Search Results

The rapid advancement of Artificial Intelligence (AI) in the field of autonomous driving has led to significant breakthroughs, enabling the development of highly sophisticated driving assistant systems. However, as these systems become more prevalent, it is crucial to address the ethical considerations surrounding their deployment and operation. This research paper delves into the multifaceted domain of ethics in AI for Autonomous Driving Assistant System ADAS/AD systems, analyzing various use cases and exploring different scenarios. Ethical concerns in AI for autonomous driving encompass a wide range of topics, including safety, privacy concerns related to data collection and usage, decision-making, ethical dilemmas, accountability, and societal impact. This research focuses on intricate challenges that arise in the field of autonomous driving and investigates these issues by examining real-world use cases.

Electric vehicles are gaining popularity as an alternative to conventional gasoline-powered vehicles since they provide a cleaner and more environmentally friendly form of mobility. The market of electric vehicles is expanding, and the availability of dependable and effective sustainable charging infrastructure is needed to satisfy this expansion. This has prompted researchers to look for innovative alternative charging systems that can offer effective charging while reducing emissions such as fuel cells. In this study, the viability and sustainability of employing fuel cells as electric vehicle charging stations in Egypt, as an example of the MENA region, were studied from the technical and economic point of views. The technical analysis used a simulation for the whole fuel cell system, which was provided by MathWorks MATLAB Simulink software.

Modern automotive industry field is recently moving to more electrification level, so the presence of Battery Electric Vehicles (BEVs) is constantly increasing, along with charging technology evolution. Typically, BEVs do not use a significant portion of their battery’s capacity in day-to-day travel, which means their most valuable asset, the battery, sits idle during most of its life. Vehicle to Load (V2L) feature enables the transfer of energy from vehicle to the external loads (like utility tools, dryer, camping equipment or any other electrical appliance) which is connected to the power socket present in the Power Panel to perform AC Discharging. V2L technology lets consumers get more energy from a vehicle, even when it is turned off, improving consumer appeal. Bottomline, consumers can use this on-board Power Panel like a normal portable generator.

This paper analyzes the leakage magnetic field generated by the Bi-Directional wireless charging system of Electric Vehicle(EV) and confirms the effect of the shielding coil in the Bi-Directional wireless charging system. In particular, in EV using the Inductive Power Transfer(IPT) method, the effective shielding coil position is proposed by analyzing the contribution of the leakage magnetic field of the Ground Assembly(GA) coil and the Vehicle Assembly(VA) coil according to the power transfer direction. Simulations were conducted using the WPT3/Z2 model of the standard SAE J2954, and it was confirmed that the GA coil contributed more to the leakage magnetic field due to the relatively large size compared to the VA coil regardless of power transfer direction.

Wireless Power Transfer (WPT) is set to become an alternative to conductive charging and promises highly efficient charging of electric and plug-in-hybrid vehicles based on the previous publications of the SAE J2954 standards. However, a single common methodology for alignment of the Vehicle Assembly (VA) to the Ground Assembly (GA) for wireless charging public infrastructure was not included in the first two versions of the SAE J2954 standard. Two methodologies for alignment are evaluated in this technical paper for a future SAE J2954 standard: Differential Inductive Positioning System (DIPS) using an auxiliary magnetic field to align; and Ultra-Wide Band (UWB) Ranging using Radio Frequency triangulation to align. Data and comparison of the two alignment methodologies are shown in conjunction with analysis and input from the SAE J2954 WPT Taskforce.

Electric vehicles (EVs) are becoming increasingly recognized as an effective solution in the battle against climate change and reducing greenhouse gas emissions. Lithium-ion batteries have become the standard for energy storage in the automobile industry, widely used in EVs due to their superior characteristics compared to other batteries. The growing popularity of the Vehicle-to-grid (V2G) concept can be attributed to its surplus energy storage capacity, positive environmental impact, and the reliability and stability of the power grid. However, the increased utilization of the battery through these integrations can result in faster degradation and the need for replacement. As batteries are one of the most expensive components of EVs, the decision to deploy an EV in V2G operations may be uncertain due to the concerns of battery degradation from the owner’s perspective.

Eco Approach and Departure (Eco-AnD) is a Connected Automated Vehicle (CAV) technology aiming to reduce energy consumption for crossing a signalized intersection or set of intersections in a corridor that features vehicle-to-infrastructure (V2I) communication capability. This research focuses on developing a Dynamic Programming (DP) based algorithm for a PHEV operating in Charge Depleting mode. The algorithm used the Reduced Order Energy Model (ROM) to capture the vehicle powertrain characteristics and road grade to capture the road dynamics. The simulation results are presented for a real-world intersection and 20-25% energy benefits are shown by comparing against a simulated human driver speed profile. The vehicle-level validation of the developed algorithm is carried out by performing closed-course track testing of the optimized speed solutions on a real CAV vehicle.

