Search Results

With the development of autonomous vehicle technology, there is an increasing tendency toward the application of intelligent sensors in environment-perception system on autonomous vehicle to assist vehicle in intelligent decision making relevant to autonomous driving. As for environment-perception system, a good track management method serves as the foundation, while multi-target tracking and multi-sensor data fusion are recognized as the key. In this paper, a track management method is proposed to deal with multi-target tracking based on the target-level data of multisource environmental sensors for autonomous vehicle. The track management includes four procedures as following: track initiation; point-track association; track update; track deletion. A modified fast algorithm for data association is applied in the point-track association procedure. Afterwards Kalman filter is implemented to update the track information of target. The algorithm has got through a simulation test.

Although Hydrostatic Transmission System (HTS) had been used in many places, such as machine tools, agriculture machinery, construction machinery, and vehicles, it had not been used in good performance. Twenty years ago many people began to design new hydrostatic transmission with higher efficiency. Hydrostatic Energy Storage Transmission System (HESTS) is one of new hydrostatic transmission system with higher efficiency. HESTS is more fit for being used in vehicle that is always running in undulating ground or starting and braking frequently. Construction of vehicular HESTS was analyzed, mathematical model of vehicular HESTS was established. The needed control strategies of vehicular HESTS were analyzed because there are many variables would be controlled in the new transmission system.

Real-time and reliable perception of the surrounding environment is an important prerequisite for advanced driving assistance system (ADAS) and automatic driving. And vision-based detection plays a significant role in environment perception for automatic vehicles. Although deep convolutional neural networks enable efficient recognition of various objects, it has difficulty in accurately detecting special vehicles, rocks, road pile, construction site, fence and so on. In this work, we address the task of traffic scene understanding with semantic image segmentation. Both driveable area and the classification of object can be attained from the segmentation result. First, we define 29 classes of objects in traffic scenarios with different labels and modify the Deeplab V2 network. Then in order to reduce the running time, MobileNet architecture is applied to generate the feature map instead of the original models.

To develop a free-piston engine-alternator integrative power system for Hybrid Electric Vehicles, the key design parameters, such as reciprocating mass of the piston assembly, compression ratio, the ignition timing, the engine fuel consumption rate and power output, are studied based on the simulation. The results show that, the system simulation model of the free piston engine can predict the in-cylinder pressure vs. the piston's displacement being accurate enough as the test results from reported reference. The model can be employed to optimize the design parameters and to predict the fuel economy and power output. It provides the methods and bases for the free piston engine design and predicting the main performance parameters' values.

As a type of alternative fuel, biodiesel has advantages in reducing greenhouse gases and ensuring energy security. Compared with petroleum diesel, biodiesel has different lower calorific value, oxygen content and octane number that would raise problems when the unoptimized common rail diesel engine is fueled with biodiesel or its petroleum diesel blends. Among these problems, decreasing full load torque output and increasing NOx and BSFC are significantly important. Fuel injection parameter calibration and optimization experiments are carried out in an in-line 6-cylinder 8.82 liter turbocharged and intercooled common rail diesel, which is equipped with Denso ECD-U2 fuel injection system, SCR (Selective catalytic reduction) and DPF (diesel particulate filter). To avoid after-treatment apparatus' coupling influence and re-calibration, emission measure point is set in front of catalysts. The experiment adopts B20 biodiesel as test fuel.

Connected and autonomous vehicles are different from traditional vehicles. The communication between vehicles (V2V) or between vehicles and infrastructures (V2I) renders it possible to convey traffic information (e.g. signal timing or speed advisory) from signal controllers to vehicles as well as vehicles to vehicles in real time. Taking this advantage, this paper aims to developing an algorithm which enables the interconnected autonomous vehicles running efficiently on arterials. A set of driving rules determining random behavior and swarm behavior of autonomous vehicles is developed based on swarm intelligence theory. Under control of these rules, each autonomous vehicle follows the same rules, which make it select target vehicle from all the optimal individuals in detection zone according to characteristics of itself, then approach to the target by changing lane, following former car, or accelerating.

Torque Vectoring Control for distributed drive electric vehicle is studied. A handling improvement algorithm for normal cornering maneuvers is proposed based on state variable feedback control: Yaw rate feedback together with steer angle feedforward is employed to improve transient response and steady gain of the yaw rate, respectively. According to the feedback coefficient's influence on the transient response, an optimization function is proposed to obtain optimum feedback coefficients under different speeds. After maximum feedforward coefficients under different speeds are obtained from the constraint of the motor exterior characteristic, final feedforward coefficients are calculated according to an optimal steering characteristic. A torque distribution algorithm is presented to help the driver to speed up during the direct yaw moment control.

In view of the problem of low-frequency (less than 10Hz, such as 0.5Hz, 1.15Hz, 8Hz in this paper) longitudinal vibration exists in a pure electric vehicle, modeling methods of drive-line torsion vibration system are conducted. Firstly, dynamometer test is performed, signals of motor speed and seat rail acceleration are obtained, the frequency characteristics of flutter is determined using the order analysis and time frequency analysis. Then four types of modeling and analysis are investigated facing the drive-line torsion vibration problem, including single model without electromagnetic stiffness, branch model without electromagnetic stiffness, single model considering electromagnetic stiffness and branch model considering electromagnetic stiffness. The results show that, modeling taking into account the electromagnetic stiffness and branches can reflect more low-frequency characteristics helps to reveal the low-frequency longitudinal flutter of the researched electric vehicle.