The invention discloses a driving intention recognition method based on a Gaussian mixture-hidden Markov model. The method specifically comprises the following steps: S1, data preparation and processing; s2, a GMM-HMM hybrid model is constructed; s3, identifying a driving intention; the step S1 comprises an NGSIM data set, data preparation and feature extraction under a Frenet coordinate system, the model constructed in the step S2 comprises a Gaussian mixture model and a hidden Markov model, and the step S3 specifically comprises mixture model training and model inspection. According to the driving intention recognition method based on the Gaussian mixture-hidden Markov model, compared with a single reference line, the double reference lines are used under the Frenet coordinate system, and the lane keeping recognition accuracy and the lane changing recognition accuracy are both improved. Therefore, the space continuity in the vehicle driving process can be fully considered by using the double reference lines, and the vehicle driving characteristic effect can be described more accurately.
本发明公开了基于高斯混合‑隐马尔可夫模型的驾驶意图识别方法,具体包括以下步骤:S1:数据准备和处理;S2:GMM‑HMM混合模型构建;S3:驾驶意图识别;所述S1步骤中包括有NGSIM数据集、数据准备和Frenet坐标系下的特征提取,所述S2步骤中构建的模型包括有高斯混合模型和隐马尔可夫模型,所述S3步骤中具体包括训练混合模型和模型检验。本发明公开的基于高斯混合‑隐马尔可夫模型的驾驶意图识别方法具有在Frenet坐标系下使用双参考线相较于使用单参考线,在车道保持识别准确率和变道识别准确率上均有所提高。这说明使用双参考线可以充分考虑到车辆行驶过程中的空间连续性,更准确地描述车辆行驶特征效果。
Driving intention recognition method based on Gaussian mixture-hidden Markov model
基于高斯混合-隐马尔可夫模型的驾驶意图识别方法
2024-05-14
Patent
Electronic Resource
Chinese
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 |
Wheel Loader Driving Intention Recognition with Gaussian Mixture - Hidden Markov Model
DOAJ | 2018
|Research of Driving Fatigue Detection Based on Gaussian Mixture Hidden Markov Model
SAE Technical Papers | 2020
|Research of Driving Fatigue Detection Based on Gaussian Mixture Hidden Markov Model
British Library Conference Proceedings | 2020
|British Library Conference Proceedings | 2021
|