Search Results

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.

Taking full advantage of available traffic environment information, making control decisions, and then planning trajectory systematically under structured roads conditions is a critical part of intelligent vehicle. In this article, a lane-changing decision-making method for intelligent vehicle is proposed based on acceleration field. Firstly, an acceleration field related to relative velocity and relative distance was built based on the analysis of braking process, and acceleration was taken as an indicator of safety evaluation. Then, a lane-changing decision method was set up with acceleration field while considering driver’s habits, traffic efficiency and safety. Furthermore, velocity regulation was also introduced in the lane-changing decision method to make it more flexible.

Knowledge of the tire slip ratio can greatly improve vehicle longitudinal stability and its dynamic performance. Most conventional slip ratio observers were mainly designed based on input of non-driven wheel speed and estimated vehicle speed. However, they are not applicable for electric vehicles (EVs) with four in-wheel motors. Also conventional methods on speed estimation via integration of accelerometer signals can often lead to large offset by long-time integral calculation. Further, model uncertainties, including steady state error and unmodeled dynamics, are considered as additive disturbances, and may affect the stability of the system with estimated state error. This paper proposes a novel slip ratio observer based on input-to-state stability (ISS) method for electric vehicles with four-wheel independent driving motors.

Forecasting the motion of the leading vehicle is a critical task for connected autonomous vehicles as it provides an efficient way to model the leading-following vehicle behavior and analyze the interactions. In this study, a personalized time-series modeling approach for leading vehicle trajectory prediction considering different driving styles is proposed. The method enables a precise, personalized trajectory prediction for leading vehicles with limited inter-vehicle communication signals, such as vehicle speed, acceleration, space headway, and time headway of the front vehicles. Based on the learning nature of human beings that a human always tries to solve problems based on grouping and similar experience, three different driving styles are first recognized based on an unsupervised clustering with a Gaussian Mixture Model (GMM).

Velocity prediction on hilly road can be applied to the energy-saving predictive control of intelligent vehicles. However, the existing methods do not deeply analyze the difference and diversity of road slope driving characteristics, which affects prediction performance of some prediction method. To further improve the prediction performance on road slope, and different road slope driving features are fully exploited and integrated with the common prediction method. A rolling prediction-based multi-scale fusion prediction considering road slope transition driving characteristics is proposed in this study. Amounts of driving data in hilly sections were collected by the advanced technology and equipment. The Markov chain model was used to construct the velocity and acceleration joint state transition characteristics under each road slope transition pair, which expresses the obvious driving difference characteristics when the road slope changes.

A feasible method was developed to reconstruct the three-dimensional flame surface of SI combustion based on 2D images. A double-window constant volume vessel was designed to simultaneously obtain the side and bottom images of the flame. The flame front was reconstructed based on 2D images with a slicing model, in which the flame characteristics were derived by slicing flame contour modeling and flame-piston collision area analysis. The flame irregularity and anisotropy were also analyzed. Two different principles were used to build the slicing model, the ellipse hypothesis modeling and deep learning modeling, in which the ellipse hypothesis modeling was applied to reconstruct the flame in the optical SI engine. And the reconstruction results were analyzed and discussed. The reconstruction results show that part of the wrinkled and folded structure of the flame front in SI engines can be revealed based on the bottom view image.

With the capability of avoiding failure in advance, failure prediction model is important not only to end users, but also to the service engineers in vehicle industry. This paper proposes an approach based on anomaly detection algorithms and telematic data to predict the failure of the engine air system with Turbo charger. Firstly, the relationship between air system and all obtained features are analyzed by both physical mechanism and data-wise. Then, the features including altitude, air temperature, engine output power, and charger pressure are selected as the input of the model, with the sampling interval of 1 minute. Based on the selected features, the healthy state for each vehicle is defined by the model as benchmark. Finally, the ‘Medium surface’ is determined for specific vehicle, which is a hyperplane with the medium points of the healthy state located at, to detect the minor weakness symptom (sub-health state).