As a key tool to maintain urban cleanliness and improve the road environment, road cleaning vehicles play an important role in improving the quality of life of residents. However, the traditional road cleaning vehicle requires the driver to monitor the situation of road garbage at all times and manually operate the cleaning process, resulting in an increase in the driver 's work intensity. To solve this problem, this paper proposes a road garbage recognition algorithm based on improved YOLOv5, which aims to reduce labor consumption and improve the efficiency of road cleaning. Firstly, the lightweight network MobileNet-V3 is used to replace the backbone feature extraction network of the YOLOv5 model. The number of parameters and computational complexity of the model are greatly reduced by replacing the standard convolution with the deep separable convolution, which enabled the model to have faster reasoning speed while maintaining higher accuracy.

The design of transportation vehicles, whether passenger or commercial, typically involves a lengthy process from concept to prototype and eventual manufacture. To improve competitiveness, original equipment manufacturers are continually exploring ways to shorten the design process. The application of digital tools such as computer-aided-design and computer-aided-engineering, as well as model-based computer simulation enable team members to virtually design and evaluate ideas within realistic operating environments. Recent advances in machine learning (ML)/artificial intelligence (AI) can be integrated into this paradigm to shorten the initial design sequence through the creation of digital agents. A digital agent can intelligently explore the design space to identify promising component features which can be collectively assessed within a virtual vehicle simulation.

Roundabouts are intersections at which automated cars seem currently not performing sufficiently well. Actually, sometimes, they get stuck and the traffic flow is seriously reduced. To overcome this problem a V2N-N2V (vehicle-to-network-network-to-vehicle) communication scheme is proposed. Cars communicate via 5G with an edge computer. A cooperative machine-learning algorithm orchestrates the traffic. Automated cars are instructed to accelerate or decelerate with the triple aim of improving the traffic flow into the roundabout, keeping safety constraints, and providing comfort for passengers on board of automated vehicles. In the roundabout, both automated cars and human-driven cars run. The roundabout scenario has been simulated by SUMO. Additionally, the scenario has been reconstructed into a dynamic driving simulator, with a real human driver in a virtual reality environment. The aim was to check the human perception of traffic flow, driving safety and driving comfort.

With the capability of avoiding failure in advance, failure prediction model is important not only to end users, but also to the service engineers in vehicle industry. This paper proposes an approach based on anomaly detection algorithms and telematic data to predict the failure of the engine air system with Turbo charger. Firstly, the relationship between air system and all obtained features are analyzed by both physical mechanism and data-wise. Then, the features including altitude, air temperature, engine output power, and charger pressure are selected as the input of the model, with the sampling interval of 1 minute. Based on the selected features, the healthy state for each vehicle is defined by the model as benchmark. Finally, the ‘Medium surface’ is determined for specific vehicle, which is a hyperplane with the medium points of the healthy state located at, to detect the minor weakness symptom (sub-health state).

Energy management of battery electric vehicle (BEV) is a very important and complex multi-system optimisation problem. The thermal energy management of a BEV plays a crucial role in consistent efficiency and performance of vehicle in all weather conditions. But in order to manage the thermal management, it requires a significant number of temperature sensors throughout the car including high voltage batteries, thus increasing the cost, complexity and weight of the car. Virtual sensors can replace physical sensors with a data-driven, physical relation-driven or machine learning-based prediction approach. This paper presents a framework for the development of a neural network virtual sensor using a thermal system hardware-in-the-loop test rig as the target system. The various neural network topologies, including RNN, LSTM, GRU, and CNN, are evaluated to determine the most effective approach.

Battery Run-down under the Electric Vehicle Operation (BREVO) model is a model that links the driver’s travel pattern to physics-based battery degradation and powertrain energy consumption models. The model simulates the impacts of charging behavior, charging rate, driving patterns, and multiple energy management modules on battery capacity degradation. This study implements reinforcement learning (RL) to the simplified BREVO model to optimize drivers’ decisions on charging such as charging rate, charging time, and charging capacity needed. This is done by a reward function that considers both the driver’s daily travel demands and the minimization of battery degradation over a year. It shows that using appropriate charger type (No Charge, Level 1, Level 2, direct-current Fast Charge [DCFC], extreme Fast Charging [xFC]) with an appropriate charging time can reduce battery degradation and total charging cost at the end of the year while satisfying driver’s daily travel demand.

