The invention discloses a driving behavior prediction method and system based on a bidirectional long and short term memory network, relates to the technical field of intelligent driving, and solves the technical problem that the driving behavior prediction of a driver is not accurate enough. According to the method, the function of quickly predicting the future longitudinal and transverse driving behaviors of the driver under the short time window is achieved, the prediction precision is high, the future longitudinal and transverse driving behaviors of the driver are predicted under the lightweight vehicle-mounted processor, and the economic cost is low. The method can widely serve the vehicle auxiliary driving system, improves the safety of the auxiliary driving system, enhances the understanding of the auxiliary system for a driver, facilitates the realization of safe driving, and has practicability and commercial value. Meanwhile, the deep learning method based on big data has very high prediction precision, robustness and generalization ability, is helpful for deep development of an advanced driving assistance system, and is widely suitable for driver behavior prediction under different vehicles.
本发明公开了一种基于双向长短时记忆网络的驾驶行为预测方法及系统,涉及智能驾驶技术领域,解决了对驾驶员驾驶行为预测不够精准的技术问题,其技术方案要点是通过成熟的车载传感器,实现了短时窗下快速预测驾驶员未来纵横向驾驶行为的功能,预测精度高,实现了在轻量级车载处理器下对驾驶员未来纵横向驾驶行为的预测,经济成本低。能够广泛的服务于车辆辅助驾驶系统,提升辅助驾驶系统的安全性,增强辅助系统对驾驶员的理解,有助于实现安全驾驶,具有实用性与商业化价值。同时,基于大数据的深度学习方法有很高的预测精度、鲁棒性和泛化能力,有助于先进驾驶辅助系统的深度开发,广泛适用于不同车辆下的驾驶员行为预测。
Driving behavior prediction method and system based on bidirectional long and short term memory network
一种基于双向长短时记忆网络的驾驶行为预测方法及系统
2022-07-15
Patent
Elektronische Ressource
Chinesisch
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
Europäisches Patentamt | 2023
|Driver driving behavior automatic analysis method based on long-term and short-term memory network
Europäisches Patentamt | 2020
|Transportation Research Record | 2023
|