Capabilities Of Vehicles Research Articles

A Probabilistic–Geometric Approach for UAV Detection and Avoidance Systems

This paper proposes a collision avoidance algorithm for the detection and avoidance capabilities of Unmanned Aerial Vehicles (UAVs). The proposed algorithm aims to ensure minimum separation between UAVs and geofencing with multiple no-fly zones, considering the sensor uncertainties. The main idea is to compute the collision probability and to initiate collision avoidance manoeuvres determined by the differential geometry concept. The proposed algorithm is validated by both theoretical and numerical analysis. The results indicate that the proposed algorithm ensures minimum separation, efficiency, and scalability compared with other benchmark algorithms.

An improved risk estimation model of lane change using naturalistic vehicle trajectories

Lane change (LC) behavior has critical effects on traffic flows and safety due to its complex interactions with surrounding vehicles. To ensure safe lane changes and prevent potential crashes, it is important to recognize the potential crash risk of lane change in real time. This study proposes an improved risk estimation (IRE) model to evaluate the potential collision risk of lane change (LCR) vehicle groups. The safety margin is introduced to consider the deceleration capability of vehicles to measure the reaction time of drivers during the LC. Then the IRE model is established, incorporating the collision probability and collision severity measured based on the safety margin. The trajectory data, extracted from the highD dataset, are used and 1536 LC samples are investigated. We compare the LCR under different contextual factors, including vehicle types (cars and trucks), two lane change directions (left and right lane change, LLC and RLC), and traffic flows (low and high traffic). It was found that truck drivers keep higher LCR compared with car drivers due to limited brake capacity, and the left lane change results in higher LCR compared with the right lane change. Additionally, lane change is associated with higher crash risk in high traffic flow, as compared to low traffic flow. The understanding of the crash risk of lane change behavior under different contextual factors, can be useful for real-time crash prediction and devising traffic management strategies.

Urban Road Safety Prediction: A Satellite Navigation Perspective

Predicting the safety of urban roads for navigation via global navigation satellite systems (GNSS) signals is considered. To ensure safe driving of automated vehicles, the vehicle must plan its trajectory to avoid navigating on unsafe roads (e.g., icy conditions, construction zones, narrow streets, etc.). Such information can be derived from the roads' physical properties, vehicle's capabilities, and weather conditions. From a GNSS-based navigation perspective, the reliability of GNSS signals in different locales, which is heavily dependent on the road layout within the surrounding environment, is crucial to ensure safe automated driving. An urban road environment surrounded by tall objects can significantly degrade the accuracy and availability of GNSS signals. This article proposes an approach to predict the reliability of GNSS-based navigation to ensure safe urban navigation. Satellite navigation reliability at a given location and time on a road is determined based on the probabilistic position error bound of the vehicle-mounted GNSS receiver. A metric for GNSS reliability for ground vehicles is suggested, and a method to predict the conservative probabilistic error bound of the GNSS navigation solution is proposed. A satellite navigation reliability map is generated for various navigation applications. As a case study, the reliability map is used in the proposed optimization problem formulation for automated ground vehicle safety-constrained path planning.

SEIS: A spatiotemporal-aware event investigation framework for social airborne sensing in disaster recovery applications

Social airborne sensing (SAS) is taking shape as a new integrated sensing paradigm that melds the human wisdom derived from social data platforms (e.g., Twitter, Facebook) with the empirical sensing capabilities of unmanned aerial vehicles (UAVs) for providing multifaceted information acquisition and situation awareness services in disaster recovery applications. A crucial task in the aftermath of a disaster is to determine the veracity of the reported events alongside assessing their underlying urgency that can possibly facilitate appropriate parties in their disaster mitigation and recovery efforts. For example, identifying a falsely reported event early on thats claims fatalities could help divert alleviation efforts to genuinely critical events. However, existing SAS schemes are limited to deducing only the veracity of the reports on social data platforms and are unable to infer the underlying urgency of the events. In this paper, we explore the opportunity to develop a spatiotemporal-aware event investigation framework for SAS that can jointly determine the veracity of reported events as well as infer their underlying urgency and deadlines. However, constructing such an integrated system introduces a few new technical challenges. The first challenge is handling the predominant data sparsity in the incoming social signals. The second challenge is optimizing the UAV deployment and event veracity estimation processes by scrutinizing the highly dynamic and latent correlations among event characteristics. The third challenge is carefully extracting and analyzing latent semantic features embedded in the social media data to infer the event urgency. To address the above challenges, we introduce the Spatiotemporal-aware Event Investigation for SAS (SEIS) framework that harnesses techniques from natural language processing (NLP), deep learning, and spatial–temporal correlation modeling for deducing the veracity, urgency and deadlines of the underlying events. Experiments through a real-world disaster recovery dataset demonstrate that SEIS achieves better event veracity estimation, event urgency inference, and deadline hit rate compared to state-of-the-art baselines.

