Search Results

The operation management of electric Taxi fleets requires cooperative optimization of Charging and Dispatching. The challenge is to make real-time decisions about which is the optimal charging station or passenger for each vehicle in the fleet. With the rapid advancement of Vehicle Internet of Things (VIOT) technologies, the aforementioned challenge can be readily addressed by leveraging big data analytics and machine learning algorithms, thereby contributing to smarter transportation systems. This study focuses on optimizing real-time decision-making for charging and dispatching in large-scale electric taxi fleets to improve their long-term benefits. To achieve this goal, a spatiotemporal decision framework using Bi-level optimization is proposed. Initially, a deep reinforcement learning-based model is built to estimate the value of charging and order dispatching under uncertainty.

SLAM (Simultaneous Localization and Mapping) plays a key role in autonomous driving. Recently, 4D Radar has attracted widespread attention because it breaks through the limitations of 3D millimeter wave radar and can simultaneously detect the distance, velocity, horizontal azimuth and elevation azimuth of the target with high resolution. However, there are few studies on 4D Radar in SLAM. In this paper, RI-FGO, a 4D Radar-Inertial SLAM method based on Factor Graph Optimization, is proposed. The RANSAC (Random Sample Consensus) method is used to eliminate the dynamic obstacle points from a single scan, and the ego-motion velocity is estimated from the static point cloud. A 4D Radar velocity factor is constructed in GTSAM to receive the estimated velocity in a single scan as a measurement and directly integrated into the factor graph. The 4D Radar point clouds of consecutive frames are matched as the odometry factor.

In recent years, the burgeoning applications of hydrogen fuel cells have ignited a growing trend in their integration within the transportation sector, with a particular focus on their potential use in multi-rotor drones. The heightened mass-based energy density of fuel cells positions them as promising alternatives to current lithium battery-powered drones, especially as the demand for extended flight durations increases. This article undertakes a comprehensive exploration, comparing the performance of lithium batteries against air-cooled fuel cells, specifically within the context of multi-rotor drones with a 3.5kW power requirement. The study reveals that, for the specified power demand, air-cooled fuel cells outperform lithium batteries, establishing them as a more efficient solution.

With the continuous popularization of electric vehicles (EVs), ensuring the best performance of EVs has become a significant concern, and lithium-ion power batteries are considered as the essential storage and conversion equipment for EVs. Therefore, it is of great significance to quickly evaluate the state of power batteries. This paper investigates a fast state estimation method of power batteries oriented to after-sales and maintenance. Based on the battery equivalent circuit model and heuristics optimization algorithm, the battery model parameters, including the internal ohmic and polarization resistance, can be identified using only 30 minutes of charging or discharging process data without full charge or discharge. At the same time, the proposed method can directly estimate the state of charge (SOC) and maximum available capacity of the battery without knowing initial SOC information.

Water content estimation is a key problem for studying the PEM fuel cell. When several hundred fuel cells are connected in serial and their active surface area is enlarged for sufficient power, the difference between cells becomes significant with respect to voltage and water content. The voltage of each cell is measurable by the cell voltage monitor (CVM) while it is difficult to estimate water content of the individual. Resistance of the polymer electrolyte membrane is monotonically related to its water content, so that the new online high frequency resistance (HFR) measurement technique is investigated to identify the uniformity of water content between cells and analyze its sensitivity to operating conditions in this paper. Firstly, the accuracy of the proposed technique is experimentally validated to be comparable to that of a commercialized electrochemical impedance spectroscopy (EIS) measurement equipment.

The formation is a crucial step in the production process of lithium-ion batteries (LIBs), during which the solid electrolyte interphase (SEI) is formed on the surface of the anode particles to passivate the electrode. It determines the performance of the battery, including its capacity and lifetime. A meticulously designed formation protocol is essential to regulate and optimize the stability of the SEI, ultimately achieving the optimal performance of the battery. Current research on formation protocols in lithium-ion batteries primarily focuses on temperature, current, and voltage windows. However, there has been limited investigation into the influence of different initial pressures on the formation process, and the evolution of cell pressure during formation remains unclear. In this study, a pressure-assisted formation device for lithium-ion pouch cells is developed, equipped with pressure sensors.

As a key component of in-vehicle intelligent voice technology, speech enhancement can extract clean speech signals contaminated by environmental noise to improve the perceptual quality and intelligibility of speech. It has extensive applications in the field of intelligent car cabins. Although some end-to-end speech enhancement methods based on time domain have been proposed, there is often limited consideration given to designing model architectures based on the characteristics of the speech signal. In this paper, we propose a new U-Net based speech enhancement framework that utilizes the temporal correlation of speech signals to reconstruct higher-quality and more intelligible clean speech.

