Multi-sensor over-the-horizon ad hoc network method based on traffic semantics and game theory

Abstract

The invention discloses a multi-sensor over-the-horizon ad hoc network method based on traffic semantics and game theory, which comprises the following steps: quantifying the effective sensing range of each sensor of vehicle-mounted and roadside units, establishing a typical scene library based on the traffic semantics, judging the vehicle sensing demand according to the corresponding working condition of the typical scene library, and finally, obtaining an optimal networking mode based on a double-layer game theory. Compared with the prior art, the method has the positive effects that the typical scene library is established based on different traffic semantics, so that the vehicle can accurately and quickly judge the beyond-visual-range perception requirement of the vehicle at the current moment, the double-layer game model is constructed based on the complete information game theory, the beyond-visual-range perception requirement of the intelligent vehicle is met, the maximum utilization of sensor information is realized, and the method has the value of solving the actual problem.

Description

technical field [0001] The invention relates to the field of intelligent driving vehicles and vehicle-road cooperative perception, in particular to a multi-source heterogeneous sensor over-the-horizon self-organizing network method based on traffic semantics and game theory. Background technique [0002] The safe driving of smart cars is a complex system composed of functional modules such as environmental perception, planning decision-making, and control execution. Among them, the environmental perception effect is an important prerequisite for the correct planning and decision-making and control execution of the car, which directly affects the safety and comfort of the vehicle. At present, commonly used environmental perception solutions include cameras, laser radars, millimeter wave radars, ultrasonic radars and other sensors to collect data in conjunction with autonomous driving maps and high-precision positioning systems for collaborative perception. Various sensors hav...

AI Technical Summary

Problems solved by technology

[0005] A Chinese patent discloses "Over-the-horizon Perception and Release Method and System Combining ADAS and V2V" (CN107979812A). The information interaction with the vehicle still has problems such as blind spots of perception information and difficulty in matching dynamic information

A Chinese patent discloses "Intelligent Networked Vehicle Operating System Based on Vehicle-Road Coordination" (CN109714421A), which uploads perception information, high-precision positioning, map matching, and many other information to the cloud for computing, without considering the relationship between competition and cooperation among sensors , which greatly increases the amount of calculation, which will not only cause waste of resources, but also reduce the matching accuracy between sensors

The Chinese patent discloses "A Game Theory-Based Optimal Configuration of RSUs for Internet of Vehicles" (CN104320789A). This method determines the configuration of the optimal RSUs based on game theory. Quickly and efficiently screen out the optimal configuration combination, which cannot meet the real-time requirements of over-the-horizon networking

Images