Uncrewed Aerial vehicles are useful for a multitude of applications in today’s age, covering a wide variety of fields such as defense, environmental science, meteorology, emergency responders, search and rescue operations, entertainment robotics, etc. Different types of aircrafts such as fixed wing UAVs, rotor wing UAVs are used for the mentioned applications depending upon the application requirements. One such category of UAVs is the lighter-than-air aircrafts, that provide their own set of advantages over the other types of UAVs. Blimps are among the participants of the lighter-than-air category that are expected to offer advantages such as higher endurance and range, and safer and more comfortable Human-machine-Interaction, etc. as compared to fixed wing and rotor wing UAVs due to their design. A ROS (Robot Operating System) based control system was developed for controlling the blimp.
This work puts forward an original autonomous planning and control framework addressing inherent modeling complexity limit through efficient heterosis between latency-connective graph estimation and generative exploration with an aim to enhance trajectory quality and resiliency in unpredicted conditions. The holistic approach encompasses state and cost prediction facilitated via morphable signature mechanism utilizing anti-cloak characteristics derived from environmental graph. In principle, a dynamic graph neural network is proposed with regards to adaptively capture essential influence caused by interactive agents and reciprocal belief augmentation. Moreover, high efficiency exploration is concerted with signature-enhanced prediction system for non-ideal perception conditions. The exploration scheme takes advantage of confidence optimization function to generate trajectory refinement over non-conventional operating circumstances.
Plug-in hybrid electric vehicles have the potential of combining the benefits of electric vehicle in terms of low emissions and internal combustion engine vehicles in terms of vehicle range. With the addition of a renewable fuel, the CO2 potential reduction increase even more. The last trends for PHEV are small combustion engine known as range extender, with battery package between full hybrid and electric powertrains. Thus, allowing an improvement in vehicle’s range, reducing battery materials while converting fuel energy through a highly efficient path. Although these vehicles have been proved to be a convenient strategy for decarbonizing the light vehicles, the use of alternative fuels is poorly studied. In this work, hydrous ethanol is chosen because is already available in some countries, such as USA and Brazil, and have an ultra-low well-to-tank CO2 emission.
In recent years, the presence of electric buses within public transportation company fleets has significantly increased. To ensure optimal fleet management, it is necessary to analyze vehicle consumption in relation to their operational conditions. This study proposes an analysis of the energy consumption of a full-electric battery bus. Energy consumption was monitored using data made available on the vehicle's CAN network, including data from the main battery and major utilities such as the traction motor, the air conditioning system (both cooling and heating), power steering, main battery chiller, and low-voltage system utilities (lights, ventilation fans, doors opening, etc.). The parameters monitored during the experimentation included the vehicle's position and, consequently, the road gradient, instantaneous vehicle speed, internal and external temperature, vehicle load (to monitor consumption under various load conditions), and the involvement of different drivers.
Simulators are essential part of the development process of vehicles and their advanced functionalities. The combination of virtual simulator and Hardware-in-the-loop technology accelerates the integration and functional validation of ECUs and mechanical components. In this study, a real-time capable tire model has been developed and coupled with an innovative simulation apparatus. On-track tests were executed to collect data necessary for tire modelling using an experimental vehicle equipped with wheel force transducer, to measure force and moments acting on tire contact patch. The steering wheel was instrumented with a torque sensor, while tie-rod axial forces were quantified using loadcells. The simulation apparatus is composed of a static and a dynamic simulator. The static simulator integrates the entire steering system from the steering column up to tie rods. Tie-rods dynamic forces are applied by two torque motors.
During the development of an Internal Combustion Engine-based powertrain, traditional procedures for control strategies calibration and validation produce huge amount of data, that can be used to develop innovative data-driven applications, such as emission virtual sensing. One of the main criticalities is related to the data quality, that cannot be easily assessed for such a big amount of data. This work focuses on an emission modeling activity, using an enhanced Light Gradient Boosting Regressor and a dedicated data pre-processing pipeline to improve data quality. First thing, a software tool is developed to access a database containing data coming from emissions tests. The tool performs a data cleaning procedure to exclude corrupted data or invalid parts of the test. Moreover, it automatically tunes model hyperparameters, it chooses the best set of features, and it validates the procedure by comparing the estimation and the experimental measurement.
AI-based methods are experiencing a rapid surge in adoption across various applications, particularly in the context of autonomous and trustworthy embedded systems. Since AI-based systems then have the potential to affect with mission critical system properties of trustworthy embedded systems, a higher level of maturity and dependability considerations is required to be followed. This paper combines the findings from the TEACHING project, which focuses on technology bricks for humanistic AI concepts, with insights derived from a facilitation workshop involving subject matter experts for dependability engineering. The paper establishes the body of knowledge and fundamental grounds outcomes discussed in an expert workshop at international conference on computer safety, reliability, and security. The assurance of dependability continues to be an open issue with no common solution yet.