Speech enhancement can extract clean speech from noise interference, enhancing its perceptual quality and intelligibility. This technology has significant applications in in-car intelligent voice interaction. However, the complex noise environment inside the vehicle, especially the human voice interference is very prominent, which brings great challenges to the vehicle speech interaction system. In this paper, we propose a speech enhancement method based on target speech features, which can better extract clean speech and improve the perceptual quality and intelligibility of enhanced speech in the environment of human noise interference. To this end, we propose a design method for the middle layer of the U-Net architecture based on Long Short-Term Memory (LSTM), which can automatically extract the target speech features that are highly distinguishable from the noise signal and human voice interference features in noisy speech, and realize the targeted extraction of clean speech.

Accurate prediction temperature variation of electric drive transmission (EDT) can effectively monitor its abnormal temperature rise that may occur under high speed and heavy load working conditions, so as to ensure the vehicles’ safe operation. In this paper, combined with real temperature and input/output characteristic data collected from EDT test platform under different working conditions, a spatio-temporal relationship dynamic graph convolution neural network based on least square method (OLS-DRGCN) for temperature prediction is proposed. Firstly, OLS is used to estimate the EDT’s internal temperature based on partial sensor information as the input of OLS-DRGCN. Secondly, the spatial dependence relationship of each temperature node is dynamically learned through node embedding and the dynamic thermal network topology of EDT is constructed. Meanwhile, the timing rule of each temperature node is obtained through the gated recurrent unit.

The optimization of speed holds critical significance for pure electric vehicles. In multi-intersection scenarios, the determination of terminal velocity plays a crucial role in addressing the complexities of the speed optimization problem. However, prevailing methodologies documented in the literature predominantly adhere to a fixed speed constraint derived from traffic light regulations, serving as the primary basis for the terminal velocity constraint. Nevertheless, this strategy can result in unnecessary acceleration and deceleration maneuvers, consequently leading to an undesirable escalation in energy consumption. To mitigate these issues and attain an optimal terminal velocity, this paper proposes an innovative speed optimization method that incorporates a terminal-velocity heuristic. Firstly, a traffic light state model is established to determine the speed range required to avoid coming to a stop at signalized intersections.

The functions of modern intelligent connected vehicles are becoming increasingly complex and diverse, and software plays an important role in these advanced features. In order to decouple the software and the hardware and improve the portability and reusability of code, Service-Oriented Architecture (SOA) has been introduced into the automotive industry. Data Distribution Service (DDS) is a widely used communication middleware which provides APIs for service-oriented Remote Procedure Call (RPC) and Service-Oriented Communications (SOC). By using DDS, application developers can flexibly define the data format according to their needs and transfer them more conveniently by publishing and subscribing to the corresponding topic. However, current open source DDS protocols all use unicast communication during the transmission of user data. When there are multiple data readers subscribing to the same topic, the data writer needs to send a unicast message to each data reader individually.

As one of the pollutants that cannot be ignored, soot has a great impact on human health, environment, and energy conversion. In this investigation, the effect of residence time (25ms, 35ms, and 45ms) and ammonia on morphology and nanostructure of soot in laminar ethylene flames has been studied under atmospheric conditions and different flame heights (15 mm and 30 mm). The transmission electron microscopy (TEM) and high-resolution transmission electron microscope (HRTEM) are used to obtain morphology of aggregates and nanostructure of primary particles, respectively. In addition, to analyze the nanostructure of the particles, an analysis program is built based on MATLAB software, which is able to obtain the fringe separation distance, fringe length, and fringe tortuosity parameters of primary particles, and has been verified by the multilayer graphene interlayer distance.

The problem of keeping the stable starting performance of diesel engine under high altitude and low temperature conditions has been done a lot of research in the field of diesel engine, but there is a lack of research on extreme conditions such as above 2000 meters above sea level and below 0°C. Aiming at solving the cold start problem of diesel engine in extreme environment, a set of chamber system of cold start environment diesel engine was constructed to simulate environment of 3000m altitude and -20°C. A series of experimental research was conducted on cold start efficiency optimization strategy of a certain type of diesel engine at 3000m altitude and -20°C. In parallel, a diesel engine model was constructed through Chemkin to explore the influence of the three parameters of compression ratio, stroke length, and fuel injection advance angle on the first cold start cycle of diesel engine at 4000m altitude and -20°C.

