No description available.

Virtual visualization of mobile robot analytical trajectories while avoiding moving obstacles is presented in this thesis as a very helpful technique to properly display and communicate simulation results. Analytical solutions to the path planning problem of mobile robots in the presence of obstacles and a dynamically changing environment have been presented in the current robotics and controls literature. These techniques have been demonstrated using two-dimensional graphical representation of simulation results. In this thesis, the analytical solution published by Dr. Zhihua Qu in December 2004 is used and simulated using a virtual visualization tool called VRML.

Scene perception and traversability analysis are real challenges for autonomous driving systems. In the context of off-road autonomy, there are additional challenges due to the unstructured environments and the existence of various vegetation types. It is necessary for the Autonomous Ground Vehicles (AGVs) to be able to identify obstacles and load-bearing surfaces in the terrain to ensure a safe navigation (McDaniel et al. 2012). The presence of vegetation in off-road autonomy applications presents unique challenges for scene understanding: 1) understory vegetation makes it difficult to detect obstacles or to identify load-bearing surfaces; and 2) trees are usually regarded as obstacles even though only trunks of the trees pose collision risk in navigation. The overarching goal of this dissertation was to study traversability analysis in unstructured forested terrains for off-road autonomy using LIDAR data. More specifically, to address the aforementioned challenges, this dissertation studied the impacts of the understory vegetation density on the solid obstacle detection performance of the off-road autonomous systems. By leveraging a physics-based autonomous driving simulator, a classification-based machine learning framework was proposed for obstacle detection based on point cloud data captured by LIDAR. Features were extracted based on a cumulative approach meaning that information related to each feature was updated at each timeframe when new data was collected by LIDAR. It was concluded that the increase in the density of understory vegetation adversely affected the classification performance in correctly detecting solid obstacles. Additionally, a regression-based framework was proposed for estimating the understory vegetation density for safe path planning purposes according to which the traversabilty risk level was regarded as a function of estimated density. Thus, the denser the predicted density of an area, the higher the risk of collision if the AGV traversed through that area. Finally, for the trees in the terrain, the dissertation investigated statistical features that can be used in machine learning algorithms to differentiate trees from solid obstacles in the context of forested off-road scenes. Using the proposed extracted features, the classification algorithm was able to generate high precision results for differentiating trees from solid obstacles. Such differentiation can result in more optimized path planning in off-road applications.

No description available.

No description available.

No description available.

O emprego de veículos terrestres autônomos tem se tornado cada vez mais comum nos últimos anos em aplicações civis e militares. Eles podem ser úteis para as pessoas com necessidades especiais e para reduzir os acidentes de trânsito e o número de baixas em combate. Esta tese aborda o problema da classificação de obstáculos e da localização do veículo em relação a um mapa topológico, sem fazer uso de GPS e de mapas digitais detalhados. Um sensor laser 3D é usado para coletar dados do ambiente. O sistema de classificação de obstáculos extrai as features da nuvem de pontos e usam-nas para alimentar um classificador que separa os dados em quatro classes: veículos, pessoas, construções, troncos de árvores e postes. Durante a extração de features, um método original para transformar uma nuvem 3D em um grid 2D é proposto, o que ajuda a reduzir o tempo de processamento. As interseções de vias de áreas urbanas são detectadas e usadas como landmarks em um mapa topológico. O sistema consegue obter a localização do veículo, utilizando os pontos de referência, e identifica as mudanças de direção do veículo quando este passa pelos cruzamentos. Os experimentos demonstraram que o sistema foi capaz de classificar corretamente os obstáculos e localizar-se sem o uso de sinais de GPS. / The employment of autonomous ground vehicles, both in civilian and military applications, has become increasingly common over the past few years. Those vehicles can be helpful for disabled people and also to reduce traffic accidents. In this thesis, approaches to the problem of obstacles classification and the localization of the vehicle in relation to a topologic map are presented. GPS devices and previous digital maps are not employed. A 3D laser sensor is used to collect data from the environment. The obstacle classification system extracts features from point clouds and uses them to feed a classifier which separates data into four classes: vehicle, people, building and light poles/ trees. During the feature extraction, an original method to transform 3D to 2D data is proposed, which helps to reduce the processing time. Crossing roads are detected and used as landmarks in a topological map. The vehicle performs self-localization using the landmarks and identifying direction changes through the crossing roads. Experiments demonstrated that system was able to correctly classify obstacles and to localize itself without using GPS signals.