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 (CAD) and engineering (CAE), 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 / artificial intelligence 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 orchestrate 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, 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.
This paper presents a Differential Flatness-Based Control (FBC) approach for the current control of Switched Reluctance Machines (SRMs), a potential candidate for the automotive industry. The main challenges in SRM control methods stem from motor nonlinearity. A nonlinear dynamic system is considered "flat" if a set of flat outputs equal to the number of inputs can be found, and the control output variables must be written as the function of the flat output and their derivatives. In electrical drives, FBC has been applied in doubly-fed induction generators, permanent magnet motors, and magnet-assisted synchronous reluctance motors. Among the few papers that have used FBC for SRM, this research distinguishes itself by addressing current control and considering both current and flux-linkage separately as a flat output, an approach not found in previous literature.
In the realm of electric vehicles (EVs), effective battery thermal management is critical to avert thermal runaway, overheating, and extend the operational lifespan of batteries. The process of designing thermal management systems can be substantially expedited through the utilization of modeling and simulation techniques. However, the high-fidelity 3D computational fluid dynamics (CFD) simulations often demand significant computational resources to provide comprehensive results under varying conditions. In this paper, we develop a reduced order model (ROM) to capture the battery thermal dynamics employing a sub-space method. To construct this ROM, we use high-fidelity CFD simulations to generate step responses of battery temperature with respect to the heat generation and cooling power. These step responses are subsequently used as training data for the ROM.
Powertrain development requires an efficient development process with no rework and model-based design (MBD), in addition to performance design that achieves low CO2 emissions. Furthermore, it also demands fuel economy performance considering real-world usage conditions, and in North America, the EPA 5-cycle, which evaluates performance in a combination of various environments, is applied. This evaluation mode necessitates predicting performance while considering engine heat flow, particularly simulation technology that takes into account behavior based on engine temperature. Additionally, in the development trend of vehicle aerodynamic improvement, variable devices like Active Grille Shutter (AGS) are utilized to contribute to reducing CO2 emissions. When equipped with AGS, the engine's heat flow environment also changes, resulting in more complex phenomena in the engine compartment compared to the without AGS.
The paper presents a trajectory tracking method for an unmanned bicycle in its local body-fixed coordinate frame. A bicycle is regarded as a multibody system consisting of four rigid bodies which are named front wheel, front fork, body frame, and rear wheel. Unlike many studies before, the interaction between tire and road is regarded as tire force instead of a nonholonomic constraint. The body frame has six degrees of freedom and the rear wheel and front fork have one degree of freedom relative to the body frame respectively. The front wheel has one degree of freedom relative to the front fork. Thus, a bike has nine degrees of freedom in total. The kinetic energy of a bike is expressed using quasi-coordinates in the local body-fixed coordinate frame which has a simpler form than using absolute coordinates in the global frame. The dynamic model can be acquired by submitting the expression of kinetic energy into the Lagrange equation.
Engineering design-decisions often involve many attributes which can differ in the levels of their importance to the decision maker (DM), while also exhibiting complex statistical relationships. Learning a decision-making policy which accurately represents the DM’s actions has long been the goal of decision analysts. To circumvent elicitation and modeling issues, this process is often oversimplified in how many factors are considered and how complicated the relationships considered between them are. Without these simplifications, the classical lottery-based preference elicitation is overly expensive, and the responses degrade rapidly in quality as the number of attributes increase. In this paper, we investigate the ability of deep preference machine learning to model high-dimensional decision-making policies utilizing rankings elicited from decision makers.
The greatest threat to human life is climate change. Carbon emission, which is a major cause of climate change, comes from human activities like burning fossil fuels. The automotive sector contributes approximately one fifth of all global carbon emissions. The key solution for addressing the problem of carbon emissions is battery electric vehicles. The high cost of the technology, the lack of charging infrastructure, and the short range of EVs are major barriers to their widespread adoption. The fact that the real range is less than the certified range is another issue for prospective customers of electric vehicles. The certified range of an EV is based on a standard driving cycle, which differs from the actual driving cycle. Therefore, it's crucial to select the right driving cycle for range estimation. In India, MIDC (modified Indian drive cycle) was adopted, which is equivalent to the New European Driving Cycle (NEDC). The maximum speed in the MIDC cycle is set to 90 km/h.