Search Results

Roundabouts are one of the most complex traffic environments in urban roads, and a key challenge for intelligent driving decision-making. Deep reinforcement learning, as an emerging solution for intelligent driving decisions, has the advantage of avoiding complex algorithm design and sustainable iteration. For the decision difficulty in roundabout scenarios, this paper proposes an artificial potential field based Soft Actor-Critic (APF-SAC) algorithm. Firstly, based on the Carla simulator and Gym framework, a reinforcement learning simulation system for roundabout driving is built. Secondly, to reduce reinforcement learning exploration difficulty, global path planning and path smoothing algorithms are designed to generate and optimize the path to guide the agent.

Adaptive cruise control is one of the key technologies in advanced driver assistance systems. However, improving the performance of autonomous driving systems requires addressing various challenges, such as maintaining the dynamic stability of the vehicle during the cruise process, accurately controlling the distance between the ego vehicle and the preceding vehicle, resisting the effects of nonlinear changes in longitudinal speed on system performance. To overcome these challenges, an adaptive cruise control strategy based on the Takagi-Sugeno fuzzy model with a focus on ensuring vehicle lateral stability is proposed. Firstly, a collaborative control model of adaptive cruise and lateral stability is established with desired acceleration and additional yaw moment as control inputs. Then, considering the effect of the nonlinear change of the longitudinal speed on the performance of the vehicle system.

Most of the skin injuries caused by traffic accidents, sports, falls, etc. are in the intermediate strain rate range (1-100s-1), and the injuries may occur at different sites, impact velocities, and orientations. To investigate the multifactorial mechanical properties of rat skin at intermediate strain rates, a three-factor, three-level experimental protocol was established using the standard orthogonal table L9(34), which includes site (upper dorsal, lower dorsal, and ventral side), strain rate (1s-1, 10s-1, and 100 s-1), and sampling orientation (0°, 45°, and 90° relative to the spine). Uniaxial tensile tests were performed on rat skin samples according to the protocol to obtain stress-stretch ratio curves. Failure strain energy was selected as the index, and the influence of each factor on these indexes, the differences between levels of each factor, and the influence of errors on the results were quantified by analysis of variance (ANOVA).

With the rapid development of intelligent driving technology, there has been a growing interest in the driving comfort of automated vehicles. As vehicles become more automated, the role of the driver shifts from actively engaging in driving tasks to that of a passenger. Consequently, the study of the passenger experience in automated driving vehicles has emerged as a significant research area. In order to examine the impact of automatic driving on passengers' riding experience in vehicle platooning scenarios, this study conducted real vehicle experiments involving six participants. The study assessed the subjective perception scores, eye movement, and electrocardiogram (ECG) signals of passengers seated in the front passenger seat under various vehicle speeds, distances, and driving modes. The results of the statistical analysis indicate that vehicle speed has the most substantial influence on passenger perception.

Steer-By-Wire (SBW) system directly transmits the driver's steering input to the wheels through electrical signals. However, the reliability of electronic equipment is significantly lower than that of mechanical structures, and the risk of failure increases, so it is important to conduct functional safety studies on SBW systems. This paper develops the functional safety of the SBW system according to the requirements of the international standard ISO26262, and first defines the relevant items and application scope of SBW system. Secondly, the Hazard and Operability (HAZOP) method was used to combine scenarios and possible dangerous events to carry out Hazard Analysis and Risk Assessment (HARA), and the Automotive Safety Integrity Level (ASIL) was obtained according to the three evaluation indicators of Exposure, Severity and Controlabillity, and then the corresponding safety objectives were established and Fault Tolerant Time Interval (FTTI) was set.

In this paper, tensile experiments were performed on the dorsal and ventral skin of rats, and the mechanical properties of the skin in these two sites were compared and analyzed. A three-factor experimental protocol of site (dorsal and ventral), strain rate (0.71s-1, 7.1×10-3s-1), and sampling orientation (0°, 45° and 90° relative to the spine) was established for tensile test using the L6(31×22) orthogonal table modified from the standard orthogonal table L4 (23). Uniaxial tensile experiments were performed on rat skin samples to calculate the stress-strain curve. The failure strain energy was selected as the index, and the sum of squared deviations of the factors to the index was calculated by analysis of variance (ANOVA), and the contributions of the factors to the failure strain energy were evaluated. The results showed that the site factor has the largest effect on the tensile strain energy with a contribution of 88.9% and a confidence level of 95%.