With the development of cellular communication technology and for the sake of reducing drag resistance, the multi-lane platoon technology will be more prosperous in the future. In this article, the cooperative vehicle platoon method on the public road is represented. The method’s architecture is mainly composed of the following parts: decision-making, path planning and control command generation. The decision-making uses the finite state machine to make decision and judgment on the cooperative lane change of vehicles, and starts to execute the lane change step when the lane change requirements are met. In terms of path planning, with the goal of ensuring comfort, the continuity of the vehicle state and no collision between vehicles, a fifth-order polynomial is used to fit every vehicle trajectory. In terms of control command generation module, a model predictive control algorithm is used to solve the multi-vehicle centralized optimization control problem.

Conventional viscous shock absorbers, in parallel with suspension springs, passively dissipate the excitation energy from road irregularity into heat waste, to reduce the transferred vibration which causes the discomfort of passengers. Energy-harvesting shock absorbers, which have the potential of conversion of kinetic energy into electric power, have been proposed as semi-active suspension to achieve better balance between the energy consumption and suspension performance. Because of the high energy density of the rotary shock absorber, a rotational energy-harvesting shock absorber with mechanical motion rectifier (MMR) is used in this paper. This paper presents the assessment of vehicle dynamic performance with the proposed energy-harvesting shock absorber in braking process. Moreover, a PI controller is proposed to attenuate the negative effect due to the pitch motion.

Aiming at the difficulty of sovling the stiffness calculation of taper-leaf spring with variable stiffness, a combined method was proposed, which combine superposition method and finite difference method. Then the calculation results of different differential segments were compared with experimental results. The compared results show that the proposed method is effective and simple. So it has some practical significance in designing the taper-leaf spring. In addition, based on the stiffness test of the taper-leaf spring, the proper adjustments to the correction factor of the single parabolic leaf spring stiffness formula was recommended(ξ =0.92-0.96).

In order to study the influence of body flexibility on the truck ride comfort, a 4 DOF half vibration model of truck based on the motion synthesis between rigid body and body flexibility is established using elastic beam theory of equal section with both free ends. At the same time, a corresponding 2 DOF rigid vibration model is also built. The frequency response functions of system and response variables of two models are derived based on front wheel. The power spectral densities and the root mean square values of body acceleration, dynamic deflections and relative dynamic loads are obtained. By comparing the simulation results of rigid-elastic model and rigid model, it shows that body flexibility has a great impact on truck ride comfort and it cannot be ignored.

In order to improve the mode switching performance of parallel hybrid electric vehicles (PHEV) and make better use of the dynamics of the vehicle, this paper proposes a three-stage control method for the start-up mode of start-up, speed synchronization, and clutch slip based on the response characteristics of actual vehicle components and the complex working conditions of the actual road. In the speed synchronization phase, a coordinated control method of “engine speed active following + continuously variable transmission (CVT) speed ratio motor speed limiting” is proposed. The real vehicle test results show that the engine starting-up coordinated control method can significantly accelerate the speed synchronization and shorten the starting-up mode duration during the rapid acceleration, so that the vehicle’s power performance can be well played and the ride comfort can be effectively guaranteed.

Since steering wheel torque feedback is one of the crucial factors for drivers to gain road feel and ensure driving safety, it is especially important to simulate the steering torque feedback for a driving simulator. At present, steering wheel feedback torque is mainly simulated by an electric motor with gear transmission. The torque response is typically slow, which can result in drivers’ discomfort and poor driving maneuverability. This paper presents a novel torque feedback device with magnetorheological (MR) fluid and coil spring. A phase separation control method is also proposed to control its feedback torque, including spring and damping torques respectively. The spring torque is generated by coil spring, the angle of coil spring can be adjusted by controlling a brushless DC motor. The damping torque is generated by MR fluid, the damping coefficient of MR fluid can be adjusted by controlling the current of excitation coil.

According to the statistics of National Highway Traffic Safety Administration, driver’s cognitive distraction, which is usually caused by drivers using mobile phones, has become one of the main causes of traffic accidents. To solve this problem and guarantee the safety of man-vehicle-road system, the most critical work is to improve the accuracy of driver’s cognitive state detection. In this paper, a novel driver’s cognitive state detecting method based on LightGBM (Light Gradient Boosting Machine) is proposed. Firstly, cognitive distraction experiments of making calls are carried out on a driving simulator to collect vehicle states, eye tracking and EEG (electron encephalogram) data simultaneously and feature extraction is conducted. Then a classifier considering road and individual characteristics used for detecting cognitive states is trained based on LightGBM algorithm, with 3 predefined cognitive states including concentration, ordinary distraction and extreme distraction.

