Search Results

In this paper, the system identification theory and method using dynamic neural networks are presented, the multilayer feedforward networks employed, the backpropagation with adaptive learning rate algorithms proposed. Finally the comparision of network output with that of the hydrostatic drive system of secondary regulation is given, and output error, sum-squared error et al, or the results that embody the effect of system identification given sine input to it are provided.

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.

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.