resultado em termos de acurácia (98,18\\%) e F-score (97\\%) / Researchers from different areas are studying the development of what we call Smart Cities: integrating Information and Communication Systems with Internet of Things to use city resources more intelligently. A major objective of smart cities is to solve problems related to urban mobility that significantly affects the quality of life of the population. An observable problem in big cities is the quality of their public transport services, specifically when we refer to the bus modal. The lack of reliable information, associated with the poor quality of public transport services, encouraging the user to look for alternatives, which aggravates urban social and environmental problems. To reverse this scenario, smart cities initiatives propose the use Intelligent Transport Systems, that can use various sensors and equipment to collect several types of data on public transport services. The capture and processing of these data allows, in theory, citizens to use the public transport with reliability and predictability. However, this data can be insufficient or of poor quality for usage in real-time. This master\'s work investigates the use of crowdsourcing data as a complement to this information. To mitigate the uncertainties introduced by the use of crowdsourcing, this research proposes and compares the use of different machine learning techniques to create a reliability analysis model for the data collected that is specialized for use on public transport system (bus) in the city of São Paulo. The results show that the Decision Tree and Gaussian Naive Bayes algorithms are more effective and efficient in performing the classification activity of the data obtained with crowdsourcing. The Decision Tree algorithm presented the best performance indicators in terms of accuracy (94.34\\%) and F-score (99\\%), and the second best execution time (0.023074 seconds). The Gaussian Naive Bayes algorithm was the most efficient, with an average execution time of 0.003182 seconds and was the forth best result in terms of accuracy (98.18\\%) and F-score (97\\%)

Pesquisadores de diversas áreas estão estudando o desenvolvimento do que chamamos de Cidades Inteligentes: a integração de Sistemas de Informação e Comunicação com tecnologias de Internet das Coisas para utilizar os recursos de uma cidade de forma mais inteligente. Um dos principais objetivos das cidades inteligentes é solucionar os problemas relacionados à mobilidade urbana, que afeta significativamente a qualidade de vida da população. Um problema observável nas grandes metrópoles é a qualidade dos seus serviços de transporte público, especialmente quando nos referimos ao modal ônibus. A falta de informações confiáveis, associada à baixa qualidade dos serviços de transporte coletivo disponibilizados, leva o usuário a não optar pela utilização desse recurso, o que agrava problemas urbanos sociais e ambientais. Para reverter esse cenário, as iniciativas em cidades inteligentes propõem o uso de Sistemas de Transportes Inteligentes que podem utilizar diversos sensores e equipamentos para coletar diferente tipos de dados referente aos serviços de transporte público. A captura e processamento desses dados permite, em tese, permite que o cidadão possa utilizar o transporte público com confiabilidade e previsibilidade. Contudo, esses dados podem ser insuficientes ou de baixa qualidade para uso em tempo real. Neste trabalho de mestrado investigamos o uso de dados obtidos via colaboração coletiva (crowdsourcing) como complemento dessas informações. Para mitigar as incertezas introduzidas pelo uso de crowdsourcing, este trabalho propõe a utilização de técnicas de aprendizado de máquina para criação de métodos de análise de confiabilidade dos dados coletados para o sistema de transporte público (por ônibus) do município de São Paulo. Para mitigar as incertezas introduzidas pelo uso de crowdsourcing, este trabalho propõe e compara o uso de diferentes técnicas de aprendizado de máquina para criar um modelo de análise de confiabilidade para os dados coletados, especializado no sistema de transporte coletivo (por ônibus) da cidade de São Paulo. Os resultados demostram, que os algoritmos de Árvore de Decisão e Gaussian Naive Bayes foram mais eficazes e eficientes na realização da atividade de classificação dos dados obtidos com crowdsourcing. O algoritmo de Árvore de Decisão, apresentou os melhores indicadores de desempenho em termos de acurácia (94,34\\%) e F-score (99\\%), e o segundo melhor tempo de execução (0,023074 segundo). Já o algoritmo de Gaussian Naive Bayes foi o mais eficiente, com tempo médio de execução de 0,003182 segundos e foi o quarto melhor resultado em termos de acurácia (98,18\\%) e F-score (97\\%) / Researchers from different areas are studying the development of what we call Smart Cities: integrating Information and Communication Systems with Internet of Things to use city resources more intelligently. A major objective of smart cities is to solve problems related to urban mobility that significantly affects the quality of life of the population. An observable problem in big cities is the quality of their public transport services, specifically when we refer to the bus modal. The lack of reliable information, associated with the poor quality of public transport services, encouraging the user to look for alternatives, which aggravates urban social and environmental problems. To reverse this scenario, smart cities initiatives propose the use Intelligent Transport Systems, that can use various sensors and equipment to collect several types of data on public transport services. The capture and processing of these data allows, in theory, citizens to use the public transport with reliability and predictability. However, this data can be insufficient or of poor quality for usage in real-time. This master\'s work investigates the use of crowdsourcing data as a complement to this information. To mitigate the uncertainties introduced by the use of crowdsourcing, this research proposes and compares the use of different machine learning techniques to create a reliability analysis model for the data collected that is specialized for use on public transport system (bus) in the city of São Paulo. The results show that the Decision Tree and Gaussian Naive Bayes algorithms are more effective and efficient in performing the classification activity of the data obtained with crowdsourcing. The Decision Tree algorithm presented the best performance indicators in terms of accuracy (94.34\\%) and F-score (99\\%), and the second best execution time (0.023074 seconds). The Gaussian Naive Bayes algorithm was the most efficient, with an average execution time of 0.003182 seconds and was the forth best result in terms of accuracy (98.18\\%) and F-score (97\\%)

