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.

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.

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.

With the extension of intelligent vehicles from individual intelligence to group intelligence, intelligent vehicle platoons on intercity highways are important for saving transportation costs, improving transportation efficiency and road utilization, ensuring traffic safety, and utilizing local traffic intelligence [1]. However, there are several problems associated with vehicle platoons including complicated vehicle driving conditions in or between platoon columns, a high degree of mutual influence, dynamic optimization of the platoon, and difficulty in the cooperative control of lane change. Aiming at the dual-column intelligent vehicle platoon control (where “dual-column” refers to the vehicle platoon driving mode formed by multiple vehicles traveling in parallel on two adjacent lanes), a multi-agent model as well as a cooperative control method for lane change based on null space behavior (NSB) for unmanned platoon vehicles are established in this paper.

With the development of brake-by-wire technology, electro-hydraulic composite braking technology came into being. This technology distributes the total braking force demand into motor regenerative braking force and hydraulic braking force, and can achieve a high energy recovery rate. The existing composite braking control belongs to single-channel control, i.e., the four wheel braking pressures are always the same, so the hydraulic braking force distribution relationship of the front and rear wheels does not change. For single-axle-driven electric vehicles, the additional regenerative braking force on the driven wheels will destroy the original braking force distribution relationship, resulting in reduced braking efficiency of the driven wheels, which are much easier to lock under poor road adhesion conditions.

Reinforcement learning is a promising approach to solve the energy management for hybrid electric vehicles. In this paper, based on the DQN (Deep Q-Network) reinforcement learning algorithm which is widely used at present, double DQN, dueling DQN and learning from demonstration are integrated; states, actions, rewards and the experience pool based on the characteristics of series-parallel multi-speed hybrid powertrain are designed; the hybrid energy management strategy based on D4QN (Double Dueling Deep Q-Network with Demonstrations) algorithm is established. Based on the training results of D4QN algorithm, multi-parameter analysis under state and action space, HCU (Hybrid control unit) application and MIL (Model in-loop) test research are conducted.

With the increase of motor speed and the deterioration of operating environment, it is more difficult to predict the transient temperature field (TTF). Meanwhile, it is difficult to obtain the temperature test dataset of key nodes under various complete road conditions, so the cost of bench test or real vehicle test is high. Therefore, it is of great significance to establish a high fidelity, lightweight temperature prediction model which can be applied to real vehicle thermal management for ensuring the safe and stable operation of motor. In this paper, a physical model simulating electromagnetic-heat-flow multi-physical coupling of permanent magnet synchronous motor (PMSM) in electric drive gearbox (EDG) is established, and the correctness of the model is verified by the actual EDG bench test.

The intersection is recognized as the most dangerous area because of the restricted road structures and indeterminate traffic regulations. Therefore, according to the Vehicle-to-everything (V2X) communication, Intelligent Transportation Systems (ITS), and Digital Twin data, we present a potential energy field method to establish the general characteristics of intersection traffic safety, evaluate the safety situation of intersection and assist intersection traffic participants in passing through the intersection safer and more efficient. The resulting potential energy field method is established by the contour line of traffic participants' potential energy, which is constructed as a superposition of disparate energies, such as boundary potential energy, body potential energy, and velocity potential energy. The intersection traffic safety is evaluated by the potential energy field characteristic of simultaneous intersection traffic participants.

With the popularity of automated vehicles, the future mixed traffic flow contains automated vehicles with different degrees of intelligence developed by other manufacturers. Therefore, simulating the interaction behavior of automated vehicles with varying levels of intelligence is crucial for testing and evaluating autonomous driving systems. Since the algorithm of traffic vehicles with various intelligence levels is difficult to obtain, it leads to hardships in quantitatively characterizing their interaction behaviors. Therefore, this paper designs a new automated vehicle test platform to solve the problem. The intelligent vehicle testbed with multiple personalized in-vehicle control units in the loop consists of three parts: 1. Multiple controllers in the loop to simulate the behavior of traffic vehicles；2. The central console applies digital twin technology to share the same traffic scenario between the tested vehicle and the traffic vehicle, creating a mixed traffic flow. 3.

High-speed vehicles in low illumination environments severely blur the images used in object detectors, which poses a potential threat to object detector-based advanced driver assistance systems (ADAS) and autonomous driving systems. Augmenting the training images for object detectors is an efficient way to mitigate the threat from motion blur. However, little attention has been paid to the motion of the vehicle and the position of objects in the traffic scene, which limits the consistence between the resulting augmented images and traffic scenes. In this paper, we present a vehicle kinematics-based image augmentation algorithm by modeling and analyzing the traffic scenes to generate more realistic augmented images and achieve higher robustness improvement on object detectors against motion blur. Firstly, we propose a traffic scene model considering vehicle motion and the relationship between the vehicle and the object in the traffic scene.

To overcome the shortcoming that vehicles with multiple steering modes need to switch steering modes at parking or very low speeds, a dynamic switch method of steering modes based on MOEA/D (Multi-objective Evolutionary Algorithm Based on Decomposition) was proposed for 4WID-4WIS (Four Wheel Independent Drive-Four Wheel Independent Steering) electric vehicle, considering the smoothness of dynamic switch, the lateral stability of the vehicle and the energy economy of tires. First of all, the vehicle model of 4WID-4WIS was established, and steering modes were introduced and analyzed. Secondly, the conditions for the dynamic switch of steering modes were designed with the goal of stability and safety. According to different constraints, the control strategy was formulated to obtain the target angle of the active wheels. Then aiming at the smoothness of the dynamic switch, the active wheel angle trajectory was constructed based on the B-spline theory.

