Search Results

For intelligent vehicles, a robust perception system relies on training datasets with a large variety of scenes. The architecture of federated learning allows for efficient collaborative model iteration while ensuring privacy and security by leveraging data from multiple parties. However, the local data from different participants is often not independent and identically distributed, significantly affecting the training effectiveness of autonomous driving perception models in the context of federated learning. Unlike the well-studied issues of label distribution discrepancies in previous work, we focus on the challenges posed by scene heterogeneity in the context of federated learning for intelligent vehicles and the inadequacy of a single scene for training multi-task perception models. In this paper, we propose a federated learning-based perception model training system.

To improve the braking energy recovery rate of pure electric garbage removal vehicles and ensure the braking effect of garbage removal vehicles, a strategy using particle swarm algorithm to optimize the regenerative braking fuzzy control of garbage removal vehicles is proposed. A multi-section front and rear wheel braking force distribution curve is designed considering the braking effect and braking energy recovery. A hierarchical regenerative braking fuzzy control strategy is established based on the braking force and braking intensity required by the vehicle. The first layer is based on the braking force required by the vehicle, based on the front and rear axle braking force distribution plan, and uses fuzzy controllers.

Autonomous vehicles require the collaborative operation of multiple modules during their journey, and enhancing tracking performance is a key focus in the field of planning and control. To address this challenge, we propose a cooperative control strategy, which is designed based on the integration of model predictive control (MPC) and a dual proportional–integral–derivative approach, referred to as collaborative control of MPC and double PID (CMDP for short in this article).The CMDP controller accomplishes the execution of actions based on information from perception and planning modules. For lateral control, the MPC algorithm is employed, transforming the MPC’s optimal problem into a standard quadratic programming problem. Simultaneously, a fuzzy control is designed to achieve adaptive changes in the constraint values for steering angles.

With the development of highway transportation and automobile industry technology, highway truck overload phenomenon occurs frequently, which poses a danger to road safety and personnel life safety. So it is very important to identify the overload phenomenon. Traditionally, static detection is adopted for overload identification, which has low efficiency. Aiming at this phenomenon, a dynamic overload identification method is proposed. Firstly, the coupled road excitation model of vehicle speed and speed bump is established, and then the 4-DOF vehicle model of half car is established. At the same time, considering that the double input vibration of the front and rear wheels will be coupled when vehicle passes through the speed bump, the model is decoupled. Then, the vertical trajectory of the body in the front axle position is obtained by Carsim software simulation.

Intelligent sweeper vehicle is gradually applied to human life, in which the accuracy of garbage identification and classification can improve cleaning efficiency and save labor cost. Although Deep Learning has made significant progress in computer vision and the application of semantic network segmentation can improve waste identification rate and classification accuracy. Due to the loss of some spatial information during the convolution process, coupled with the lack of specific datasets for garbage identification, the training of the network and the improvement of recognition and classification accuracy are affected. Based on the Unet algorithm, in this paper we adjust the number of input and output channels in the convolutional layer to improve the speed during the feature extraction part. In addition, manually generated datasets are used to greatly improve the robustness of the model.

Regenerative braking is an effective way to increase the cruising range of vehicles. In commercial vehicles with large vehicle mass, regenerative braking can be maintained in a high-power working state for a long time theoretically because of the large braking torque and long braking time. But in fact, it is often impossible to run at full power because of battery safety problems. In this paper, a control strategy is designed to maintain the maximum power operation of regenerative braking as much as possible. The maximum charging power of the battery is obtained through the battery model, and it is set as the battery limiting parameter. The regenerative braking torque and power are obtained by using the motor model. The eddy current retarder is used to absorb the excess power that the battery can't bear, and the braking torque of the eddy current retarder is calculated. Finally, mechanical braking is used to make up the insufficient braking torque.

Accurate surrounding vehicle motion prediction is critical for enabling safe, high quality autonomous driving decision-making and motion planning. Aiming at the problem that the current deep learning-based trajectory prediction methods are not accurate and effective for extracting the interaction between vehicles and the road environment information, we design a target vehicle intention-aware dual attention network (IDAN), which establishes a multi-task learning framework combining intention network and trajectory prediction network, imposing dual constraints. The intention network generates an intention encoding representing the driver’s intention information. It inputs it into the attention module of the trajectory prediction network to assist the trajectory prediction network to achieve better prediction accuracy.

