Search Results

The drivers' hysteretic perception to surrounding environment will affect vehicular fuel economy, especially for the heavy-duty vehicles driving under complex conditions and long distance in mountainous areas. Unreasonable acceleration or deceleration on the slope will increase the fuel consumption. Improving the performance of the engine and the transmission system has limited energy saving potential, and most fuel-efficient driving assistant systems don't consider the road conditions. The main purpose of this research is to introduce an economic driving scheme with consideration of the prestored slope information in which the vehicle speed in mountainous slopes is reasonably planned to guide the driver's behavior for reduction of the fuel consumption. Economic driving optimization algorithm with low space dimension and fast computation speed is established to plan accurate and real-time economic driving scheme.

Path planning system, which is one of driver assistance systems, can calculate the driving paths and estimate the driving time through the road information provided by information source. Traditional path planning systems calculate the driving paths through Dijsktra's algorithm or A* algorithm but only consider the road information from electronic maps. It is not safe enough for operating vehicles because of the insufficient information of vehicle performance as well as the driver's willingness. This study is based on the Dijsktra's algorithm, which comprehensively considered vehicular active safety constraints such as road information, vehicle performance and the driver's willingness to optimize the Dijsktra's algorithm. Then the path planning system can calculate the optimal driving paths that would satisfy the safety requirement of the vehicle. This study used LabVIEW as a visual host computer and MATLAB to calculate dynamic property of the vehicle.

For cooperative adaptive cruise control (CACC) system, a robust following control algorithm based on fuzzy PID principle is adopted in this paper. Firstly, a nonlinear vehicle dynamics model considering the lag of driving force and acceleration constraints was established. Then, with the vehicle’s control hierarchic, the upper controller takes the relative speed between vehicles and the spacing error as inputs to output the following vehicle's target acceleration, while the lower controller takes the target acceleration as inputs and the throttle opening and brake master cylinder pressure as outputs. For the setting of target spacing, this paper additionally considers the relative speed between vehicles and the acceleration of the front vehicle. Through testing, compared with the traditional variable safety distance model, the average distance reduces by 5.43% when leading vehicle is accelerating, while increases by 2.74% in deceleration.

Lane detection is an important component in automatic pilot system and advanced driving assistance system (ADAS). The stability and precision of lane detection will directly determine precision of control and lane plan of vehicles. Traditional mechanical vision lane detection approaches in complicated environment have the deficiencies of low precision and feature semantic description disabilities. But the lane detection depending on deep learning, e.g. SCNN network, LaneNet network, ENet-SAD network have imbalance problems of splitting precision and storage usage. This paper proposes an approach of high-efficiency deep learning Segnet-LSTM semantic segmentation network. This network structure is composed with encoding network and corresponding decoding networks. First, convolution and maximum pooling. The proposal extracts texture details of five images and stores searching position of maximum pooling. Meanwhile, it will implement interpolate processing to the lost points.