Search Results

Automatic lane change of intelligent vehicles is a complex process. Besides of safety, feelings of the driver and passengers during the lane change are also very important. In this paper, a lane change trajectory planner is designed to generate an ideal collision-free trajectory to satisfy the driver’s preference. Various lane changing modes, gentle lane change, general lane change, radical lane change and personalized lane change, are designed to meet the needs of different passengers on vehicles simultaneously. In this paper, the condition of the two-lane change is studied. One vehicle is in front of the ego vehicle at the same lane and one is at the rear of the ego vehicle at the target lane. A trajectory planning method is then established based on constant speed offset and sine curve, vehicle distances and speed difference, etc. The key factors which can reflect drivers’ lane change characteristics are then acquired.

The utilization of the SLAM (Simultaneous Localization and Mapping) technique was extended from the robotics to the autonomous vehicles for achieving the positioning. However, SLAM cannot obtain the global position of the vehicle but a relative one to the start. For sake of this, a fast and accurate system was proposed to obtain both the local position and the global position of vehicles based on mono-SLAM which realized the SLAM by using monocular camera with a lower cost and power consumption. Firstly, the rough latitude and longitude of current position was obtained by using common GPS without differential signal. Then, the Mono-SLAM operated on the consecutive video frames to generate the localization and local trajectory and its accuracy was further improved by utilizing the IMU information. After that, a piece of Map centered in the rough position obtained by common GPS was downloaded from the Open Street Map.

Target detection is essential to the advanced driving assistance system (ADAS) and automatic driving. And the data fusion of millimeter wave radar and camera could provide more accurate and complete information of targets and enhance the environmental perception performance. In this paper, a method of vehicle and pedestrian detection based on the data fusion of millimeter wave radar and camera is proposed to improve the target distance estimation accuracy. The first step is the targets data acquisition. A deep learning model called Single Shot MultiBox Detector (SSD) is utilized for targets detection in consecutive video frames captured by camera and further optimized for high real-time performance and accuracy. Secondly, the coordinate system of camera and radar are unified by coordinate transformation matrix. Then, the parallel Kalman filter is used to track the targets detected by radar and camera respectively.

In order to solve the problem that in the traditional trilateral positioning algorithm, the final positioning error is large when there is a certain error in the measured three-sided distance, a UWB positioning algorithm based on Back Propagation (BP) neural network is proposed. The algorithm utilizes the fast learning characteristic and the ability of approximating any non-linear mapping of neural network, and realizes the location of the mobile label through the TOA measurement value provided by the base station and the BP neural network. By comparing the traditional trilateral positioning algorithm, the BP neural network algorithm based on four distance inputs and the BP neural network algorithm based on four distance inputs with trilateral positioning coordinates, it can be seen that the positioning error of traditional trilateral positioning algorithm is 30 cm, and the positioning error of the positioning algorithm based on the BP neural network proposed in this paper is 10 cm.

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.

Vehicle and pedestrian detection technology is the most important part of advanced driving assistance system (ADAS) and automatic driving. The fusion of millimeter wave radar and camera is an important trend to enhance the environmental perception performance. In this paper, we propose a method of vehicle and pedestrian detection based on millimeter wave radar and camera. Moreover, the proposed method complete the detection of vehicle and pedestrian based on dynamic region generated by the radar data and sliding window. First, the radar target information is mapped to the image by means of coordinate transformation. Then by analyzing the scene, we obtain the sliding windows. Next, the sliding windows are detected by HOG features and SVM classifier in a rough detect. Then using the match function to confirm the target. Finally detecting the windows in a precision detection and merging the detecting windows. The target detection process is carried out in the following three steps.

For achieving vehicle light weighting, the motion deviation is calculated for substitution of PMMA glazing for inorganic glass. In this paper, a test method is proposed to measure and calculate the motion deviation of the dual-curvature glass. To simulate the dual-curvature glass, the torus surface is fitted with least square method according to the window frame data, which are measured by Coordinate Measuring Machine. By using this method, the motion deviation of PMMA glazing and inorganic glass can be calculated, which can not only validate the effectiveness of motion simulation, but also compare the performances. The results demonstrate that the performance of PMMA glazing is better than that of inorganic glass and the simulation results is validated.

In this paper, a new method for determining the forming limit diagram (FLD) of thin sheet metals, called DIC-Grid method, is proposed based on digital image correlation (DIC) technique. It's assumed that there exists one virtual grid with an initial diameter of 2.5mm, which is usually the same dimension as the grid in traditional circular grid analysis, close to the crack of specimen, and the limit strain point on FLD is determined by the deformation of this virtual grid. The DIC-Grid method has been compared with traditional circular grid analysis and the standard ISO/FDIS 12004-2 in Nakajima tests. The results show that the forming limit strains obtained by the newly proposed method are more stable and precise. Furthermore, DIC-Grid method can avoid the measurement error which exists in the circular grid analysis. Meanwhile, it overcomes the shortcomings of time-consuming data processing and non-applicable for unrealistic strain distribution in the method of ISO standard.