Monocular-Vision-Based Precise Runway Detection Applied to State Estimation for Carrier-Based UAV Landing.

Improving the level of autonomy during the landing phase helps promote the full-envelope autonomous flight capability of unmanned aerial vehicles (UAVs). Aiming at the identification of potential landing sites, an end-to-end state estimation method for the autonomous landing of carrier-based UAVs based on monocular vision is proposed in this paper, which allows them to discover landing sites in flight by using equipped optical sensors and avoid a crash or damage during normal and emergency landings. This scheme aims to solve two problems: the requirement of accuracy for runway detection and the requirement of precision for UAV state estimation. First, we design a robust runway detection framework on the basis of YOLOv5 (you only look once, ver. 5) with four modules: a data augmentation layer, a feature extraction layer, a feature aggregation layer and a target prediction layer. Then, the corner prediction method based on geometric features is introduced into the prediction model of the detection framework, which enables the landing field prediction to more precisely fit the runway appearance. In simulation experiments, we developed datasets applied to carrier-based UAV landing simulations based on monocular vision. In addition, our method was implemented with help of the PyTorch deep learning tool, which supports the dynamic and efficient construction of a detection network. Results showed that the proposed method achieved a higher precision and better performance on state estimation during carrier-based UAV landings.

Modeling and Quantitative Evaluation Method of Environmental Complexity for Measuring Autonomous Capabilities of Military Unmanned Ground Vehicles

This paper proposes a sampling-based multi-dimensional entropy hierarchical evaluation method to evaluate the environmental complexity for measuring autonomous capabilities of military unmanned ground vehicles. Through establishing the multi-dimensional environment model, the complexity of environmental elements in various dimensions is measured by combining the analytic hierarchy process and the improved gravitational field model. Based on the graph entropy and the environment segmentation sampling strategy, the environmental complexity is comprehensively evaluated from the two perspectives of the objective complexity of the environmental structure and the subjective complexity of environmental characteristics. The evaluation of the actual test environment shows that the environmental complexity evaluation model can effectively reflect the individual complexity differences of environmental elements, and achieve the comprehensive complexity evaluation of the environment including multiple test scenarios, which provides a basis for the test scenario design and measuring autonomous capabilities of military unmanned ground vehicles.

A collaborative computation and dependency-aware task offloading method for vehicular edge computing: a reinforcement learning approach

Vehicular edge computing (VEC) is emerging as a new computing paradigm to improve the quality of vehicular services and enhance the capabilities of vehicles. It enables performing tasks with low latency by deploying computing and storage resources close to vehicles. However, the traditional task offloading schemes only focus on one-shot offloading, taking less into consideration task dependency. Furthermore, the continuous action space problem during task offloading should be considered. In this paper, an efficient dependency-aware task offloading scheme for VEC with vehicle-edge-cloud collaborative computation is proposed, where subtasks can be processed locally or can be offloaded to an edge server, or a cloud server for execution. Specifically, first, the directed acyclic graph (DAG) is utilized to model the dependency of subtasks. Second, a task offloading algorithm based on Deep Deterministic Policy Gradient (DDPG) was proposed to obtain the optimal offloading strategy in a vehicle-edge-cloud environment, which efficiently solves the continuous control problem and helps reach fast convergence. Finally, extensive simulation experiments have been conducted, and the experimental results show that the proposed scheme can improve performance by about 13.62% on average against three baselines.

