Font Size: a A A

Research On Obstacle Detection And Obstacle Avoidance Strategy Of Intelligent Vehicle

Posted on:2013-02-19Degree:MasterType:Thesis
Country:ChinaCandidate:L HanFull Text:PDF
GTID:2218330371455855Subject:Control theory and control engineering
Abstract/Summary:PDF Full Text Request
With the rapid growth of the numbers of automobile, the safety of highway traffic draws more and more Governments and societies' attention. Currently, the Automotive Active Safety Technology has become mature and sophisticated, and the vehicle collision avoidance system based on intelligent transportation systems (ITS) is becoming the focus of the world. The intelligent vehicle collision avoidance system is using the modern information technology, sensing technology to extend the driver's perception, and passed the information from the perception technology (such as speed, pedestrians or other obstructions distance, etc.) to the driver, Meanwhile it can identify the safety hazard from road condition and vehicle condition information. In addition, the system will control the car automatically in order to take the initiative away from danger of vehicles in an emergency. So the technology can ensure the the driving safety, reducing the number of traffic accidents and improve traffic safety.Predict danger from detected obstacles and obstacle avoidance strategy are key technologies of the intelligent vehicle obstacle avoidance system. The key point of obstacle detection is not only to determine the safety area of vehicles traveling, but also the perceived of obstacles that may exist in front of the vehicle, including the location of obstructions in the road, size and state of motion, and the distance of the car-depth information. Obstacle avoidance strategy relies on accurate information of the obstacles, and considered in the vehicle because of the speed set too fast. In addition, we have to care about the safe start-up, reliable parking, efficiency of energy-saving, transportation costs and so on.As mentioned above, in this paper, I analyze a variety of intelligent vehicle driving environment based on existing data, and sort out the typical obstacles mode for both vehicles and pedestrians. For these two obstacles, this paper presents the combined obstacle detection method for vehicles and pedestrians. At the beginning, firstly, pre-processing the image, on this basis, detected the lane, and let the triangle regional which consisted by two lane lines as obstacle detection region, and then extract the aspect ratio and dispersion characteristics of the obstacles in this area, and using the feature fusion to determine the obstacle type. Finally, using the appropriate method to precise positioning of the vehicle locationSecondly, this paper compared the advantages and disadvantages of obstacle avoidance trajectory, and determined the arc trajectory as the obstacle avoidance trajectory. Both the turning radius and critical safe distance are also the obstacle avoidance strategy's parameters. Then simulate the propose scheme by the matlab tool.At last, this paper uses MATLAB to build a simulation platform for obstacle avoidance system, shows the block diagram of the simulation platform, and details the function of each module. Simulation results show that the vehicles and pedestrians joint obstacle detection method and the obstacle avoidance strategy based on a safe distance and the vehicle relative velocity not only detected but also avoid the vehicle obstacle accurately and timely to ensure the safety of vehicles driving.
Keywords/Search Tags:obstacle-avoidance system, obstacle detection, Multi-Feature Fusion, obstacle avoidance strategy, critical safe distance
PDF Full Text Request
Related items