Search Results

In automatic driving application, the velocity planner can be considered as a key factor to ensure the safety and comfort. One of the most important tasks of the velocity planner is to simulate the velocity characteristics of human drivers. In this paper, two Driver In-the-Loop (DIL) experiments are designed to explain velocity characteristics of human drivers. In the first experiment, static obstacles are placed on both sides of the straight road to shorten the cross range that vehicles can driver across. Moreover, different cross ranges are set to study the influence of the steering wheel error. In the second experiment, velocity characteristics are investigated under the condition of different road widths and curvatures in a U-turn road contour. In both tests, different drivers’ preview behavior is analyzed through the operation of throttle, braking, and steering.

At present, the development of autonomous driving technology is still immature, and there is still a long way until fully driverless vehicles. Therefore, the state of the driver is still an important factor affecting traffic safety, and it is of great significance to detect the driver’s distracted behavior. In the task of driver distracted behavior detection, some characteristics of driver behavior in the cockpit can be further utilized to improve the detection performance. Compared with general human behaviors, driving behaviors are confined to enclosed space and are far less diverse. With this in mind, we propose a sparse spatiotemporal transformer which extracts local spatiotemporal features by segmenting the video at the low level of the model, and filters out local key spatiotemporal information associated with larger attention values based on the attention map in the middle layer, so as to enhance the high-level global semantic features.

An accurate and timely positioning of the vehicle is required at all times for autonomous driving. The global navigation satellite system (GNSS), even when integrated with costly inertial measurement units (IMUs), would often fail to provide high-accuracy positioning due to GNSS-challenged environments such as urban canyons. As a result, visual odometry is proposed as an effective complimentary approach. Although it’s widely recognized that visual odometry should be developed based on both visible and infrared images to address issues such as frequent changes in ambient lightening conditions, the mechanism of visible-infrared fusion is often poorly designed. This study proposes a Generative Adversarial Network (GAN) based model comprises a generator, which aims to produce a fused image combining infrared intensities and visible gradients, and a discriminator whose target is to force the fused image to retain as many details that exist mostly in visible images as possible.

For series hybrid electric vehicles (SHEV), rule-based strategies are realistic and powerful in real-time applications. However, the previous rule-based strategy cannot strike a balance between the best fuel economy and the best battery performance while maintaining the advantages of real-time applications. In order to obtain higher efficiency and reduce battery consumption, we have developed an adaptive hybrid thermostat strategy. On the basis of maintaining the load leveling of the thermostat strategy, the threshold-changing mechanism is added to realize the adaptive adjustment of the engine starting power under different SOC conditions, so as to achieve the goal of prolonging the battery life. In addition, the more fuel-efficient emergency handling rules designed to further reduce comprehensive fuel consumption.

Vehicles equipped with articulated steering systems have advantages such as low energy consumption, simple structure, and excellent maneuverability. However, due to the specific characteristics of the system, these vehicles often face challenges in terms of lateral stability. Addressing this issue, this paper leverages the precise and independently controllable wheel torques of a hub motor-driven vehicle. First, an equivalent double-slider model is selected as the dynamic control model, and the control object is rationalized. Subsequently, based on the model predictive control method and considering control accuracy and robustness, a weight-variable adaptive model predictive control approach is proposed. This method addresses the optimization challenges of multiple systems, constraints, and objectives, achieving adaptive control of stability, maneuverability, tire slip ratio, and articulation angle along with individual wheel torques during the entire steering process of the vehicle.

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.

People, vehicles and circumstances are the three key factors, which affect transportation systems. Offering more information to the driver and helping him observe on all sides so that he can make decisions correctly are of great importance for reducing accidents. According to the present traffic regulations, in this paper we focus on the rules and process used during steering and proposed to implement them in a car information central control system based on CAN. A comparison of the brake time between brake by driver and by radars revealed the great interest of using ECUs connected by CAN network.

Hydraulic retarder has been widely applied on military vehicles and heavy commercial vehicles because of it could provide great brake torque and has lasting working time [1]. In order to reduce driver's frequent actions in braking process and prevent hydraulic retarder system from overheating, it is need to apply constant braking torque control, this control target has a strict requirement to hydraulic control system design. Many parameters often require repeated test to determine, which increases the R&D cost and extends the research cycle. This paper tries to find a time-efficient research method of hydraulic retarder control system through studying on a heavy military vehicle hydraulic retarder system. Hydraulic retarder model is set up through test data. The hydraulic control system is built based on AMESim. Controller model is set up based on PID control. The whole vehicle brake model is built based on MATLAB/Simulink.

