Abstract

the number of electric vehicles increases, the impact of their charging on distribution networks is being investigated using different load profiles. Due to the lack of real charging data, the majority of these load impact studies are making assumptions for the electric vehicle charging demand profiles. In this paper a two-step modelling framework was developed to extract the useful information hidden in real EVs charging event data. Real EVs charging demand data were obtained from Plugged-in Midlands (PiM) project, one of the eight ‘Plugged-in Places’ projects supported by the UK Office for Low Emission Vehicles (OLEV). A data mining model was developed to investigate the characteristics of electric vehicle charging demand in a geographical area. A Fuzzy-Based model aggregates these characteristics and estimates the potential relative risk level of EVs charging demand among different geographical areas independently to their actual corresponding distribution networks. A case study with real charging and weather data from three counties in UK is presented to demonstrate the modelling framework. Document type: Article

Abstract

The need to develop and deploy Beyond Visual Line of Sight (BVLOS) aerial vehicles has intensified over the last decade. As the demand for Unmanned Aircraft Systems (UAS) has increased, so too has the regulations that surrounds the industry. Strict regulations are currently in place but differ from country to country. Due to these regulations BVLOS innovators have been posed the task of exploring the means of operating flight missions with the UAV out of the sight of the pilot. Autonomous flight capability is not only fundamental to BVLOS operations for UAS but also likely to have a significant impact on the future development of passenger carrying autonomous aircraft. This review explores the technologies that have been developed to date that enable BVLOS applications. BVLOS flight operations have the potential to open a huge area of commercial opportunity however, there remain many concerns about the current capabilities of UAS to detect and avoid manned and unmanned airborne hazards that may pose a significant safety risk.

Abstract

Reliable anticipation of pedestrian trajectory is imperative for the operation of autonomous vehicles and can significantly enhance the functionality of advanced driver assistance systems. While significant progress has been made in the field of pedestrian detection, forecasting pedestrian trajectories remains a challenging problem due to the unpredictable nature of pedestrians and the huge space of potentially useful features. In this work, we present a deep learning approach for pedestrian trajectory forecasting using a single vehicle-mounted camera. Deep learning models that have revolutionized other areas in computer vision have seen limited application to trajectory forecasting, in part due to the lack of richly annotated training data. We address the lack of training data by introducing a scalable machine annotation scheme that enables our model to be trained using a large dataset without human annotation. In addition, we propose Dynamic Trajectory Predictor (DTP), a model for forecasting pedestrian trajectory up to one second into the future. DTP is trained using both human and machine-annotated data, and anticipates dynamic motion that is not captured by linear models. Experimental evaluation confirms the benefits of the proposed model. Comment: 6 pages, 5 figures. To appear in the proceedings of the 2019 IEEE Intelligent Vehicles Symposium (IV)

Abstract

Considering the traffic congestion and low energy\\ud consumption, small electric four-wheeled narrow tilting vehicles\\ud (NTV) are expected to be the new generation of city cars. In order\\ud to maintain lateral stability, the NTVs should have to lean into\\ud corners like two-wheeled vehicles. This is a challenge to keep a\\ud NTV stable during turning at different speeds. This paper aims\\ud to design a nonlinearity compensation based tilting controller\\ud for the direct tilting mechanism based NTVs. The controller\\ud adaptively compensates the nonlinearities of NTV roll dynamics\\ud in different vehicle speeds without the accurate vehicle models\\ud and, consequently, improve its robustness to rider’s behaviour. By\\ud utilising the proposed nonlinear tilting control system, both new\\ud riders and experienced riders can drive the NTVs easily with\\ud improved tilting stability. Simulations have been conducted to\\ud validate the applicability and robustness of the proposed control\\ud approach.

Abstract

Increasing automation in the automotive systems has re-focused the industry's attention on verification and validation methods and especially on the development of test scenarios. The complex nature of Advanced Driver Assistance Systems (ADASs) and Automated Driving (AD) systems warrant the adoption of new and innovative means of evaluating and establishing the safety of such systems. In this paper, the authors discuss the results from a semi-structured interview study, which involved interviewing ADAS and AD experts across the industry supply chain. \\ud \\ud Eighteen experts (each with over 10 years' of experience in testing and development of automotive systems) from different countries were interviewed on two themes: test methods and test scenarios. Each of the themes had three guiding questions which had some follow-up questions. The interviews were transcribed and a thematic analysis via coding was conducted on the transcripts. A two-stage coding analysis process was done to first identify codes from the transcripts and subsequently, the codes were grouped into categories. \\ud \\ud The analysis of transcripts for the question about the biggest challenge in the area of test methods revealed two specific themes. Firstly, the definition of pass/fail criteria and secondly the quality of requirements (completeness and consistency). The analysis of the questions on test scenarios revealed that "good" scenario is one that is able to test a safety goal and ways in which a system may fail. Based on the analysis of the transcripts, the authors propose two types of testing for ADAS and AD systems: Requirements-Based Testing (traditional method) and Hazard Based Testing. The proposed approach not only generates test scenarios for testing how the system works, but also how the system may fail.

