Search Results

Tracking vehicle trajectories is essential for autonomous vehicles and advanced driver-assistance systems to understand traffic environment and evaluate collision risk. In order to reduce the position deviation and fluctuation of tracking on-road vehicle by millimeter-wave radar (MMWR), an interactive multi-model Kalman filter (IMM-KF) tracking algorithm including data association and track management is proposed. In general, it is difficult to model the target vehicle accurately due to lack of vehicle kinematics parameters, like wheel base, uncertainty of driving behavior and limitation of sensor’s field of view. To handle the uncertainty problem, an interacting multiple model (IMM) approach using Kalman filters is employed to estimate multitarget’s states. Then the compensation of radar ego motion is achieved, since the original measurement is under the radar polar coordinate system.

Electric Power Steering (EPS) is the actuator of several lateral-dynamic-related Advanced Driver Assistance Systems (ADAS). A driving simulator with EPS will be much helpful for the ADAS development. However, if a real EPS is used in the driving simulator, it is quite difficult to realize the road reaction force accurately and responsively. To overcome this weakness, a virtual EPS platform is established. The virtual EPS platform contains two parts: one is the vehicle and EPS model, the other is the force feedback actuator (FFA) of the Steer-by-Wire (SBW) system. The FFA is an interface between the driver and the EPS/vehicle model. The reactive torque of the FFA is obtained based on the models. Meanwhile, the input of the EPS model is the steering angle of the FFA. Comparing to a real EPS, the virtual EPS platform has a problem of instability because of the actuator lag of the FFA. Therefore, a damping control method is applied to make the system stable.

In the recent years, the interaction between human driver and Advanced Driver Assistance System (ADAS) has gradually aroused people’s concern. As a result, the concept of personalized ADAS is being put forward. As an important system of ADAS, Lane Keeping Assistance System (LKAS) also attracts great attention. To achieve personalized LKAS, driver lane keeping characteristic (DLKC) indices which could distinguish different driver lane keeping behavior should be researched. However, there are few researches on DLKC indices for personalized LKAS. Although there are many researches on modeling driver steering behavior, these researches are not sufficient to obtain DLKC indices. One reason is that most of researches are for double lane change behavior which is different from driver lane keeping behavior. The other reason is that the researches on driver lane keeping behavior only provide model structure and rarely discuss identification procedure such as how to select suitable data.

The Linear Internal Combustion Engine-Linear Generator Integrated System (LICELGIS) is different from conventional crank-based engine for reducing frictional losses by eliminating the crankshaft. Thus, the LICELGIS piston stroke is not constrained geometrically and the system compression ratio is variable. During steady-state operation, the LICELGIS converts the fuel chemical energy into electric power with piston assembly reciprocating motion, which can be used as a range-extender in hybrid electric vehicles. The LICELGIS scavenging process is prerequisite and key for the system steady-state operation, which has remarkable influence on mixture gas and, eventually, on engine combustion performance. In order to achieve high scavenging performance, a LICELGIS is investigated in this paper. The LICELGIS motion characteristics and scavenging process were analyzed.

In China there are many mixed driving roads which cause a lot of safety problems between vehicles and pedalcyclists. Research on driver behavior under risk scenarios with pedalcyclist is relatively few. In this paper driver brake parameters under naturalistic driving are studied and pedalcyclists include bicyclist, tricyclist, electric bicyclist and motorcyclist. Brake reaction time and maximum brake jerk are used to evaluate driver brake reaction speed. Average deceleration is used to evaluate the effect of driver brake operation. Maximum deceleration is used to evaluate driver braking ability. Driver behaviors collected in China are classified and risk scenarios with pedalcyclist are obtained. Driver brake parameters are extracted and statistical characteristics of driver brake parameters are obtained. Influence factors are analyzed with univariate ANOVA and regression analysis.

Cut-in scenario is common in traffic and has potential collision risk. Human driver can detect other vehicle’s cut-in intention and take appropriate maneuvers to reduce collision risk. However, autonomous driving systems don’t have as good performance as human driver. Hence a deeper understanding on driving behavior is necessary. How to make decisions like human driver is an important problem for automated vehicles. In this paper, a method is proposed to classify the dangerous cut-in situations and normal ones. Dangerous cases were extracted automatically from naturalistic driving database using specific detection criteria. Among those cases, 70 valid dangerous cut-in cases were selected manually. The largest deceleration of subject vehicle is over 4 m/s2. Besides, 249 normal cut-in cases were extracted by going through video data of 2000km traveled distance. In normal driving cases, subject vehicle may brake or keep accelerating and the largest deceleration was less than 3 m/s2.

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.

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.

As turbulence modeling has become an indispensable approach to perform flow simulation in a wide range of industrial applications, how to enhance the prediction accuracy has gained increasing attention during the past years. Of all the turbulence models, RANS is the most common choice for many OEMs due to its short turn-around time and strong robustness. However, the default setting of RANS is usually benchmarked through classical and well-studied engineering examples, not always suitable for resolving complex flows in specific circumstances. Many previous researches have suggested a small tuning in turbulence model coefficients could achieve higher accuracy on a variety of flow scenarios. Instead of adjusting parameters by trial and error from experience, this paper introduced a new data-driven method of turbulence model recalibration using adjoint solver, based on Generalized k-ω (GEKO) model, one variant of RANS.