With the improvement of sensor accuracy, sensor data plays an increasingly important role in intelligent vehicle motion control. Good use of sensor data can improve the control of vehicles. However, data-based end-to-end control has the disadvantages of poorly interpreted control models and high time costs; model-based control methods often have difficulties designing high-fidelity vehicle controllers because of model errors and uncertainties in building vehicle dynamics models. In the face of high-speed steering conditions, vehicle control is difficult to ensure stability and safety. Therefore, this paper proposes a hybrid model and data-driven control method. Based on the vehicle state data and road information data provided by vehicle sensors, the method constructs a deep neural network based on LSTM and Attention, which is used as a compensator to solve the performance degradation of the LQR controller due to modeling errors.

The articulated steering system is widely used in engineering vehicles due to its high mobility and low steering radius. The design parameters have a vital impact on the selection of the steering system assemblies, such as the operation stroke, pressure, and force of the hydraulic cylinders during the steering process, which will affect the system weight. The system energy consumption is also relevant to the geometry parameters. According to the kinetic analysis of the steering system and dynamic analysis of the steering process, the kinetic model of an engineering vehicle steering system is built, and the length and pressure variation of the cylinder is calculated and validated by the field test. The influence of the factors is analyzed based on the established model. To lower the system weight, needed pressure, and force, the multi-objective particle swarm optimization method is initiated to optimize the geometry parameter of the articulated steering system.

The development of intelligent transportation improves road efficiency, reduces automobile energy consumption, and improves driving safety. The core of intelligent transportation is the two-way information interaction between vehicles and the road environment. At present, road environmental information can flow to the vehicle, while the vehicle’s information rarely flows to the outside world. The electronic throttle and electronic braking systems of some vehicles use sensors to get the state of the accelerator and brake pedal, which can be transmitted to the outside environment through technologies such as the Internet of Vehicles. But the Internet of Vehicles technology has not been widely used, and it relies on signal sources, which is a passive way of information acquisition. In this paper, an active identification method is proposed to get the vehicle pedal on-off state as well as the driver’s operation behavior through existing traffic facilities.

When driving in mountainous areas, vehicles often encounter long downhill sections. Due to the large mass of bus and the drum brake with poor heat dissipation effect, it is easy for bus to produce braking thermal decay in long downhill section, which makes the vehicle out of control and causes safety accidents. The braking methods of parallel hybrid electric bus include drum braking, engine braking and regenerative braking, whose torque models are established in this paper. The coasting test in Trucksim is used to verify the correctness of the engine braking torque model. Based on coupling braking torque curve with vehicle speed in different gradient, the stable speed is determined and the shift strategy is proposed. The temperature rise model of brake drum is established to analyze the temperature change of brake drum during long downhill. Then, according to the ramp data of G22 freeway, the above models are simulated.

Road traffic accidents resulting from alcohol-impaired driving are increasing globally despite several measures, currently in place, to curb the trend. For this reason, recent research aims at integrating alcohol early-detection systems and driving simulator experiments to identify intoxicated drivers. However, driving simulator experiments on drunk driving have focused mostly on male participants than female drivers whose characteristics have scarcely been explored. Hence in this paper, vehicle dynamic control inputs on steering, braking, and acceleration performance of 75 licensed female drivers with an upshot of alcohol at four different blood alcohol concentration (BAC) levels (0%, 0.03%, 0.05%, and 0.08%) were investigated. The participants completed simulated driving in a fixed-based simulator experiment coupled with real-time ecological scenarios to extract discrete responses.

The mountain roads are curved and complicated, with undulating terrain and large distance between charging stations. Compared with traditional powered vehicles, in addition to safety issues, pure electric vehicles also need to deal with the driving range issue. At present, the relevant researches on automobile driving in mountainous areas mainly focus on the driving safety of traditional fuel oil vehicles when going uphill and downhill, while there are few researches on the driving planning of pure electric commercial vehicles on curved slope road. This paper presents a speed planning method for pure electric commercial vehicles based on vehicle-road collaboration technology. First, establish the vehicle dynamics model, analyze the vehicle dynamics characteristics when passing the downhill curve, calculate the safe speed range of the vehicle when passing the downhill curve, and establish the safe speed model of the downhill curve.