Abstract

The main goal of the study centers on developing a model for the purpose of air traffic forecasting by using off-the-shelf data mining and machine learning techniques. Although data driven modeling has been extensively applied in the aviation sector, little research has been done in the area of air traffic forecasting. This study is inspired by previous research focused on improving the Federal Aviation Administration (FAA) Terminal Area Forecasting (TAF) methodology, which historically assumed that the US air transportation system (ATS) network structure was static. Recent developments use data mining algorithms to predict the likelihood of previously un-connected airport-pairs being connected in the future, and the likelihood of connected airport-pairs becoming un-connected. Despite the innovation of this research, it does not focus on improving the FAA’s existing methodology for forecasting future air traffic levels on existing routes, which is based on relatively simple regression and growth models. We investigate different approaches for improving and developing new features within the existing data mining applications in air traffic forecasting. We focus particularly on predicting detailed traffic information for the US ATS. Initially, a 2-stage log-log model is applied to establish the significance of different inputs and to identify issues of endogeneity and multi-colinearity, while maintaining the simplicity of current models. Although the model shows high goodness of fit, it tested positive for both mentioned issues as well as presenting problems with causality. With the objective of solving these issues, a 3-stage model that is under development is introduced. This model employs logistic regression and discrete choice modelling. As part of future work, machine learning techniques such as clustering and neural networks will be applied to improve this model’s performance.

Abstract

dvanced urban traffic control systems are often based on feed-back algorithms. For instance, current traffic control systems often operate on the basis of adaptive green phases and flexible co-ordination in road (sub) networks based on measured traffic conditions. However, these approaches are still not very efficient during unforeseen situations such as road incidents when changes in traffic are requested in a short time interval. Therefore, we need self-managing systems that can plan and act effectively in order to restore an unexpected road traffic situations into the normal order. A significant step towards this is exploiting Automated Planning techniques which can reason about unforeseen situations in the road network and come up with plans (sequences of actions) achieving a desired traffic situation. In this paper, we introduce the problem of self-management of a road traffic network as a temporal planning problem in order to effectively navigate cars throughout a road network. We demonstrate the feasibility of such a concept and discuss our preliminary evaluation in order to identify strengths and weaknesses of our approach and point to some promising directions of future research.

Abstract

The purpose of this paper is to bring together multiple literature sources which present innovative methodologies for the assessment of driver state, driving context and performance by means of technology within a vehicle and consumer electronic devices. It also provides an overview of ongoing research and trends in the area of driver state monitoring. As part of this review a model of a hybrid driver state monitoring system is proposed. The model incorporates technology within a vehicle and multiple brought-in devices for enhanced validity and reliability of recorded data. Additionally, the model draws upon requirement of data fusion in order to generate unified driver state indicator(-s) that could be used to modify in-vehicle information and safety systems hence, make them driver state adaptable. Such modification could help to reach optimal driving performance in a particular driving situation. To conclude, we discuss the advantages of integrating hybrid driver state monitoring system into a vehicle and suggest future areas of research.

Abstract

—L-band Digital Aeronautical Communication System (LDACS) is an emerging standard that aims at enhancing air traffic management by transitioning the traditional analog aeronautical communication systems to the superior and highly efficient digital domain. The standard places stringent requirements on the communication channels to allow them to coexist with critical L-band systems, requiring complex processing and filters in baseband. Approaches based on cognitive radio are also proposed since this allows tremendous increase in communication capacity and spectral efficiency. This requires high computational capability in airborne vehicles that can perform the complex filtering and masking, along with tasks associated with cognitive radio systems like spectrum sensing and baseband adaptation, while consuming very less power. This paper proposes a radio architecture based on new generation FPGAs that offers advanced capabilities like partial reconfiguration. The proposed architecture allows non-concurrent baseband modules to be dynamically loaded only when they are required, resulting in improved energy efficiency, without sacrificing performance. We evaluate the case of non-concurrent spectrum sensing logic and transmission filters on our cognitive radio platform based on Xilinx Zynq, and show that our approach results in 28.3% reduction in DSP utilisation leading to lower energy consumption at run-time.\\ud

Abstract

The specifications that define an automotive development project are established at an early point in the process and define the direction of such a development, and changing these decisions becomes more costly the further the project progresses. Tools to enable better consideration of choice can help prevent this. The tool presented is designed to aid with the decisions needed when embarking on the development of a vehicle that incorporates electric-vehicle technologies and the important choices made regarding the battery pack required by such a vehicle. The tool incorporates a sizing model for determining the number of cells and the configuration required to meet a specified battery requirement. The tool then uses a 1-d model to determine some of the basic thermal and power characteristics that can then be used to inform other parts of the design specification. When attached to a database containing cell information, the tool can pre-select candidate cells to meet the requirement, and rapid execution time of the tool means that it can be used to quickly compare between cell choices, at a level understandable by all stakeholders in the decision making process. Document type: Conference object