Abstract
This work is focused on the development of system able to keep tracking driver's behavior without a black box device mounted inside the car. Firstly, we intend to explore the data from GPS (Global Positioning System), accelerometer, gyroscope and magnetometer for a full characterization of the vehicle dynamics. Secondly, we develop an event detector that determines and classifies distinct kind of maneuvers, like turns, lane change, U-turns, among others. Finally, we developed a simple aggressiveness classifier using fuzzy logic. Experiments have been conducted and the initial results of the system were found to be encouraging on the implementation of a non-intrusive system for driver analysis.

Abstract
Recently, model-based approaches have been proposed for fault diagnosis as an emerging alternative to traditional techniques. Particularly, the inversion-and observer-based were proposed for fault diagnosis as successful model-based approaches. However, the research's results related to these approaches are reduced and generally applied to a specific converter or control type. Therefore, the inversion-and observer-based approaches performance presented in the literature does not permit to compare both techniques in order to conclude which one is more suitable for fault diagnosis. In this context, this paper presents a comparative study of inversion-and observer based approaches for fault diagnosis in a DC-DC boost converter. More specifically, after modeling both the power converter and the fault detection and isolation methods, it were inserted faults on the transistor and capacitor (degradation) in order to validate the performance of the proposed approaches. The results demonstrate that these are efficient alternatives to the conventional techniques that are usually used for fault diagnosis in power electronics systems. Both inverse-and observer-based approaches showed similarities and effectiveness in detecting and isolating faults on the studied DC-DC boost converter.

Abstract
This study presents a scheme to detect and isolate faults in over-actuated electric vehicles. Although this research work is still emerging, it already provides a view of the main challenges on the problem and discusses some possible approaches that can be useful to overcome the key difficulties. This paper intends to present a fault detection algorithm based on Unknown Input Observer (UIO). The residuals are built through the difference of signals between the measured outputs and the output estimations from the observer. The main idea is to detect fault in the electric motors and steering wheel actuator. The algorithm is presented and tested with some fault scenarios using the co-simulation tool between Simulink/MATLAB and the high-fidelity model from Carsim software.

Abstract
While a great number of battery balancing circuit topologies have been proposed, the unique control objective typically pursued is equalization of single cell charge. However, a balancing circuit could offer potentially more control features, especially with topologies able to provide bidirectional power flow control. This has not been explored yet in literature or at least not with enough thoroughness. Thus, in addition to charge balancing, up to three more objectives could be pursued simultaneously. Firstly, virtual resistance control, in order to provide dynamic compensation for variations in terminal cell voltage. Secondly, thermal management, to achieve a more uniform temperature distribution within a battery pack. Third, on-board diagnosis or fault detection tools, e.g. to perform characterization tests or to identify and even isolate problematic cells. In this paper, this issue is discussed and evaluated for a battery pack made up of 48 large format Li-Ion cells in series in a e-mobility application. Simulation results demonstrate the technical feasibility of this newly defined concept.

Abstract
High level vehicle automation systems are currently being studied to attenuate highway traffic and energy consumption by applying the concept of platooning, which has gained increased attention due to progresses in the next generation of mobile communication (5G). The introduction of more complex automation systems originates, however, fault entry points that hinders the system safety and resilience. This paper presents an initial control architecture for the electric vehicles platoon from a fault-tolerant control perspective. To achieve a fault-tolerant platooning structure an over-actuated electric vehicle topology is proposed which may allow the implementation of different redundancies. Furthermore, some of the major challenges in the platooning network control system (NCS) are presented and the techniques to overcome these issues are explored.

Abstract
Autonomous vehicles are becoming a reality that in the next future will most probably start populating everyday roads. Such vehicles can, on the one hand, increase safety through automated driving, and, on the other, be a means of transportation also for people with disabilities who cannot move alone on commercial cars. Within this class of vehicles, mechanical layouts that allow an actuator redundancy coupled with electric propulsion appear particularly interesting, as they make it possible to design motion controller that can optimally blend multiple objectives, both dynamic, safety and driver-oriented. This paper considers such setting and concentrates on the design of a path-following algorithm with minimum-time features, with the aim of combining performance and energy-oriented optimization of the vehicle motion. The effectiveness of the approach is assessed by means of simulation tests carried out on the CarSim vehicle simulation environment. © IFAC.