Batteries are exposed to dynamic load during vehicle driving. It is significant to clarify the load input of the battery system during vehicle driving for battery pack structural design and optimization. Currently, bolt connection is mostly applied for battery pack constraint to vehicle, as well as for module assembly inside the pack. However, accurate bolt load is always difficult to obtain, while directly force measurement is expensive and time consuming in engineering. In this paper, a precise data driven model based on Elman neural network is established to identify the dynamic bolt loads of the battery pack, using tested acceleration data near bolts. The dynamic bolt force data is measured at the same time with the acceleration data during vehicle running in different driving conditions, utilizing customized bolt force sensors.

Low back pain has a higher prevalence among drivers who have long term history of vehicle operations. Vehicle vibration has been considered to contribute to the onset of low back pain. However, the fundamental mechanism that relates vibration to low back pain is still not clear. Little is known about the relationship between vibration exposure, the biomechanical response, and the physiological responses of the seated human. The aim of this study was to determine the vibration frequency that causes the increase of muscle activity that can lead to muscle fatigue and low back pain. This study investigated the effects of various vibration frequencies on the lumbar and thoracic paraspinal muscle responses among 11 seated volunteers exposed to sinusoidal whole body vibration varying from 4Hz to 30Hz at 0.4 g of acceleration. The accelerations of the seat and the pelvis were recorded during various frequency of vibrations. Muscle activity was measured using electromyography (EMG).

To find out the main excitation sources of a bus floor's vibration, modal analysis and spectral analysis were respectively performed in the paper. First we tested the vibration modal of the bus's floor under the full-load condition, and the first ten natural frequencies and vibration modes were obtained for the source identification of the bus floor's vibration. Second the vibration characteristic of the bus floor was measured in an on-road experiment. The acceleration sensors were arranged on the bus's floor and the possible excitation sources of the bus, which includes engine mounting system, driveline system, exhaust system, and wheels. Then the on-road experiment was carefully conducted on a highway under the four kinds of test condition: in-situ acceleration, uniform velocity (90km/h, 100km/h, 110km/h, 120km/h), uniform acceleration with top gear, and stall sliding condition with neutral gear.

Accurate identification of driver’s braking intention is essential in advanced driver assistance system and can make the driving process more comfortable and trustworthy. In this paper, a novel method for driver braking intention identification in cut-in scenarios was proposed by using driver’s gaze information and motion information of cut-in vehicles. Firstly, a "looking in and looking out" experimental platform including three eye-tracking cameras and one front-view camera was built to collect driver's gaze information and the vehicle motion information. Secondly, driver’s gaze features and motion features of cut-in vehicles were selected and the braking intention identification performance of several decision tree-based ensemble learning algorithms was compared. Thirdly, the feature importance was analyzed by using SHAP (SHapley Additive exPlanations) values. This novel method of braking intention identification makes full use of in-vehicle camera sensors.

The driving risk field model offers a feasible approach for assessing driving risks and planning safe trajectory in complex traffic scenarios. However, the conventional risk field fails to account for the vehicle size and acceleration, results in the same trajectories are generated when facing different vehicle types and unable to make safe decisions in emergency situations. Therefore, this paper firstly introduces the acceleration and vehicle size of surrounding vehicles for improving the driving risk model. Then, an integrated decision-making and planning model is proposed based on the combination of the novelty risk field and model predictive control (MPC), in which driving risk and vehicle dynamics constraints are taken into consideration. Finally, the multiple driving scenarios are designed and analyzed for validate the proposed model.

With the rapid advancement in intelligent vehicle technologies, comprehensive environmental perception has become crucial for achieving higher levels of autonomous driving. Among various perception tasks, monitoring road types and evenness is particularly significant. Different road categories imply varied surface adhesion coefficients, and the evenness of the road reflects distinct physical properties of the road surface. This paper introduces a two-stage road perception framework. Initially, the framework undergoes pre-training on a large annotated drivable area dataset, acquiring a set of pre-trained parameters with robust generalization capabilities, thereby endowing the model with the ability to locate road areas in complex regions.