O emprego de veículos terrestres autônomos tem se tornado cada vez mais comum nos últimos anos em aplicações civis e militares. Eles podem ser úteis para as pessoas com necessidades especiais e para reduzir os acidentes de trânsito e o número de baixas em combate. Esta tese aborda o problema da classificação de obstáculos e da localização do veículo em relação a um mapa topológico, sem fazer uso de GPS e de mapas digitais detalhados. Um sensor laser 3D é usado para coletar dados do ambiente. O sistema de classificação de obstáculos extrai as features da nuvem de pontos e usam-nas para alimentar um classificador que separa os dados em quatro classes: veículos, pessoas, construções, troncos de árvores e postes. Durante a extração de features, um método original para transformar uma nuvem 3D em um grid 2D é proposto, o que ajuda a reduzir o tempo de processamento. As interseções de vias de áreas urbanas são detectadas e usadas como landmarks em um mapa topológico. O sistema consegue obter a localização do veículo, utilizando os pontos de referência, e identifica as mudanças de direção do veículo quando este passa pelos cruzamentos. Os experimentos demonstraram que o sistema foi capaz de classificar corretamente os obstáculos e localizar-se sem o uso de sinais de GPS. / The employment of autonomous ground vehicles, both in civilian and military applications, has become increasingly common over the past few years. Those vehicles can be helpful for disabled people and also to reduce traffic accidents. In this thesis, approaches to the problem of obstacles classification and the localization of the vehicle in relation to a topologic map are presented. GPS devices and previous digital maps are not employed. A 3D laser sensor is used to collect data from the environment. The obstacle classification system extracts features from point clouds and uses them to feed a classifier which separates data into four classes: vehicle, people, building and light poles/ trees. During the feature extraction, an original method to transform 3D to 2D data is proposed, which helps to reduce the processing time. Crossing roads are detected and used as landmarks in a topological map. The vehicle performs self-localization using the landmarks and identifying direction changes through the crossing roads. Experiments demonstrated that system was able to correctly classify obstacles and to localize itself without using GPS signals.

No description available.

The rapid growth of E-commerce around the world has prompted related stakeholders to place a greater emphasis on automation. Catastrophes like pandemics are boosting the public demand for quick and efficient transportation, among others. Automated vehicle technologies are associated with the last-mile delivery operations that lead to improving sustainability and Smart Cities. In this context, Autonomous Vehicles are being explored as a viable urban logistics solution.This empirical thesis conducts a feasibility study to investigate the feasibility of incorporating an Autonomous Vehicle into E-commerce operations in Stockholm, Sweden. A case study is analyzed by foodora AB, a German company that operates as a distributor of food and goods in the Swedish market. The study provides a framework that depicts the issues faced by Q- commerce, Operational Planning, and Stakeholders, respectively when introducing Autonomous Vehicles. The results of the study’s qualitative and quantitative approach show that Stockholm's infrastructure is in line with the sustainability plans and is considered ready for droid operations. According to the findings, the utilization rate that is defined as the number of orders delivered per hour can be as high as 2.4 resulting in a high degree of customer satisfaction. However, regulations, classifications, weather conditions, and internet connectivity continue to be major challenges. Autonomous Vehicles must be included in legislative consideration as a mode of transportation in the future to facilitate operations and safety measures. / Den snabba tillväxten av e-handel runtom i världen har fått närstående intressenter att lägga större vikt vid automatisering. Katastrofer som pandemier ökar allmänhetens krav på bland annat snabba och effektiva transporter. Autonoma fordon är förknippade med ”last-mile” transporter av gods som leder till förbättrad hållbarhet och smarta städer. I detta sammanhang utforskas autonoma fordon som en livskraftig citylogistik-lösning.Denna empiriska avhandling genomför en genomförbarhetsstudie för att undersöka möjligheten att integrera ett autonomt fordon i e-handelsverksamheten i Stockholm, Sverige. I synnerhet analyseras en fallstudie av foodora AB, ett tyskt företag som är verksamma som distributör av matvaror på den svenska marknaden. Studien ger ett ramverk som visar de frågor som Q-handel, operativ planering respektive intressenter står inför vid ett införande av autonoma fordon. Resultaten av studiens kvalitativa och kvantitativa tillvägagångssätt visar att Stockholms infrastruktur är i linje med hållbarhetsplanerna och till synes redo för droid leveranser. Enligt resultaten kan utnyttjandegraden, definierad som antal utförda orderleveranser inom en timme, vara så hög som 2,4, vilket resulterar i en hög grad av kundtillfredsställelse. Regler, klassificeringar, väderförhållanden och internetanslutning är dock fortfarande stora utmaningar. Autonoma fordon måste tas med i lagstiftningen som ett transportmedel i framtiden för att underlätta drift och säkerhetsåtgärder.