Unmanned vehicle multi-lane navigation formation method based on graph theory and potential field method

Abstract

The invention discloses an unmanned vehicle multi-lane navigation formation method based on a graph theory and a potential field method. The method comprises the following steps of 1), transmitting the predefined formation structure information to the vehicles according to the formation control of an unmanned vehicle fleet, wherein the formation structure information comprises the number of vehicles with a team forming relation, the positions of the vehicles, and the expected distances between the vehicles; 2) planning the speed and displacement required for keeping the formation by using a graph theory method and according to the predefined unmanned vehicle formation and the distance between the unmanned vehicles; 3) obtaining the unmanned vehicle formation trajectory planning according to the unmanned vehicle fleet formation planning, and performing unmanned vehicle obstacle avoidance trajectory planning on the formation trajectory planning; and 4) weighting the unmanned vehicle formation trajectory planning and the planning result of the unmanned vehicle formation trajectory planning to obtain the final planning result of the vehicle and generate the final trajectory. The methodcan adapt to the traffic scene change and automatically change the formation so as to improve the traffic safety and efficiency.

Description

technical field [0001] The invention relates to the automatic driving control technology of intelligent vehicles, in particular to a multi-lane escort formation method for unmanned vehicles based on graph theory and potential field method. Background technique [0002] At present, most of the self-driving cars in the world adopt the "sense-plan-act" (sense-plan-act) three-layer structural model. The surrounding road environment information; then use complex and efficient intelligent algorithms to process environmental information, formulate safe and reliable driving strategies according to traffic regulations, and plan feasible reference trajectories in real time; finally, accurately track the planned local reference trajectories. At the same time, vehicle formation driving can effectively improve road utilization and reduce fuel consumption, and multi-vehicle formation driving is of great significance and value. Therefore, how to plan a safe, smooth, and efficient vehicle ...

AI Technical Summary

Problems solved by technology

However, the method focuses on maintaining the stability and accuracy of the formation, lacks the consideration of environmental factors, and the flexibility of vehicle formation is poor

Images