Accurate sensing of road conditions is one of the necessary technologies for safe driving of intelligent vehicles. Compared with the structured road, the unstructured road has complex road conditions, and the response characteristics of vehicles under different road conditions are also different. Therefore, accurately identifying the road categories in front of the vehicle in advance can effectively help the intelligent vehicle timely adjust relevant control strategies for different road conditions and improve the driving comfort and safety of the vehicle. However, traditional road identification methods based on vehicle kinematics or dynamics are difficult to accurately identify the road conditions ahead of the vehicle in advance. Therefore, this paper proposes an unstructured road region detection and road classification algorithm based on machine vision to obtain the road conditions ahead.

It is generally considered that the material properties of foam are the most important factors in vehicle seat, which affect the human-seat interface pressure. Therefore, only the role of foam is usually considered when the finite element method is used to simulate the human-seat interface pressure. In this paper, the mechanical properties and the modeling method of commonly used seat cover material were studied. The models of the seat with and without cover were established respectively according to the real-vehicle seat geometric data, and the human-seat interface pressure was simulated after the seat and human model consisting of bones, soft tissue and skin were assembled. The simulation result was compared with the actual measurement results from test, which verified the accuracy of the simulation and the role of seat cover in the human-seat interface pressure simulation.

Driving assistance system is regarded as an effective method to improve driving safety and comfort and is widely used in automobiles. However, due to the different driving styles of different drivers, their acceptance and comfort of driving assistance systems are also different, which greatly affects the driving experience. The key to solving the problem is to let the system understand the driving style and achieve humanization or personalization. This paper focuses on clustering and identification of different driving styles. In this paper, based on the driver's real vehicle experiment, a driving data acquisition platform was built, meanwhile driving conditions were set and drivers were recruited to collect driving information. In order to facilitate the identification of driving style, the correlation analysis of driving features is conducted and the principal component analysis method is used to reduce the dimension of driving features.

The hippocampus plays a crucial role in brain function and is one of the important areas of concern in closed head injury. Hippocampal injury is related to a variety of factors including the strength of mechanical load, animal age, and helmet material. To investigate the order of these factors on hippocampal injury, a three-factor, three-level experimental protocol was established using the L9(34) orthogonal table. A closed head injury experiment regarding impact strength (0.3MPa, 0.5MPa, 0.7MPa), rat age (eight- week-old, ten-week-old, twelve-week-old), and helmet material (steel, plastic, rubber) were achieved by striking the rat's head with a pneumatic-driven impactor. The number of hippocampal CA3 cells was used as an evaluation indicator. The contribution of factors to the indicators and the confidence level were obtained by analysis of variance.

With the aim of addressing the problem of inconsistency of the traditional proportion integration (PI) driver model with the actual driving behavior, a longitudinal driver model based on the elastic net regression (ENR) and adaptive network fuzzy inference system (ANFIS) method is proposed. First, longitudinal driving behavior data are collected through bench tests to extract the characteristic parameters that affect driving behavior. A quadratic regression model is established after considering the nonlinear characteristics of the driver behavior. The multi-collinear problem of high-dimensional variables in the regression model is solved by the ENR method, and the parameters with significant influence on driving behavior selected. A longitudinal driver model of ANFIS was established with the selected characteristic parameters as input. Finally, the validity of the model is verified by comparing it with the PI and ENR driver models.

Aiming at the problems of long lane change intention recognition, complicated lane change model, and huge amount of processing data in the current research, this paper uses principal component analysis to improve the driver’s lane change intention recognition model using traditional pattern recognition. Firstly collect 7 parameters including driver operation and vehicle running characteristics. After data standardization and PCA (principal component analysis), the top three principal components that can reflect the information content of the original data are nearly 90%. Then, a lane-change intent recognition model based on GMM-HMM was established, three lane change intents cannot be directly observed as the hidden state of the model; and three principal component quantities obtained through linear changes are used as observational measurements.

The RON(Research Octane Number) is the most important indicator of motor petrol, and the petrol refining process is one of the important links in petrol production. However, RON is often lost during petrol refining and RON Loss means the value of RON lost during petrol refining. The prediction of the RON loss of petrol during the refining process is helpful to the improvement of petrol refining process and the processing of petrol. The traditional RON prediction method relied on physical and chemical properties, and did not fully consider the high nonlinearity and strong coupling relationship of the petrol refining process. There is a lack of data-driven RON loss models. This paper studies the construction of the RON loss model in the petrol refining process.