Modern possibilities of using unmanned aerial vehicles by Police authorities and units: Analysis of foreign and Ukrainian experience

The relevance of the research subject is conditioned upon the scientific originality and practical significance of using modern capabilities of unmanned aerial vehicles by police authorities and units. The relevance of the research issue is that the provisions of the current legislation defining the legal basis for using unmanned aerial vehicles by police authorities and units are mostly formally defined. Based on this, and considering that the law enforcement system has encountered new challenges which constantly require the introduction of the latest methods and means of countering crime, including using modern achievements of digital, technological, scientific and technical progress, the purpose of this research is to analyse the foreign experience of using unmanned aerial systems by law enforcement agencies, and based on this, to develop proposals for improving the current legislation in the part concerning using UAVs. The research methodology includes a combination of general scientific and special methods that allow for defining assumptions and drawing conclusions. The research examines the relevant issues of the day concerning using the technical capabilities of unmanned aerial systems in the course of performing the tasks assigned to police agencies and units. In particular, the author examines the international experience of some technologically advanced countries (the USA, Great Britain, Germany, France, China and Israel) in using modern capabilities of unmanned aerial vehicles by law enforcement agencies. Attention is devoted to the development of the aviation industry of Ukraine in terms of the design of Ukrainian unmanned aerial vehicles, and the prospects for their implementation in the activities of the National Police. The author outlines the main prospects for using unmanned aerial vehicles in the activities of police agencies and units. In particular, those related to the protection of public order, road safety, detection, suppression and counteraction to criminal and administrative offences, and protection and defence of human rights and freedoms, life and health. The scientific originality and practical significance of the research are that it highlights the current possibilities of using unmanned aerial vehicles by police authorities and units, outlines some issues of a working nature which require resolution, and, based on international experience, identifies the areas for improvement of the current legislation on using unmanned aerial vehicles by the National Police

Real-Time Fault Diagnosis for EVs With Multilabel Feature Selection and Sliding Window Control

Real-time fault diagnosis on vehicles can effectively avoid potential accidents, which, however, is difficult and challenging to be widely deployed due to the low computational capability and limited data storage of electric vehicles (EVs). To address this issue, we propose a vehicle-mounted fault diagnosis system with low computational complexity and small data storage, for achieving real-time monitoring of vehicle status. To facilitate the accurate and optimized feature selection, we had been collecting 6.52-GB real data from three EVs in 12 months. Motivated by those data, we first propose a multilabel feature selection algorithm to obtain the feature weights, based on which the optimal number of features is then calculated through the backpropagation neural network (BPNN), thus minimizing the computational cost of real-time fault diagnosis regarding sample dimensions. To further simplify the fault diagnosis system, i.e., reducing the minimum required capacity of data storage, we design a real-time diagnosis sliding window (RDSW) where the window moves forward as new samples arrive and the stale data outside the window are discarded. In particular, we calculate the optimal size of RDSW, which controls the minimum required number of samples to guarantee the accuracy of real-time fault diagnosis. Owing to the mechanism of RDSW, vehicles no longer need to store massive data to guarantee the accuracy of real-time fault diagnosis. In addition, the results of real-time fault diagnosis at each vehicle can be shared with other vehicles in cooperative intelligent transportation systems (C-ITS). Finally, comprehensive simulation is conducted to validate the effectiveness of the proposed diagnosis system in terms of accuracy, complexity and storage capacity.

High-Reliability and Low-Energy Sensor Sharing in Vehicle Platoon Based on Multihop Millimeter-Wave Communication

Sensor sharing is an important ability for vehicle platoon to reduce vehicle costs and improve driving safety. However, sensing data with a large amount of information is difficult to be shared by using traditional communication methods. Applying millimeter-wave communication can improve sensor sharing capabilities of vehicles, but millimeter wave has large propagation loss and is easy to be blocked by obstacles. Therefore, how to apply millimeter-wave communication to improve sensor sharing capabilities in vehicle platoon is still an open issue. To this end, we present a stochastic game approach and propose two distributed algorithms to achieve high-reliability and low-energy sensor sharing. First, we model the multihop millimeter-wave sensor sharing of the vehicle platoon as an optimization problem of reducing energy consumption while ensuring communication reliability, and then based on the characteristics of vehicle communication, we transform the optimization problem into a multiagent stochastic game. Second, by utilizing the characteristic that the immediate cost has nothing to do with the transfer function of the game, we prove that this stochastic game has equilibrium by proving that each subgame has a Nash equilibrium. Third, we propose an equilibrium-guided multiagent distributed (EGMD) algorithm to obtain the optimal action of each vehicle in the platoon, and then based on the analysis of the limitation of the approach, we present a multiagent distributed cooperation (MDC) algorithm to further reduce the system energy consumption. Finally, through simulation experiments, we evaluate a variety of approaches and demonstrate that our proposed methods can significantly reduce energy consumption while ensuring communication reliability.

