Accidents often occur at sea, so effective maritime search and rescue is essential. In the current process of sea search and rescue, the operation efficiency of large search and rescue equipment is ...low and it cannot provide stable communication link. In this article, unmanned aerial vehicles (UAVs) and unmanned surface vehicles (USVs) are used to form a cognitive mobile computing network for co-operative search and rescue, and reinforcement learning (RL) is used to plan search path and improve communication throughput. Based on the scene of marine search and rescue, the grid method is used to model the search and rescue area. Meanwhile, an intragroup communication architecture based on UAVs and USVs is designed to assist intragroup communication by recognizing the link channel state between UAVs. Search and rescue path planning is carried out through the strategy iteration of Markov decision process (MDP). Furthermore, distributed RL is used to recognize the channel state and perform mobile computing, so as to optimize the data throughput in the communication group. The simulation results show that we have successfully completed the path planning task. Compared with conventional methods, RL based on different reward functions has better throughput performance under the same number of UAVs auxiliary communications.
To further the technique of indirect measurement, the contact-point response of a moving test vehicle is adopted for the damage detection of bridges. First, the contact-point response of the vehicle ...moving over the bridge is derived both analytically and in central difference form (for field use). Then, the instantaneous amplitude squared (IAS) of the driving component of the contact-point response is calculated by the Hilbert transform, making use of its narrow-band feature. The IAS peaks serve as the key parameter for damage detection. In the numerical simulation, a damage (crack) is modeled by a hinge-spring unit. The feasibility of the proposed method to detect the location and severity of a damage or multi damages of the bridge is verified. Also, the effects of surface roughness, vehicle speed, measurement noise and random traffic are studied. In the presence of ongoing traffic, the damages of the bridge are identified from the repeated or invariant IAS peaks generated for different traffic flows by the same test vehicle over the bridge.
Display omitted
•Use vehicle's contact point with the bridge to identify bridge modal properties and damages.•Performance: Contact-point response > vehicle-body response > bridge response.•Use the instantaneous amplitude squared (IAS) to identify the location and severity of damage(s).•Effects studied: surface roughness, vehicle speed, measurement noise, random traffic.•Identify the damages of a bridge under repeated traffic flows from repeated IAS peaks.
The timely detection of targets in uncharted territory, followed by tracking and monitoring of the targets are an important part of ocean monitoring activities. The cross-domain monitoring approach ...refers to the way of monitoring target in all directions in the sky and sea. Most of the existing studies are based on collaborative monitoring within the same domain. Cross-domain monitoring complements effectively the existing monitoring methods, which collects richer and more comprehensive data. In this paper, the monitoring process is divided into two stages: target search and target tracking. Autonomous underwater vehicle(AUV), unmanned surface vehicle(USV) and Unmanned aerial vehicle(UAV) are used as research objects of the collaborative algorithm in cross-domain monitoring. The cost function and status of each vehicle are defined. The collaborative target tracking algorithm is designed by Q-learning. The effectiveness of the algorithm is verified by simulation. It proves that the method used in this paper is feasible and can satisfy various constraints.
Accurate and reliable prediction of future motions of the nearby agents and effective environment understanding will contribute to high-quality and meticulous path planning for the automated vehicles ...under uncertainty and guarantee traffic safety for future real-world deployments. This task becomes more challenging in highly dynamic and complex scenarios such as unsignalized intersections where no lights exist to control vehicles behavior, or there are not multiple lines for the vehicles to anticipate drivers' future intentions based on the lane in which they are driving. In this study, we introduce a novel deep learning-based methodology to anticipate vehicles path at unsignalized intersections. The method provides multimodal outputs to take into account the inherited uncertainty and multimodality nature of vehicles behavior. Our proposed model works based on dilated convolutional networks in combination with a mixture density layer. We then cluster various existing mixes into possible paths that are ranked based on probability. We assess the performance and generalization capability of our vehicle path prediction model using several metrics over a large naturalistic dataset containing more than 23800 vehicle trajectories. The obtained results reveal the higher performance of our path prediction approach compared with several baselines and benchmarks.
Counter-drone technology plays a vital role in protecting airspace against unwanted and malicious drones. Counter-drone systems increasingly rely on unmanned traffic management services, such as ...remote identification and flight authorization enforcement, for the detection and mitigation of unauthorized activities on the part of unmanned aerial vehicles (UAVs). These services support automated drone identification and verification of the drone activity's compliance before taking any enforcement action. Available drone identification standards, such as ASTM F3411-22 for drone remote identification (DRI), specify key requirements for entities involved in UAV operations. However, DRI systems can fail for many technical and nontechnical reasons related to the drone itself, its operator, the identification system, other involved service suppliers, or the communication between these actors. On the other hand, experience has shown that even licensed drone operators can violate permitted flight parameters mistakenly or for unavoidable reasons. In such contingency situations, the counter-drone system should perform additional checks and interact with relevant agents before classifying the drone as illegal and taking action against it. This article presents a set of protocols to formalize the interaction between the counter-drone system and relevant agents to clarify possible failures and violations. The goal is to complement current DRI systems mitigating the effect of erroneous drone identification and supporting reliable decision-making. The simulation of worst-case scenarios shows that executing the clarification protocols takes just a few seconds, and this delay is only notable in situations where immediate action is required to neutralize illegal drones.