With the rapid development of the logistics and transportation industry, heavy-duty trucks play an increasingly important role in social life. However, due to the characteristics of large cargo loads, high center of mass and relatively narrow wheelbase, the driving stability of heavy trucks are poor, and it is easy to cause rollover accidents under high-speed driving conditions, large angle steering and emergency obstacle avoidance. To improve the roll stability of heavy trucks, it is necessary to design an active anti-rollover control system, through the analysis of the yaw rate and the load transfer rate of the vehicle, driving states can be estimated during the driving process. Under the intervention of the control system, the lateral transfer rate of heavy trucks can be reduced to correct the driving posture of the vehicle body and reduce the possibility of rollover accidents.

In the field of active safety, the active four-wheel-steering (4WS) system seems to be an attractive alternative and an effective tool to improve the vehicles' handling stability in lane-keeping control performance. Under normal using condition, the vehicle's lateral acceleration is comparatively small, and the mathematic relationship between the small side force excitation and the small slip angle of the tire is in the linear region. Furthermore, the effects of roll, heave, and pitch motions are neglected as well as the dynamic characteristics of the tires and suspension system in this work. Therefore, the linear quadratic control (LQC) theory is used to ensure that the output of the 4WS control system can keep track of the desired yaw rate and zero-sideslip-angle response can also be realized at the same time.

Driver distraction detection is crucial to driving safety when autonomous vehicles are co-piloted. Recognizing drivers’ behaviors that are highly related with distraction from real-time video stream is widely acknowledged as an effective approach mainly due to its non-intrusiveness. In recently years, deep learning neural networks have been adopted to by-pass the procedure of designing features artificially, which used to be the major downside of computer-vision based approaches. However, the detection accuracy and generalization ability is still not satisfying since most deep learning models extracts only spatial information contained in images. This research develops a driver distraction model based on a two-stream, spatial and temporal, convolutional neural network (CNN).

In order to improve the driving experience of drivers and the efficiency of vehicle development, a method of objective drivability for passenger car powertrain is proposed, which is based on prior knowledge, principal component analysis (PCA) and SMART principle. First, drivability parameters of powertrain for passenger cars are determined according to working principle of powertrain, including engine torque, engine speed, gearbox position, accelerate pedal, brake pedal, steering wheel angle, longitudinal acceleration and lateral acceleration, etc. The drivability quantitative index system is designed based on field test data, prior knowledge and SMART principles. Then, D-S evidence theory and sliding window method are applied to identify objective drivability evaluation conditions of powertrain for passenger cars, including static gearshift conditions, starting conditions, creep conditions, tip-in, tip out, upshift conditions, acceleration, downshift conditions and de-acceleration.

In order to improve the drivability of passenger cars with dual clutch transmission (DCT) and reveal the criteria for objective evaluation criteria and characteristic index and feature index division of vehicles under specific working conditions, a drivability evaluation system that integrates data-driven and the consistency between subjective and objective is proposed. At first, combined with the control principle and dynamics theory of specific working conditions, a quantitative index system of vehicle drivability is constructed, including three modules: data source, evaluation working conditions and objective indicators. Then, a novel intelligent drivability objective evaluation tools (I-DOET) is designed, including data acquisition, de-noising, working condition recognition, feature extraction and automatic scoring.

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.

Based on the fuzzy inference system, it constructs a discretionary lane-changing decision model for different types of preceding vehicles and compares and analyzes the parameter differences of their input membership functions. According to the driver questionnaire survey, the model uses three parameters that drivers can easily percept as the model input—preceding vehicle distance in the current lane, preceding vehicle distance in the target lane, and following-vehicle distance in the target lane—uses Next-Generation Simulation (NGSIM) vehicle trajectory data to optimize the input membership functions of models based on genetic algorithm according to different vehicle lane-changing trajectory data to analyze the impact of the preceding vehicle type before lane change to the intelligent lane-changing decision.

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.

Decision-making of lane-change for autonomous vehicles faces challenges due to the behavioral differences among human drivers in dynamic traffic environments. To enhance the performances of autonomous vehicles, this paper proposes a game theoretic decision-making method that considers the diverse Social Value Orientations (SVO) of drivers. To begin with, trajectory features are extracted from the NGSIM dataset, followed by the application of Inverse Reinforcement Learning (IRL) to determine the reward preferences exhibited by drivers with distinct Social Value Orientation (SVO) during their decision-making process. Subsequently, a reward function is formulated, considering the factors of safety, efficiency, and comfort. To tackle the challenges associated with interaction, a Stackelberg game model is employed.

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.

This paper proposed a model predictive control(MPC) based car-following control strategy for electric vehicles considering comfort, in order to improve the comfort of the car-following control system of electric vehicles. The MPC algorithm is improved in the following three aspects to improve the comfort: Firstly, a five-state longitudinal car-following model is adopted, so that the MPC algorithm can optimize the acceleration and acceleration change rate of the ego vehicle. Secondly, for the weight coefficients of the output vector and the input vector of the objective function, the fixed weight coefficients are changed into variable weight coefficients by the way of Nash equilibrium game, so that the control system can improve the weight of the parameters used to control the comfort under suitable driving conditions.