Drug delivery to the brain: In situ gelling formulation enhances carbamazepine diffusion through nasal mucosa models with mucin

The objective of this work was to optimize a thermosensitive in situ gelling formulation to improve intranasal and nose-to-brain delivery of the antiepileptic drug carbamazepine (CBZ). A preliminary procedure of vehicles obtained just mixing different fractions of poloxamer 407 (P407) and poloxamer 188 (P188) revealed preparations with phase transition temperatures, times to gelation and pH values suitable for nasal delivery. Subsequently, the mucoadhesive properties of the most promising formulations were tuned by adding hydroxypropylmethylcellulose types of different viscosity grades, and the effect of the adhesive polymers was evaluated by testing in vitro time and strength of mucoadhesion on specimens of sheep nasal mucosa. The formulation that showed the greatest mucoadhesive potential in vitro, with a time and force of mucoadhesion equal to 1746,75 s and 3.66 × 10-4 N, respectively, was that composed of 22% P407, 5% P188 and 0.8% HPMC low-viscous and it was further investigated for its ability to increase drug solubility and to control the release of the drug. Lastly, the capability of the candidate vehicle to ensure drug permeation across the biomimetic membrane Permeapad®, an artificial phospholipid-based barrier with a stratified architecture, and the same barrier enriched with a mucin layer was verified. The final formulation was characterized by a pH value of 6.0, underwent gelation at 32.33°C in 37.85 s, thus showing all the features required by in situ gelling thermosensitive preparations designed for nasal delivery and, more notably, it conserved the ability to favor drug permeation in the presence of mucin. These findings suggest that the optimized gelling system could be a promising and easy to realize strategy to improve CBZ delivery to the brain exploiting both a direct and indirect pathway.

Aeroelastic characterisation of a bio-inspired flapping membrane wing

Natural fliers like bats exploit the complex fluid–structure interaction between their flexible membrane wings and the air with great ease. Yet, replicating and scaling the balance between the structural and fluid-dynamical parameters of unsteady membrane wings for engineering applications remains challenging. In this study, we introduce a novel bio-inspired membrane wing design and systematically investigate the fluid–structure interactions of flapping membrane wings. The membrane wing can passively camber, and its leading and trailing edges rotate with respect to the stroke plane. We find optimal combinations of the membrane properties and flapping kinematics that out-perform their rigid counterparts both in terms of increased stroke-average lift and efficiency, but the improvements are not persistent over the entire input parameter space. The lift and efficiency optima occur at different angles of attack and effective membrane stiffnesses which we characterise with the aeroelastic number. At optimal aeroelastic numbers, the membrane has a moderate camber between 15% and 20% and its leading and trailing edges align favourably with the flow. Higher camber at lower aeroelastic numbers leads to reduced aerodynamic performance due to negative angles of attack at the leading edge and an over-rotation of the trailing edge. Most of the performance gain of the membrane wings with respect to rigid wings is achieved in the second half of the stroke when the wing is decelerating. The stroke-maximum camber is reached around mid-stroke but is sustained during most of the remainder of the stroke which leads to an increase in lift and a reduction in power. Our results show that combining the effect of variable stiffness and angle of attack variation can significantly enhance the aerodynamic performance of membrane wings and has the potential to improve the control capabilities of micro air vehicles.

3D trajectory planning based on the Rapidly-exploring Random Tree–Connect and artificial potential fields method for unmanned aerial vehicles

This research proposes a multifaceted approach of three-dimensional trajectory planning based on the combination of Rapidly-exploring Random Tree–Connect algorithm and artificial potential field method to improve the path search ability and dynamic obstacles avoidance capability of unmanned aerial vehicles. Firstly, an improved method of the target gravity is developed by controlling the sampling range to reduce invalid sampling and speed up the convergence speed of the algorithm so as to lessen the restriction of low efficiency and random sampling of the Rapidly-exploring Random Tree–Connect algorithm. Moreover, the regulation factor is introduced into the artificial potential field method to deal with the problem of target unreachable in the trajectory planning. Then the improved Rapidly-exploring Random Tree–Connect algorithm is implemented to plan the global path in a complex environment. This step is carried out via selecting the local target point on the global path found in the global plan, dividing the complex environment into simple environment and utilizing the artificial potential field method to achieve the effect of avoiding unknown dynamic obstacles in the simple environment. Finally, cubic B-spline is employed to smoothing of the planned trajectory. The simulation results demonstrate that the combination of two improved algorithms improves the path search ability and dynamic barrier avoidance capability of the unmanned aerial vehicles.