Electric vehicle sharing (EVS) can alleviate traffic congestion and reduce emissions. However, the poor user experience and lack of word-of-mouth effect lead to the low utilization rate of EVS in China. Based on the demand and pain points of EVS, this paper concentrates on travel mode choice behavior of consumers under social networks and establishes an agent-based model for EVS diffusion. The results show that: (1) Social networks can promote the diffusion of EVS and the number of opinion leaders and the number of fans of opinion leaders play an important role. (2) Consumers are more sensitive to travel costs than non-travel time now, but with the improvement of demand for travel experience, consumers are more concerned with non-travel time. (3) The non-travel time of EVS needs to be reduced to 9, 8 and 7 minutes respectively to retain users when the travel cost increases to 0.7, 0.8 and 0.9 Yuan/minute.

A formal gesture recognition based on optics has limitations, but millimeter-wave (MMW) radar has shown significant advantages in gesture recognition. Therefore, the MMW radar has become the most promising human-computer interaction equipment, which can be used for human-computer interaction of vehicle personnel. This paper proposes a multi-branch network based on a residual neural network (ResNet) to solve the problems of insufficient feature extraction and fusion of the MMW radar and immense algorithm complexity. By constructing the gesture sample library of six gestures, the MMW radar signal is processed and coupled to establish the relationship between the motion parameters of the distance, speed, and angle of the gesture information and time, and the depth features are extracted. Then the three depth features are fused. Finally, the classification and recognition of MMW radar gesture signals are realized through the full connection layer.

Gas diffusion layer (GDL), as a critical constituent of the proton exchange membrane fuel cell (PEMFC), plays a key role in mass, heat, electron, and species transport. GDL generally has two distinct layers: a macro-porous substrate (MPS) and a micro-porous layer (MPL). The fibers in MPS and the cracks formed during the deposition process on the surface of MPL change the overall transport capacity and effect the output performance of PEMFC. In this paper, methods of identifying the structural features of fibers and cracks in GDL images based on artificial intelligence are proposed. The block probabilistic Hough transform and the quadric voting based on the weighted K-means algorithm are programmed to realize the fiber feature extraction, and the crack feature extraction is realized by the regional connectivity algorithm and the geometric feature calculation based on the circumscribed graph of the crack region.

Deep neural network models have been widely used for environment perception of intelligent vehicles. However, due to models’ innate probabilistic property, the lack of transparency, and sensitivity to data, perception results have inevitable uncertainties. To compensate for the weakness of probabilistic models, many pieces of research have been proposed to analyze and quantify such uncertainties. For safety-critical intelligent vehicles, the uncertainty analysis of data and models for environment perception is especially important. Uncertainty estimation can be a way to quantify the risk of environment perception. In this regard, it is essential to deliver a comprehensive survey. This work presents a comprehensive overview of uncertainty estimation in deep neural networks for environment perception of intelligent vehicles.

For high levels autonomous driving functions, the Decision Layer often takes on more responsibility due to the requirement of facing more diverse and even rare conditions. It is very difficult to accurately find a safe and efficient lane change timing when autonomous vehicles encounter complex traffic flow and need to change lanes. The traditional method based on rules and experiences has the limitation that it is difficult to be taken into account all possible conditions. Therefore, this paper designs a lane-changing decision algorithm based on data-driven and machine learning, and uses the DQN (Deep Q Network) algorithm in Reinforcement Learning to determine the appropriate lane-changing timing and target lane. Firstly, the scene characteristics of the highway are analyzed, the input and output of the decision-making model are designated and the data from the Perception Layer are processed.

The past decade has witnessed the rapid development of autonomous parking technology, since it has promising capacity to improve traffic efficiency and reduce the burden on drivers. However, it is prone to the trap of self-centeredness when each vehicle is automated parking in isolation. And it is easy to cause traffic congestion and even chaos when multiple autonomous vehicles require of parking into the same lot. In order to address the multiple vehicle parking problem, we propose a parking planning method with genetic algorithm. Firstly, an optimal mathematic model is established to describe the multiple autonomous vehicle parking problem. Secondly, a genetic algorithm is designed to solve the optimization problem. Thirdly, illustrative examples are developed to verify the parking planner. The performance of the present method indicates its competence in addressing parking multiple autonomous vehicles problem.

Based on the sample data obtained from the bench test of a four-cylinder naturally aspirated CNG engine, three different machine learning models, BP, SVM and GRNN, were used to develop the intake charge prediction model for the intake system of this engine, in which engine speed, intake manifold pressure and intake temperature, VVT angle and gas injection time were taken as input parameters and intake charge was used as output parameter. The comparative analysis of the experimental data and model prediction data showed that the mean absolute error (MAE) of BP model, GRNN model, and SVM model were 2.69, 8.11and 5.13, and the root mean square error (MSE) were 3.53, 9.29, and 7.17, respectively. BP model has smaller prediction error and higher accuracy than SVM and GRNN models, which is more suitable for the prediction of the intake charge of this type of four-cylinder naturally aspirated CNG engine.