Driver state monitoring is a crucial technology for enhancing road safety and preventing human error-caused accidents in the era of autonomous vehicles. This paper presents CogniSafe, a comprehensive driver monitoring system that uses deep learning and computer vision methods to detect various types of driver distractions and fatigue. CogniSafe consists of four modules: Driver anomaly detection and classification: A novel two-phase network that proposes and recognizes driver anomalies, such as texting, drinking, and adjusting radios, using multimodal and multiview input. Gaze estimation: A video-based neural network that jointly learns head pose and gaze dynamics, achieving robust and efficient gaze estimation across different head poses. Eye state analysis: A multi-tasking CNN that encodes features from both eye and mouth regions, predicting the percentage of eye closure (PERCLOS) and the frequency of mouth opening (FOM).

Model-based developments have been introduced to reduce the development time for vehicle systems. Various model-based tools, including MATLAB and Simulink, have been introduced, and each vehicle component uses different tools to model assets. This makes the system complex and reduces the simulation efficiency because of the need for interfaces or converters when reusing model assets and combining parts. However, machine learning, in which neural nets are pretrained to make inferences in real time, is being applied to automatic driving and applications such as object recognition. This study developed a system in which the inputs and outputs assigned to a model were trained using neural nets, and the trained neural nets were combined with UML: Unified Modeling Language. A previous UML integration proposal integrated C/C++ code automatically generated from the models. Therefore, the previous proposal made limited use of modeling tools with automatic code generation capabilities.

With further development of autonomous vehicles additional challenges appear. One of these challenges arises in the context of mixed traffic scenarios where automated and autonomous vehicles coexist with manually operated vehicles as well as other road users such as cyclists and pedestrians. In this evolving landscape, understanding, predicting, and mimicking human driving behavior is becoming not only a challenging but also a compelling facet of autonomous driving research. This is necessary not only for safety reasons, but also to promote trust in artificial intelligence (AI), especially in self-driving cars where trust is often compromised by the opacity of neural network models. The central goal of this study is therefore to address this trust issue. A common approach to imitate human driving behavior through expert demonstrations is imitation learning (IL). However, balancing performance and explainability in these models is a major challenge.

The on-board emergency call system with accurate occupant injury prediction can help rescuers deliver more targeted traffic accident rescue and save more lives. We use machine learning methods to establish, train, and validate a number of classification models that can predict occupant injuries (by determining whether the MAIS (Maximum Abbreviated Injury Scale) level is greater than 2) based on crash data, and ranked the correlation of some factors affecting vehicle occupant injury levels in accidents. The optimal model was selected by the model prediction accuracy, and the Grid Search method was used to optimize the hyper-parameters for the model.

The rise of Software-Defined Vehicles (SDV) has rapidly advanced the development of Advanced Driver Assistance Systems (ADAS), Autonomous Vehicle (AV), and Battery Electric Vehicle (BEV) technology. While AVs need power to compute data from perception to controls, BEVs need the efficiency to optimize their electric driving range and stand out compared to traditional Internal Combustion Engine (ICE) vehicles. AVs possess certain shortcomings in the current world, but SAE Level 2+ (L2+) Automated Vehicles are the focus of all major Original Equipment Manufacturers (OEMs). The most common form of an SDV today is the amalgamation of AV and BEV technology on the same platform which is prominently available in most OEM’s lineups. As the compute and sensing architectures for L2+ automated vehicles lean towards a computationally expensive centralized design, it may hamper the most important purchasing factor of a BEV, the electric driving range.

The IncQuery AUTOSAR-UML Bridge is an innovative solution for Assisted Documentation Creation and Automated Handover, aiming at driving a paradigm shift in integrated digital engineering in the automotive domain. The AUTOSAR-UML Bridge is addressing a well-known gap in the engineering ecosystem of automotive design, where the co-design of AUTOSAR models and other model-based artifacts is often hampered by tedious workflows involving manual syncing of model contents between AUTOSAR and UML/SysML tools. The Bridge is aiming at streamlining the workflow by generating high-quality UML models from AUTOSAR projects, with built-in ISO26262 and ASPICE compliance. Automotive software architects and systems engineers spend a lot of time with creating ISO26262-compliant documentation, by creating UML models from AUTOSAR architecture designs, or establishing traceability between requirements captured in SysML and design artefacts that exist in both modeling languages.

The design of lightweight vehicle structures has become a common method for automotive manufacturers to increase fuel efficiency and decrease carbon emission of their products. By using aluminum instead of steel, manufacturers can reduce the weight of a vehicle while still maintaining the required strength and stiffness. Currently, Resistance Spot Welding (RSW) is used extensively to join steel body panels but presents challenges when applied to aluminum. When compared to steel, RSW of aluminum requires frequent electrode cleaning, higher energy usage, and more controlled welding parameters, which has driven up the cost of manufacturing. Due to the increased cost associated with RSW of aluminum, Refill Friction Stir Spot Welding (RFSSW) is being considered as an alternative to RSW for joining aluminum body panels. RFSSW consumes less energy, requires less maintenance, and produces more consistent welding in aluminum as compared to RSW.