After significant efforts from many parties, the World-wide harmonized Light duty Test Procedure (WLTP) has seen its light first as the UNECE Global Technical Regulation and then as the procedure ...adopted in the type-approval of light-duty vehicles in Europe. The paper focuses its attention on the main procedural differences between the WLTP and the New European Driving Cycle (NEDC), which is the test-procedure currently used in Europe. In general terms the WLTP appears to be a significant improvement compared to the NEDC. The main differences between two test procedures are identified and their impact on CO2 emissions quantified using the in-house built simulation software CO2MPAS. On the basis of each of these differences, the paper assesses the potential total impact on the final reported type-approval CO2 emissions. The biggest impact on CO2 emissions is coming from the changes in the road load determination procedure (∼10% increase). Procedural changes concerning the test in the laboratory will bring another 8% and post-processing and declaration of results will result in difference of approximately 5% (each). Overall, the WLTP is likely to increase the type-approval CO2 emissions by approximately 25%. Therefore, the WLTP will be able to reduce more than half of the gap identified between the type-approval and real-life figures in Europe. This should be seen as a considerable improvement given the ontological limitations of a laboratory-based test procedure.
We propose a novel communication efficient and privacy preserving federated learning framework for enhancing the performance of Internet of Vehicles (IoV), wherein on-vehicle learning models are ...trained by exchanging inputs, outputs and their learning parameters locally. Moreover, we use analytic modeling as a tool for reasoning and developing the required IoV scenario and stabilize their data flow dynamics by considering TCP CUBIC streams over WiFi networks to prove our idea.
Particle emissions from heavy-duty vehicles (HDVs) have significant environmental and public health impacts. This study measured total particle number emission factors (PNEFs) from six newly ...certified HDVs powered by diesel and compressed natural gas totaling over 6800 miles of on-road operation in California. Distance-, fuel- and work-based PNEFs were calculated for each vehicle. Distance-based PNEFs of vehicles equipped with original equipment manufacturer (OEM) diesel particulate filters (DPFs) in this study have decreased by 355–3200 times compared to a previous retrofit DPF dynamometer study. Fuel-based PNEFs were consistent with previous studies measuring plume exhaust in the ambient air. Meanwhile, on-road PNEF shows route and technology dependence. For vehicles with OEM DPFs and Selective Catalytic Reduction Systems, PNEFs under highway driving (i.e., 3.34 × 1012 to 2.29 × 1013 particles/mile) were larger than those measured on urban and drayage routes (i.e., 5.06 × 1011 to 1.31 × 1013 particles/mile). This is likely because a significant amount of nucleation mode volatile particles were formed when the DPF outlet temperature reached a critical value, usually over 310 °C, which was commonly achieved when vehicle speed sustained over 45 mph. A model year 2013 diesel HDV produced approximately 10 times higher PNEFs during DPF active regeneration events than nonactive regeneration.
To achieve benefits similar to those seen in hybrid-/all-electric ground-based and marine vehicles, electric propulsion has been proposed for large commercial aircraft. Among the main drivers of this ...are improved fuel economy, reduced harmful emissions, and lower audible noise. In converting to electric propulsion, the added electrical components’ masses must be minimised so that the benefits that the components enable – improved turbine efficiency, distributed propulsion and propulsion-airframe integration – are not cancelled out by their weight penalty. This puts stringent requirements on the large electric machines used in the system, both those that generate electric power from the turbine shaft and those that drive propellers or ducted fans, because they are among the heaviest of the added electric components. A key machine design metric in this application is the specific power (SP), or the power-to-mass ratio. This study gives a comprehensive overview of large electric machines for aircraft electric propulsion applications, with a focus on methods for mass reduction and SP improvement.
This study explores the economics of the public electric vehicle (EV) charging station in Korea to provide insights into the business. In Korea, the public charging infrastructure is typically ...important for the large scale diffusion of EV because many potential EV buyers live in multi-family residential units with limited off-street parking and thus installing home chargers is restricted. With internal data from the private charging service providers, this study shows that the charging business is hardly profitable with the current charging price of $0.23/kWh with subsidies to mitigate initial investment costs. In addition, many industry analysts have noted that subsidies may distort charging market; building charging stations to get the subsidies without considering economics of stations resulting in very low utilization rate. Removing the subsidies may minimize the market distortion but the economic feasibility becomes much worse. We propose the discriminatory price scheme, that is, different charging prices for the slow and the fast chargers. The appropriate charging prices without subsidies are estimated to be $0.25/kWh for the slow chargers (9% higher than the current charging price) and $0.39/kWh for the fast chargers (70% higher than the current price).
•The public charging infrastructure is important for the large scale diffusion of electric vehicle (EV).•This study shows that the charging business in Korea is hardly profitable with the current charging price of $0.23/kWh.•In addition, government subsidies may distort EV charging market.•The discriminatory price scheme, different charging prices for the slow and the fast chargers, may minimize the market distortion.•EV charging business may survive with 9% higher for the slow and 70% higher for the fast chargers, without subsidies.