The on-ramp merging driving scenario is challenging for achieving the highest-level autonomous driving. Current research using reinforcement learning methods to address the on-ramp merging problem of automated vehicles (AVs) is mainly designed for a single AV, treating other vehicles as part of the environment. This paper proposes a control framework for cooperative on-ramp merging of multiple AVs based on multi-agent deep reinforcement learning (MADRL). This framework facilitates AVs on the ramp and adjacent mainline to learn a coordinate control policy for their longitudinal and lateral motions based on the environment observations. Unlike the hierarchical architecture, this paper integrates decision and control into a unified optimal control problem to solve an on-ramp merging strategy through MADRL.

In the field of vehicle aerodynamic simulation, Reynold Averaged Navier-Stokes (RANS) model is widely used due to its high efficiency. However, it has some limitations in capturing complex flow features and simulating large separated flows. In order to improve the computational accuracy within a suitable cost, the Field Inversion and Machine Learning (FIML) method, based on a data-driven approach, has received increasing attention in recent years. In this paper, the optimal coefficients of the Generalized k-ω (GEKO) model are firstly obtained by the discrete adjoint method of FIML, utilizing the results of wind tunnel experiments. Then, the mapping relationship between the flow field characteristics and the optimal coefficients is established by a neural network to augment the turbulence model.

Recently, several datasets have become available for occupant monitoring algorithm development, including real and synthetic datasets. However, real data acquisition is expensive and labeling is complex, while virtual data may not accurately reflect actual human physiology. To address these issues and obtain high-fidelity data for training intelligent driving monitoring systems, we have constructed a hybrid dataset that combines real driving image data with corresponding virtual data generated from 3D driving scenarios. We have also taken into account individual anthropometric measures and driving postures. Our approach not only greatly enriches the dataset by using virtual data to augment the sample size, but it also saves the need for extensive annotation efforts. Besides, we can enhance the authenticity of the virtual data by applying ergonomics techniques based on RAMSIS, which is crucial in dataset construction.

The software installed in Electronic Control Units (ECUs) has witnessed a significant scale expansion as the functionality of Intelligent Connected Vehicles (ICVs) has become more sophisticated. To seek convenient long-term functional maintenance, stakeholders want to access ECUs data or update software from anywhere via diagnostic. Accordingly, as one of the external interfaces, Diagnostics over Internet Protocol (DoIP) is inevitably prone to malicious attacks. It is essential to note that cybersecurity threats not only arise from inherent protocol defects but also consider software implementation vulnerabilities. When implementing a specification, developers have considerable freedom to decide how to proceed. Differences between protocol specifications and implementations are often unavoidable, which can result in security vulnerabilities and potential attacks exploiting them.

Accurate and reliable localization in GNSS-denied environments is critical for autonomous driving. Nevertheless, LiDAR-based and camera-based methods are easily affected by adverse weather conditions such as rain, snow, and fog. The 4D Radar with all-weather performance and high resolution has attracted more interest. Currently, there are few localization algorithms based on 4D Radar, so there is an urgent need to develop reliable and accurate positioning solutions. This paper introduces RIO-Vehicle, a novel tightly coupled 4D Radar/IMU/vehicle dynamics within the factor graph framework. RIO-Vehicle aims to achieve reliable and accurate vehicle state estimation, encompassing position, velocity, and attitude. To enhance the accuracy of relative constraints, we introduce a new integrated IMU/Dynamics pre-integration model that combines a 2D vehicle dynamics model with a 3D kinematics model.

LiDAR and camera fusion have emerged as a promising approach for improving place recognition in robotics and autonomous vehicles. However, most existing approaches often treat sensors separately, overlooking the potential benefits of correlation between them. In this paper, we propose a Cross- Modality Module (CMM) to leverage the potential correlation of LiDAR and camera features for place recognition. Besides, to fully exploit potential of each modality, we propose a Local-Global Fusion Module to supplement global coarse-grained features with local fine-grained features. The experiment results on public datasets demonstrate that our approach effectively improves the average recall by 2.3%, reaching 98.7%, compared with simply stacking of LiDAR and camera.

Radar is playing more and important role in multiple object detection and tracking system due to the fact that Radar can not only determine the velocity instantly but also it is less influenced by environment conditions. However, Radar faces the problem that it has many detection clutter，false alarms and detection results are easily affected by the reflected echoes of road boundary in traffic scenes. Besides this, With the increase of the number of targets and the number of effective echoes, the number of interconnection matrices increases exponentially in joint probability data association, which will seriously affect the real-time and accuracy of high-speed scene algorithms.in the tracking system. So, A method of using millimeter wave radar to detect and fit the boundary guardrail of high-speed road is proposed, and the fitting results are applied to the vehicle detection and tracking system to improve the tracking accuracy.