Autonomous driving technology, as the product of the fifth stage of the information technology revolution, is of great significance for improving urban traffic and environmentally friendly sustainable development. Autonomous driving can be divided into three main modules. The input of the decision module is the perception information from the perception module and the output of the control strategy to the control module. The deep reinforcement learning method proposes an end-to-end decision-making system design scheme. This paper adopts the Deep Deterministic Policy Gradient Algorithm (DDPG) that incorporates the Priority Experience Playback (PER) method. The framework of the algorithm is based on the actor-critic network structure model. The model takes the continuously acquired perception information as input and the continuous control of the vehicle as output.

It’s hard to achieve complete self-driving using hand-crafting generalized decision-making rules, while the end-to-end self-driving system is low in complexity, does not require hand-crafting rules, and can deal with complex situations. Modular-based self-driving systems require multi-task fusion and high-precision maps, resulting in high system complexity and increased costs. In end-to-end self-driving, we usually only use camera to obtain scene status information, so image processing is very important. Numerous deep learning applications benefit from multi-task learning, as the multi-task learning can accelerate model training and improve accuracy with combine all tasks into one model, which reduces the amount of calculation and allows these systems to run in real-time. Therefore, the approach of obtaining rich scene state information based on multi-task learning is very attractive. In this paper, we propose an approach to multi-task learning for semantics, geometry and motion.

Driving style and skill classification are of great significance in human-oriented advanced driver-assistance system (ADAS) development. In this paper, we propose Fully-Connected Deep Neural Networks (FC-DNN) to classify drivers’ styles and skills with naturalistic driving data. Followed by the data collection and pre-processing, FC-DNN with a series of deep learning optimization algorithms are applied. In the experimental part, the proposed model is validated and compared with other commonly used supervised learning methods including the k-nearest neighbors (KNN), support vector machine (SVM), decision tree (DT), random forest (RF), and multilayer perceptron (MLP). The results show that the proposed model has a higher Macro F1 score than other methods. In addition, we discussed the effect of different time window sizes on experimental results. The results show that the driving information of 1s can improve the final evaluation score of the model.

To reduce the interference and conflict of human-machine cooperative control, lighten the operation workload of drivers, and improve the friendliness and acceptability of intelligent vehicles, a personalized human-machine cooperative lane-change trajectory tracking control method was proposed. First, a lane-changing driving data acquisition test was carried out to collect different driving behaviors of different drivers and form the data pool for the machine learning method. Two typical driving behaviors from an aggressive driver and a moderate driver are selected to be studied. Then, a control structure combined by feedforward and feedback control based on Long Short Term Memory (LSTM) and model-based optimum control was introduced. LSTM is a machine learning method that has the ability of memory. It is used to capture the lane-changing behaviors of each driver to achieve personalization. For each driver, a specific personalized controller is trained using his driving data.

As a new brake-by-wire solution, the electro-booster (Ebooster) brake system can work with the electronic stability program (ESP) equipped in the real vehicle to realize various excellent functions such as basic force boosting (BFB), active braking and energy recovery, which is promoting the development of smart vehicles. Among them, the BFB is the function of Ebooster's servo force to assist the driver's brake pedal force establishing high-intensity braking pressure. After the BFB function failure of the Ebooster, it was not possible to provide sufficient brake pressure for the driver's normal braking, and eventually led to traffic accidents. In this paper, a compensation redundancy control strategy based on ESP is proposed for the BFB failure of the self-designed Ebooster.

Active steering technology can improve the operability of the driver by the involvement to the steering system. Driver is the major controller of the vehicle Therefore, the involvement of advanced technologies including the active steering technology shouldn’t interfere with the intention of the driver, and the driver should still have great control of the vehicle. The aim of this paper is to solve the problem of the driver’s control when the active steering system works to improve the flexibility of the low speed and the stability of the high speed, and the active steering model based on the driver’s steering intention is established. Through the CarSim simulation software, this paper adopts 9 parameters related to the vehicle steering of the DLC (Double Line Change). And PCA (Principal Component Analysis) algorithm, a tool of statistical analysis, is applied to select 4 parameters which can stand for the DLC from the 9 parameters, which makes the data processing easier.

The requirement for low emissions and better vehicle performance has led to the demand for lightweight vehicle structures. Two new lightweight methods of design and optimization for the lower control arm were proposed in this research to improve the effectiveness of the traditional lightweight method. Prior to the two lightweight design and optimization methods, the static performance, including strength, stiffness and mode, and fatigue performance for the lower control arm were analyzed and they provided constraints for subsequent design and optimization. The first method of lightweight design and optimization was integrated application of topography optimization, size optimization, shape optimization and free shape optimization for the control arm. Topography optimization was first applied to find the optimal distribution form of reinforcement rib for the lower control arm. Size optimization was then applied in this study to optimize the plate thickness.