Driving Behavior Analysis (DBA) plays a pivotal role in designing intelligent transportation systems, enhancing road safety, and advancing Autonomous Vehicles (AVs). Driver identification, as a key aspect of DBA, has the potential to provide unprecedented opportunities for enhanced security and driver profiling. However, the current solutions for driver identification suffer from demanding extensive data collection, limited scalability, and inadequate generalization. Furthermore, DBA is also essential for training AVs, addressing the main challenges they face: accurately perceiving their surroundings to make informed decisions and to navigate safely, and effectively handling unforeseen scenarios. In the first part of this thesis, we concentrate on behavior analysis for driver identification and verification and design two novel schemes aiming to reduce data dependency and enhance the generalization ability of existing approaches. First, we propose a novel driver identification model, called DriverRep, which reduces data dependency by presenting a fully unsupervised triplet loss training. DriverRep is the first model that extracts the latent representations associated with each driver, called driver embeddings, in an unsupervised manner. In addition, we develop a novel model to tackle driver verification and impostor detection tasks based on DBA and extracted driver embeddings. In the second part, we focus on behavior prediction for AVs and their surrounding agents. First, we tackle behavior prediction in dynamic and complex scenarios by introducing three novel prediction models for forecasting drivers intentions and behaviors at unsignalized intersections. We then address social reasoning by proposing a novel prediction model that analyzes agent interactions using graph neural networks, making the scene understanding process more informative for AVs. Our proposed prediction model, called STAG, explicitly activates social modeling with a directed graph representation while considering spatial and temporal inter-agent correlations. We further design a novel prediction system, namely CAPHA, which conditions the future behavior of agents on grid-based plans modeled as a Markov decision process and solves the prediction task via inverse reinforcement learning to produce scene compliant behaviors. Moreover, we introduce a novel goal-based prediction model, called GMP, which encodes interactions between agents and dynamic and static context information to estimate the distribution of target goals, efficiently considering the inherent uncertainty in agents behavior. Extensive quantitative and qualitative comparisons have been conducted between the developed solutions and related benchmark schemes using various scenarios and environments. The obtained results demonstrate the potential of these solutions for the understudy tasks of DBA and real-world applications.

Emissions related to aviation have during the last decades become an important topic of discussion. Besides carbon dioxide ($CO_2$) which is the major pollutant from air travel, other gas emissions such as hydrocarbons ($HC$), nitrogen oxides ($NO_x$), carbon monoxide ($CO$) and sulfur oxides ($SO_x$) also need to be investigated. The work within this field has traditionally been challenged by the fact that aircraft emission calculations often required engine proprietary data which usually is difficult to obtain. However, in recent years other methods have been developed and this report investigates one such method, namely The Boeing Fuel Flow Method 2. The analysis is carried out on an ATR 72-500 turboprop aircraft flying at $13000$ feet from Visby to Bromma, Sweden. The method uses continuous data of fuel flow and altitude together with estimated emission index data at sea level for the specific engine to estimate the amount of emissions emitted during the flight. From this it was possible to determine the levels of $HC$,$NO_x$,$CO$, $CO_2$ and $SO_x$ emitted during the different stages of flight. There was a clear trend that $HC$ and $CO$ emissions were the highest at low fuel flow levels, i.e. at low power, while $NO_x$ increased with increasing fuel flow. Emission levels of $CO_2$ and $SO_x$ were found to be proportional to fuel flow. In addition, two alternative trajectories at $10000$ and $24000$ feet were studied. When comparing the $10000$ feet route with the original $13000$ feet route the the level of $NO_x$, $CO_2$ and $SO_x$ were unaffected while $HC$ and $CO$ decreased as the period of high fuel flow were shortened. In the $24000$ feet route the levels of $HC$, $CO$ and $SO_x$ were unaffected while the level of $CO_2$ and $NO_x$ decreased. This decrease can be explained by the lowered fuel flow rate as air resistance is significantly lower at $24000$ feet compared to $13000$ feet.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.