Group target advancing trend prediction method based on LSTM neural network

Abstract

The invention provides a group target advancing trend prediction method based on an LSTM neural network, and the method comprises the steps: carrying out the modeling of interactive group targets in an actual scene through the relative spatial relation between group targets, and establishing the LSTM long-short-term memory neural network for the prediction and calculation of a track position. Dependence prediction is carried out according to contact communication between single targets in a group, a cooperative relationship, single target model characteristics and group target activity properties, unreasonable factors are eliminated, a minimum prediction space of a group target advancing track trend is obtained, and a final prediction result is visually expressed. Compared with the traditional single target trajectory prediction, according to the method, the related problem of predicting the advancing trend of the complex group target with certain correlation and interactivity is solved; information such as a target historical track, a target association relationship, a target model category, a target mass characteristic and a target activity property can be fully utilized to comprehensively calculate and predict, and a prediction result of a group target advancing trend is accurately provided.

Description

technical field [0001] The invention relates to a method for predicting the traveling trend of a group target based on an LSTM neural network. Background technique [0002] At present, there are relatively extensive research and applications on the prediction technology of target travel trends in the fields of unmanned driving, traffic flow, pedestrian trajectory, etc. at home and abroad. Predicting the trend and trajectory of the target as accurately as possible is of great significance for grasping the future position of the target as soon as possible and mining the target's behavioral intention. However, there are still many problems in the overall trend prediction for a group of group targets with complex relationships such as communication and cooperation: 1) Existing prediction technologies are more focused on the prediction of a single category of target trajectories, and lack Research on the prediction of the overall traveling trend of multi-type and interactive gro...

AI Technical Summary

Problems solved by technology

However, there are still many problems in the overall trend prediction for a group of group targets with complex relationships such as communication and cooperation: 1) Existing prediction technologies are more focused on the prediction of a single category of target trajectories, and lack Research on the prediction of the overall traveling trend of multi-type and interactive group targets

2) Insufficient use of target historical trajectory information and insufficient consideration of the dynamics of the target environment in the prediction make the prediction accuracy rate overly dependent on the current state of the target; 3) Ignoring the inherent characteristics of a single target such as model and volume The influence of weight in the forecasting of the group's overall traveling trend

4) Lack of consideration of the impact of the nature of the target activity on the prediction space

5) There is a lack of an effective way to calculate and express the prediction results of the group target's travel trend

Images