Multi-target cooperative tracking method based on vehicle-to-vehicle communication

Abstract

The invention discloses a multi-target cooperative tracking method based on vehicle-to-vehicle communication. The method comprises the following steps: a main vehicle and a cooperative vehicle periodically and independently track a target state in a detection range of a vehicle-mounted sensor; the cooperative vehicle sends the self state obtained in the target tracking result to the main vehicle through vehicle-to-vehicle communication; the state of the tracking target received from the cooperative vehicle and the state of the cooperative vehicle are synchronized to the sensing moment of the main vehicle; a coordinate value of the cooperative vehicle in a main vehicle coordinate system is calculated according to the obtained state of the main vehicle and the state of the cooperative vehicle after synchronization; the correlation between the relative angle between the coordinate systems of the two vehicles and the respective tracking targets of the two vehicles is calculated; and the target state information associated with the two vehicles is fused and the target state information which is not associated with each other is kept. The beneficial effects of the invention are that themethod can improve the tracking precision of multiple targets, enlarges the sensing range of an intelligent vehicle, and reduces the sensing blind area; and the number of vehicle sensors can be reduced according to needs, and the manufacturing cost of the intelligent automobile can be reduced.

Description

technical field [0001] The invention relates to a vehicle-to-target tracking method, in particular to a multi-target cooperative tracking method based on vehicle-vehicle communication, and belongs to the technical field of intelligent driving and multi-target tracking. Background technique [0002] The target tracking system is an important part of the intelligent vehicle environment perception system. In order to realize the decision-making and control of the vehicle's automatic driving, it is necessary to accurately detect and estimate various targets in the surrounding environment of the intelligent vehicle, including the exact position and motion state of vehicles and pedestrians. information. The random finite set (Random Finite Set, RFS) theory proposed in recent years directly extends the single-objective Bayesian filtering framework to multi-objective situations, but because it is too complicated in operation, Mahler.R proposed an approximation method, that is, the p...

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: The present invention provides a vehicle-to-vehicle communication based on the problems existing in the prior art that it is impossible to track partially or completely blocked targets and targets outside the detection range of sensors and data delays in the application of vehicle-to-vehicle communication technology. The method of multi-target cooperative tracking can accurately track partially or completely blocked targets and targets outside the detection range of sensors, and can also improve the tracking accuracy of targets that appear within the detection range of two vehicles at the same time, which can be used for the planning of intelligent vehicles. important reference for decision-making

Images