Peripheral target vehicle state estimation method based on vehicle-to-vehicle communication and GMPHD filtering

Abstract

The invention discloses a peripheral target vehicle state estimation method based on vehicle-to-vehicle communication and GMPHD filtering. The method comprises the following steps of initializing multi-target Gaussian mixture posterior intensity, acquiring point cloud data, preprocessing the point cloud data, converting the point cloud data into a vehicle body coordinate system, predicting multi-target prior intensity, obtaining multi-target posterior intensity, performing information communication and coordinate time synchronization on peripheral target vehicles, converting a synchronized measurement set into the vehicle body coordinate system, updating the multi-target posterior intensity by applying the measurement set, and obtaining final multi-target posterior intensity; setting an abandon threshold value, a merge threshold value and the maximum Gaussian mixture number, and pruning and merging the multi-target posterior intensity; and extracting a target state to obtain a multi-target state collection. Compared with the prior art, the peripheral target vehicle state estimation method can integrate vehicle perception information and state information sent by a peripheral targetvehicle in the Internet of vehicles environment, and improve the accuracy and robustness of target positioning and tracking.

Description

technical field [0001] The invention relates to a method for cooperative perception of surrounding target vehicles based on Internet of Vehicles, in particular to a method for estimating the state of surrounding target vehicles based on vehicle-vehicle communication and GMPHD filtering, and belongs to the field of intelligent vehicles. Background technique [0002] Intelligent vehicles have functions such as environmental perception, planning and decision-making, and inter-vehicle communication. Among them, surrounding target vehicle tracking is an important environmental perception capability of smart vehicles, which means that the self-vehicle collects various information of the surrounding environment in real time through on-board sensors, identifies the target vehicle of interest, and tracks its driving trajectory, so as to obtain the target vehicle accurate status information. Reliable estimation of the state of surrounding vehicles is an important basis for applicatio...

AI Technical Summary

Problems solved by technology

However, this type of method has inherent defects that are difficult to overcome: on the one hand, the "combination explosion" will lead to a computational bottleneck; on the other hand, there is a "coupling" relationship between data association and state estimation, and the correlation error and state estimation error are easy to interact. influences

However, due to the limitations of the current vehicle-mounted sensors in terms of perception ability and sensing range, as well as the mutual occlusion between target vehicles, it is difficult to achieve continuous and accurate tracking of multiple target vehicles only by using the vehicle-mounted sensors, thus limiting the intelligence car's environmental awareness

Images