Electromagnetic Scattering Characteristics of Blunt Cone Aircraft Under THz Waves Based on PO Method

The physical optics (PO) method based on subregional triangular patch division was used to study the electromagnetic (EM) scattering characteristics of a blunt cone hypersonic vehicle under terahertz (THz) waves in different environments. First, the backscattering radar cross section (RCS) of a metal blunt cone under gigahertz and THz waves was calculated separately; the results show that the RCS under the THz wave has higher accuracy and can better reflect the structural characteristics of the target. Then, the RCS of a blunt cone covered with a plasma sheath at different reentry heights was calculated; the results show that the existence of the plasma sheath will reduce the target RCS, and the degree of reduction is related to the maximum electron density, the frequency of incident waves, and other factors, but THz waves can alleviate this effect. Finally, the RCS of a blunt cone covered with a plasma sheath and radar absorbing material (RAM) at different incident EM wave frequencies were also studied, and some interesting conclusions are preliminarily obtained. Our work can provide a meaningful reference for advancing research on the stealth and anti-stealth capabilities of hypersonic vehicles.

Timeliness-Aware Incentive Mechanism for Vehicular Crowdsourcing in Smart Cities

Vehicular crowdsourcing is a promising paradigm that takes advantage of powerful onboard capabilities of vehicles to perform various tasks in smart cities. To fulfill this vision, a well-designed incentive mechanism is essential to stimulate the participation of vehicles. In this paper, we propose a timeliness-aware incentive mechanism for vehicular crowdsourcing by taking vehicle’s uncertain travel time into account. In view of the stochastic nature of traffic conditions, we derive a tractable expression for the probability distribution of task delay based on a discrete-time traffic model. By leveraging reverse auction framework, we model the utility of a service requester as a function in terms of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">uncertain</i> task delay and incurred payment. To maximize the requester’s utility under a budget constraint, we cast the mechanism design as a non-monotone submodular maximization problem over a knapsack constraint. Based on this formulation, we develop a <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">t</u> ruthful <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">b</u> udgeted <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">u</u> tility <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</u> aximization <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</u> uction (TBUMA), which is truthful, budget feasible, profitable, individually rational and computationally efficient. Through extensive trace-based simulations, we demonstrate the effectiveness of our proposed incentive mechanism.

Reliability‐based offloading strategy for deadline‐constrained taskflows in vehicular edge computing environments

AbstractVehicular edge computing (VEC) offers a new paradigm for improving vehicular services and enhancing vehicle capabilities. In the VEC environments, vehicles can offload tasks to edge servers deployed in roadside units or other vehicles via wireless networks to enhance their computation capability. However, the high mobility of vehicles will lead to constant change of the network topology among resources, which will affect the completion time and the reliability of offloaded tasks. Therefore, we proposes a reliability‐based offloading strategy by considering task attributes, resource state, completion time, and reliability to map task flows to resources that can satisfy the time constraints with high reliability. The experimental results show that, compared with existing typical algorithms, the proposed strategy not only reduces the average completion time of tasks, but also ensures the reliability of tasks.

USV collision hazard assessment and track planning algorithm

To improve the autonomous collision avoidance capability of an unmanned surface vehicle (USV) under complex working conditions, this study proposes a local track planning algorithm for USVs based on collision hazard assessment. This algorithm uses hierarchical analysis and discrepancy method to determine the collision risk index (CRI) values of different encounter scenarios, and then introduces fuzzy inference theory to construct a quantitative collision hazard assessment model based on the principle of combining subjective and objective assessment and the pessimistic principle of class classification, which provides a decision basis for a collision avoidance plan. In response to the unexpected encounter, an improved vector field histogram algorithm is proposed to use the CRI value of the obstacle as the key parameter of the histogram, solve the restricted area by removing the grid model and threshold improvement, establish the cost function to calculate the optimal sailing interval under the rules and dynamics constraints of the Convention on International Regulations for Preventing Collisions at Sea (COLREGS), and realise the local target point by tracking local track planning during autonomous collision avoidance. Simulation and on-lake experiments demonstrate the effectiveness of the collision hazard assessment model and local track planning algorithm proposed in this paper.