The driver monitoring system (DMS) plays an essential role in reducing traffic accidents caused by human errors due to driver distraction and fatigue. The vision-based DMS has been the most widely used because of its advantages of non-contact and high recognition accuracy. However, the traditional RGB camera-based DMS has poor recognition accuracy under complex lighting conditions, while the IR-based DMS has a high cost. In order to improve the recognition accuracy of conventional RGB camera-based DMS under complicated illumination conditions, this paper proposes a lightweight low-illumination image enhancement network inspired by the Retinex theory. The lightweight aspect of the network structure is realized by introducing a pixel-wise adjustment function. In addition, the optimization bottleneck problem is solved by introducing the shortcut mechanism.

Harmony-with-traffic refers to the ability of autonomous vehicles to maximize the driving benefits such as comfort, efficiency, and energy consumption of themselves and the surrounding traffic during interactive driving under traffic rules. In the test of harmony-with-traffic, one or more background vehicles that can respond to the driving behavior of the vehicle under test are required. For this purpose, the functional requirements of car-following model for harmony-with-traffic evaluation are analyzed from the dimensions of test conditions, constraints, steady state and dynamic response. Based on them, an interactive car-following model (ICFM) is developed. In this model, the concept of equivalent distance is proposed to transfer lateral influence to longitudinal. The calculation methods of expected speed are designed according to the different car-following modes divided by interaction object, reaction distance and equivalent distance.

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.

The research and development of data-driven highly automated driving system components such as trajectory prediction, motion planning, driving test scenario generation, and safety validation all require large amounts of naturalistic vehicle trajectory data. Therefore, a variety of data collection methods have emerged to meet the growing demand. Among these, camera-equipped drones are gaining more and more attention because of their obvious advantages. Specifically, compared to others, drones have a wider field of bird's eye view, which is less likely to be blocked, and they could collect more complete and natural vehicle trajectory data. Besides, they are not easily observed by traffic participants and ensure that the human driver behavior data collected is realistic and natural. In this paper, we present a complete vehicle trajectory data extraction framework based on aerial videos. It consists of three parts: 1) objects detection, 2) data association, and 3) data cleaning.

Cut-in scenarios are common and of potential risk in China but Advanced Driver Assistant System (ADAS) doesn’t work well under such scenarios. In order to improve the acceptance of ADAS, its reactions to Cut-in scenarios should meet driver’s driving habits and expectancy. Brake is considered as an express of risk and brake tendency in normal Cut-in situations needs more investigation. Under critical Cut-in scenarios, driver tends to brake hard to eliminate collision risk when cutting in vehicle right crossing lane. However, under less critical Cut-in scenarios, namely normal Cut-in scenarios, driver brakes in some cases and takes no brake maneuver in others. The time when driver initiated to brake was defined as key time. If driver had no brake maneuver, the time when cutting-in vehicle right crossed lane was defined as key time. This paper focuses on driver’s brake tendency at key time under normal Cut-in situations.

In the autonomous driving perception task, the accuracy of target detection is an essential evaluation, especially for small targets. In this work, we propose a multi-sensor fusion neural network that combines radar and image data to improve the confidence level of the camera when detecting targets and the accuracy of the prediction box regression. The fusion network is based on the basic structure of single-shot multi-box detection (SSD). Inspired by the attention mechanism in image processing, our work incorporates the a priori knowledge of radar detection in the convolutional block attention module (CBAM), which forms a new attention mechanism module called radar convolutional block attention module (RCBAM). We add the RCBAM into the SSD target detection network to build a deep neural network fusing millimeter-wave radar and camera.

Motivated by applying artificial intelligence technology to the automobile industry, reinforcement learning is becoming more and more popular in the community of intelligent driving research. The reward function is one of the critical factors which affecting reinforcement learning. Its design principle is highly dependent on the features of the agent. The agent studied in this paper can do perception, decision-making, and motion-control, which aims to be the assistant or substitute for human driving in the latest future. Therefore, this paper analyzes the characteristics of excellent human driving behavior based on the six-layer model of driving scenarios and constructs it into a human knowledge graph. Furthermore, for highway pilot driving, the expert demo data is created, and the reward function is self-learned via inverse reinforcement learning. The reward function design method proposed in this paper has been verified in the Unity ML-Agent environment.

Object detection is an important visual content of the autonomous vehicle, the traditional detecting methods usually cost a lot of computational memory and elapsed time. This paper proposes to use lightweight deep convolutional neural network (MobilenetV3-SSDLite) to carry out the object detection task of autonomous vehicles. Simulation analysis based on this method is implemented, the feature layer obtained after h-swish activation function in the first Conv of the 13th bottleneck module in MobilenetV3 is taken as the first effective feature layer, and the feature layer before pooling and convolution of the antepenultimate layer in MobilenetV3 is taken as the second effective feature layer, and these two feature layers are extracted from the MobilenetV3 network.

The main challenge for future autonomous vehicles is to identify their location and body pose in real time during driving, that is, “where am I? and how will I go?”. We address the problems of pose estimation and scene perception from continuous visual frames in intelligent vehicle. Recent advanced technology in the domain of deep learning proposes to train some learning models for vehicle’s series detection tasks in a supervised or unsupervised manner, which has numerous advances over traditional approaches, mainly reflected in the absence of manual calibration and synchronization of the camera and IMU. In the paper, we propose a novel approach for pose estimation and scene recognition with a deep fusion of multi-modal neural features in the manner of unsupervised. Firstly, low-cost camera and IMU are used to extract original visual and inertial data, then the visual and inertial encoders are utilized to encoder the feature of the two modes.