There are a large number of curves and slopes in the mountainous areas. Unreasonable acceleration and deceleration in these areas will increase the burden of the brake system and the fuel consumption of the vehicle. The main purpose of this paper is to introduce a speed planning and promotion system for commercial vehicles in mountainous areas. The wind, slope, curve, engine brake, and rolling resistances are analyzed to establish the thermal model of the brake system. Based on the thermal model, the safe speed of the brake system is acquired. The maximum safe speed on the turning section is generated by the vehicle dynamic model. And the economic speed is calculated according to the fuel consumption model. The planning speed is provided based on these models. This system can guide the driver to handle the vehicle speed more reasonably.

Regenerative braking is an effective technology to extend the driving range of electrified vehicles by recovering kinetic energy from braking. This paper focuses on the design of the regenerative braking control strategy for a commercial vehicle which requires significantly larger braking power than passenger cars. To maximize the energy recovery while ensuring the braking efficiency of the vehicle and its braking safety, this paper proposed a fuzzy logic strategy for regenerative braking control, and a feasibility study was conducted for an electric van. The work includes in three steps. Firstly, state variables that significantly affect regenerative braking performance, i.e., vehicle speed, battery State-of-Charge (SOC), and braking intensity, are identified based on mathematical modelling of the vehicle system dynamics in braking maneuver.

Braking energy recovery is an important method for Battery Electric Vehicle (BEV) to save energy and increase driving range. The vehicle braking system performs regenerative braking control based on driver operations. Different braking operations have a significant impact on energy recovery efficiency. This paper proposes a method for planning the braking process of a BEV based on the Intelligent Vehicle Infrastructure Cooperative System (IVICS). By actively planning the braking process, the braking energy recovery efficiency is improved. Vehicles need to decelerate and brake before entering a curve. The IVICS is used to obtain information about the curve section ahead of the vehicle's driving route. Then calculating the reference speed of the curve, and obtaining the vehicle's braking target in advance, so as to actively plan the vehicle braking process.

Discretionary lane changing is commonly seen in highway driving. Intelligent vehicles are expected to change lanes discretionarily for better driving experience and higher traffic efficiency. This study proposed to optimize the decision-making and trajectory-planning process so that intelligent vehicles made lane changes not only with driving safety taken into account, but also with the goal to improve driving comfort as well as to meet the driver’ s expectation. The mechanism of how various factors contribute to the driver’s intention to change lanes was studied by carrying out a series of driving simulation experiments, and a Lane-Changing Intention Generation (LCIG) model based on Bi-directional Long Short-Term Memory (Bi-LSTM) was proposed.

With the increase of car ownership and the complex and crowded parking environment, it is difficult for drivers to complete the parking operation quickly and accurately, which may cause traffic accidents such as vehicle collisions and road jams because of poor parking skills. The emergence of an automatic parking system can help drivers park safely and reduce the occurrence of safety accidents. In this paper, the neural network identifier on the control method of an adaptive integral derivative of a neural network is proposed for an automatic parallel parking system with front-wheel steering is studied by using MATLAB/Simulink environment, and the simulation is carried out. Firstly, according to vehicle parameters and obstacle avoidance constraints, the minimum parking space, and parking starting position are calculated. Meanwhile, the path planning of parallel parking spaces is carried out by quintic polynomial.

Electronic Stability Control (ESC) is an important measure to proactively guarantee vehicle safety. In this paper, the method of four-wheel hub-motor torque control is compared with the traditional single-wheel hydraulic brake control in ESC system. The control strategy adopts the hierarchical structure. In upper controller, the stability of the vehicle is identified by threshold method, the additional yaw moment control uses a way to get the moment including feedforward and feedback parts based on the linear quadratic regulator (LQR). The medium controller is tire slip rate control, in order to get the optimal target slip rate from the upper additional yaw moment, a method of quadratic programming to optimize the longitudinal force is proposed for each wheel. The inputs of tire state for the magic tire model is introduced so as to calculate the target slip rate from the target longitudinal force.

Deep Deterministic Policy Gradient (DDPG) is one of the Deep Reinforcement Learning algorithms. Because of the well perform in continuous motion control, DDPG algorithm is applied in the field of self-driving. Regarding the problems of the instability of DDPG algorithm during training and low training efficiency and slow convergence rate. An improved DDPG algorithm based on segmented experience replay is presented. On the basis of the DDPG algorithm, the segmented experience replay select the training experience by the importance according to the training progress to improve the training efficiency and stability of the training model. The algorithm was tested in an open source 3D car racing simulator called TORCS. The simulation results demonstrate the training stability is significantly improved compared with the DDPG algorithm and the DQN algorithm, and the average return is about 46% higher than the DDPG algorithm and about 55% higher than the DQN algorithm.