ОСОБЛИВОСТІ ВИЯВЛЕННЯ ОПЕРАТИВНО-ТАКТИЧНИХ БЕЗПІЛОТНИХ ЛІТАЛЬНИХ АПАРАТІВ РАДІОЛОКАТОРАМИ РАДІОТЕХНІЧНИХ ВІЙСЬК

The range of aircraft is expanding rapidly and it should currently include objects from hypersonic aircraft to small unmanned aerial vehicles. Accordingly, airspace control must be carried out on all types of aircraft. The article discusses the features of radar detection of very complex objects for active location - unmanned aerial vehicles of tactical and operative-tactical level. Their tactical and technical characteristics, design features and tactics of application allow such aircraft to perform combat missions sometimes without detection of the enemy's air defense system. The article discusses the factors and features that contribute to the untimely detection of objects such as unmanned aerial vehicles by radar stations of radio troops or lead to difficulties in their observation. Ways to improve radar surveillance of unmanned aerial vehicles are noted. The analysis of the experience of combat use of unmanned aerial vehicles in the area of the Joint Forces operation is carried out in the east of Ukraine in 2014–2022 the Syrian military conflict, the second Karabakh war of 2020 and the modern Russian-Ukrainian war. There are more important factors that contributed to the effective use of unmanned aerial vehicles. The generalized information of change of features of the military conflicts which were formed thanks to possibilities of unmanned aerial vehicles is resulted. It is shown that modern reconnaissance and combat capabilities of unmanned aerial vehicles are rapidly changing not only the tactics of using weapons and military equipment of the Armed Forces, but also changing the strategy of warfare. Much attention is paid to the analysis of the mass use of unmanned aerial vehicles of various types in the current Russian-Ukrainian military conflict. Keywords: unmanned aerial vehicle, low-visibility detection, passive interference, radio technical troops.

Agent-Based Model of Electric Vehicle Charging Demand for Long-Distance Driving in the State of Indiana

Historically the U.S. transportation system has been continuously improved to adopt new policies and technologies. The transportation vehicle energy transition from fossil fuels to electricity is promoted by policymakers and major automakers with an expectation of enhancing sustainability aspects such as fossil fuel consumption reduction, carbon emissions reduction, and lower operations and maintenance costs. However, the electrification of the existing transportation infrastructure system requires substantial upgrades to overcome two major concerns from ordinary drivers and the public. One is the driver’s range anxiety based on the current capability of the electric vehicle (EV) technologies. The other is the availability of EV charging stations near the planned route. To address these two issues, we introduce an agent-based simulation model to project the consequences of electrification in the Indiana state highway system. Specifically, the model is developed to monitor the status of long-distance EV trips between different regions. The multi-agent engine method guarantees the model can adapt to diverse scenarios and complex environments. The simulation experiment verifies that the proposed model can provide the expected outcomes, including the numerical data of electric energy demand and the geospatial information (as location coordinates) of failed trips. By performing a GIS-based analysis of the results, the derived geospatial data can help state transportation agencies determine where to deploy the charging facilities to satisfy the overall charging demand. The proposed simulation framework offers a novel and strategic way to resolve the challenges for EV charging-related research and projects.

A transferable energy management strategy for hybrid electric vehicles via dueling deep deterministic policy gradient

Due to the high mileage and heavy load capabilities of hybrid electric vehicles (HEVs), energy management becomes crucial in improving energy efficiency. To avoid the over-dependence on the hard-crafted models, deep reinforcement learning (DRL) is utilized to learn more precise energy management strategies (EMSs), but cannot generalize well to different driving situations in most cases. When driving cycles are changed, the neural network needs to be retrained, which is a time-consuming and laborious task. A more efficient transferable way is to combine DRL algorithms with transfer learning, which can utilize the knowledge of the driving cycles in other new driving situations, leading to better initial performance and a faster training process to convergence. In this paper, we propose a novel transferable EMS by incorporating the DRL method and dueling network architecture for HEVs. Simulation results indicate that the proposed method can generalize well to new driving cycles, with comparably initial performance and faster convergence in the training process.