<p>This master thesis is to highlight the importance of what needs to be identified in the CVIS system, how this could be done, how different techniques affect privacy and security and how the privacy and security mechanisms can be improved for the whole system. The report starts with a background of ERTICO – ITS Europe, followed by a description of how the CVIS project is organized, how the CVIS system will work, and a presentation of privacy, security and identification, both in general and in CVIS. After this follows the analysis and the report is finally wrapped up with conclusions and recommendations.</p><p>Why this is an important topic to highlight and discuss and the reason being for this master thesis, is because there is a clear need within the CVIS consortium to harmonise these topics. As it is today, different persons and different sub-projects have different views and opinions on what needs to be identified for example. This needs to be harmonised in order for everyone to know what is being developed, but also, and much more importantly, to in the end get acceptance for the CVIS system. If people do not feel they can trust the system, if they feel it is not secure or that it violates their privacy, they will not use it, even if it has been proved the technique works.</p><p>The key question discussed in the report is what needs to be identified. This is the most important question to solve. There must be very good reasons and consensus why a certain entity is to be identified, otherwise identification of that entity will always be questioned. This also links very tightly with privacy.</p><p>The objective of this master thesis is to bring forward this critical question about identification, to highlight different reasons for identifying or not identifying different entities and to get the discussion started.</p><p>Finally, the main conclusions and recommendations on what to actually identify is the vehicle and the different parts in the central sub-system. The best technique would be by using single sign on with a very strong encryption, for example random numbers, that will be handle by a new node Identification Management Centre or that it will be a part of the Host Management Centre. To ensure privacy in the system, the single sign on mechanism should be combined with the approach of using pseudonyms when communicating in the CVIS system.</p>

This study assesses how to measure and evaluate performance impacts of IntelligentTransport Systems (ITS) in the transport chain.The importance of transportation in global trade has increased significantly in the lastdecades. Cost pressure, rising customer demand for sophisticated logistics services, sustainabilityand security as well as safety issues have boosted the need for more efficient,effective and differentiated transport operations. Intelligent Transport Systems werefound to have the potential to address these challenges in the transport chain. However,due to the novelty of the technology both ITS developers and users face huge uncertaintyabout the performance impacts of ITS. Evaluating ITS in the transport chain beforethe rollout based on concrete measures is likely to reduce the uncertainty involvedin ITS developments and enhance the adoption rate of the new technology. The increasingnumber of ITS projects, like the Secure Intermodal Transport Systems at VolvoTechnology, create a need for a structured approach to measure and evaluate ITS.A literature review concerning the characteristics of the transport industry, technologyadoption, ITS and performance measurements served as a basis for the empirical studyin which 8 semi-structured interviews with different stakeholders in the transport industrywere conducted in order to find out how the performance impacts of ITS are perceivedin the industry and how they could possibly be assessed. The focus groupmethod was used to validate and apply the findings from the interview study to a GeofencingITS-service.The study has confirmed that the concept of ITS is still an emerging phenomenon in thetransportation industry. There is no common understanding of ITS among researchersand practitioners in the transport industry and still a lack of knowledge regarding theperformance impacts of ITS. Even though it could be found that ITS leverages mainlythe service level that can be offered to the customer and that they increase the efficiencyin the back office, the great variety of ITS-services calls for an individual assessment.Structuring the assessment into the phases of measurement design, implementation anduse of the measures facilitates this process. For the different phases a set of activitiescritical for a successful assessment of ITS have been identified. Despite its usefulnessfor mitigating the uncertainty related to the new technology, the focus group validationuncovered that a comprehensive measurement for ITS is not appropriate from the outset,but should be assessed based on the cost of the measurement, the ITS project priority,the customer relations as well as the hierarchical structure in the provider firm.

