Print Email Facebook Twitter ACC target performance setting via NDS big data analysis Title ACC target performance setting via NDS big data analysis Author Pizzigoni, Edoardo (TU Delft Mechanical, Maritime and Materials Engineering) Contributor Happee, R. (mentor) Wang, M. (graduation committee) Stapel, J.C.J. (graduation committee) Degree granting institution Delft University of Technology Programme Mechanical Engineering | Vehicle Engineering Date 2019-07-02 Abstract Advanced Driving Assistance Systems (ADAS) technologies like Adaptive Cruise Control (ACC) are becoming the normality for many users, and many major car manufacturers are introducing SAE level 2 and 3 automation systems into the market. The main advantage of Automated Vehicles (AV) will be the significant decrease in road accidents and casualties. However, a significant shift from conventional to automated vehicles must occur before it can have a positive impact on society. If the behaviour of the vehicle is not perceived as natural, the user will most likely not activate the ADAS features again. During this study a naturalistic dataset is used to investigate the driver behaviour, in the hope of bringing the current ACC logic to a more human-like behaviour that will feel more natural to the driver. The research question summarizes the final objective of this study: How can Naturalistic Driving Study (NDS) datasets be used in target performance setting for ACC systems? This study will answer the research question by studying human behaviour in the scene of following an accelerating vehicle. The main body of this thesis is divided in three chapters, one for each step of the research. First the information about the used datasets are provided together with the methodologies used to extract the relevant time-series data. Secondly driver behaviour models are created in order to mathematically characterize human behaviour. The strength of the created models is their ability to represent the full range of driver behaviour in terms of driving style. The aggressiveness parameter of the model can be easily adjusted to represent different percentiles of driver behaviour. This allows for a quick and effective tuning process: by changing a single parameter the driving style of the model can be fully modified. Finally, the driver behaviour models are implemented into a simulation environment. The models are simulated against an existing ACC logic in order to assess the difference in behaviour. The comparison highlighted two conclusions: first, the ACC logic behaves in a very conservative way compared to driver behaviour, especially when starting from standstill. Secondly, the kept by the ACC logic was not consistent throughout the speed range. This variation of the logic's driving style could result even more bothersome to the customer than its general conservative behaviour. The string stability of the driver behaviour models was also assessed. Although the proposed logic proved more stable than the regular ACC logic, it still cannot reach full string stability. Hopefully, with the method developed in this study, the process of getting accustomed to this new technology will become easier for the customer. Thanks to the driver behaviour models the motion of the vehicle can feel familiar and predictable, with the controller becoming part of the Human Machine Interface (HMI). As the customer gets more familiar with this technology his expectation will also increase and change, especially as the levels of automation start to increase. This will inevitably push automakers to continue to improve the technology to deliver increasingly advanced and safe vehicles. Subject ACCADASdriver modelingdriver behaviourAutomated vehiclescar followingnaturalistic driving study To reference this document use: http://resolver.tudelft.nl/uuid:da09fb40-8142-4545-8440-2c91ef7434ff Embargo date 2023-07-02 Part of collection Student theses Document type master thesis Rights © 2019 Edoardo Pizzigoni Files PDF Master_Thesis_Pizzigoni_Final.pdf 5.43 MB Close viewer /islandora/object/uuid:da09fb40-8142-4545-8440-2c91ef7434ff/datastream/OBJ/view