This master thesis is to highlight the importance of what needs to be identified in the CVIS system, how this could be done, how different techniques affect privacy and security and how the privacy and security mechanisms can be improved for the whole system. The report starts with a background of ERTICO – ITS Europe, followed by a description of how the CVIS project is organized, how the CVIS system will work, and a presentation of privacy, security and identification, both in general and in CVIS. After this follows the analysis and the report is finally wrapped up with conclusions and recommendations. Why this is an important topic to highlight and discuss and the reason being for this master thesis, is because there is a clear need within the CVIS consortium to harmonise these topics. As it is today, different persons and different sub-projects have different views and opinions on what needs to be identified for example. This needs to be harmonised in order for everyone to know what is being developed, but also, and much more importantly, to in the end get acceptance for the CVIS system. If people do not feel they can trust the system, if they feel it is not secure or that it violates their privacy, they will not use it, even if it has been proved the technique works. The key question discussed in the report is what needs to be identified. This is the most important question to solve. There must be very good reasons and consensus why a certain entity is to be identified, otherwise identification of that entity will always be questioned. This also links very tightly with privacy. The objective of this master thesis is to bring forward this critical question about identification, to highlight different reasons for identifying or not identifying different entities and to get the discussion started. Finally, the main conclusions and recommendations on what to actually identify is the vehicle and the different parts in the central sub-system. The best technique would be by using single sign on with a very strong encryption, for example random numbers, that will be handle by a new node Identification Management Centre or that it will be a part of the Host Management Centre. To ensure privacy in the system, the single sign on mechanism should be combined with the approach of using pseudonyms when communicating in the CVIS system.

With perpetual strains on resources, road agencies need to develop network-level decision-making frameworks to ensure optimum resource allocation. This is especially true for incident management services and in particular variable message signs (VMS), which are relatively immature disciplines compared to traditional road engineering. The objective of incident management and VMS is to minimise the safety, efficiency, reliability and environmental impacts of incidents on the operations of the transport system. This may be achieved by informing travellers of the incidents so they can adapt their behaviour in a manner that reduces community impacts, such as lateness and the associated vehicle emissions, unreliability of travel times, as well as secondary accidents due to incidents. Generally, road authorities do carry out needs assessments, but qualitatively in many cases. Therefore, this masters research presents a framework that is systematic, quantitative and relatively easy to implement. In order to prioritise VMS infrastructure deployment, a risk management approach was taken that focuses on minimising the impacts on, and costs to the community. In the framework and case study conducted, safety, efficiency and reliability, and environmental impacts are quantified using an economic risk management approach to determine an overall risk score. This score can be used to rank road sections within the network, indicating the roads with the highest risk of incident network impacts and therefore the roads with the highest need for intervention. A cost-effectiveness based risk-reduction ranking can then be determined for each incident management treatment type, comparing the net risk with treatment to that without treatment, and dividing by the net present value of deployment. The two types of ranking, pure risk and cost-effectiveness based risk reduction, will help to minimise the network impacts on the community and optimise resource allocation.

Road freight transport travel time estimation is an important task in fleet management and traffic planning. Goods often must be delivered in a predefined time window and any deviation may lead to serious consequences. It is possible to improve travel time estimation by considering more factors that may affect it. In this thesis work we identify factors that may affect travel time, find possible sources of information about them, propose a model for estimating travel time of heavy goods vehicles, and verify this model on real data. As results, the experiments showed that considering time related and weather related factors, it is possible to improve accuracy of travel time estimation. Also, it was shown that the influence of a particular factor on travel time depended on the considered road segment. Furthermore, it was shown that different data mining algorithms should be applied for different road segments in order to get the best estimation.