Driving intention recognition method, device and equipment and storage medium

By preprocessing and filtering historical vehicle data, and combining it with the Mamba module to establish a short-term driving data prediction model, driving intentions can be identified using preset rules. This solves the problems of high computational cost and poor accuracy of deep learning models, and achieves high efficiency and accuracy in driving intention recognition.

CN119116971BActive Publication Date: 2026-06-26CHONGQING NORMAL UNIVERSITY
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHONGQING NORMAL UNIVERSITY
Filing Date
2024-10-09
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Deep learning models are computationally expensive, time-consuming to train, and have poor accuracy and reliability in driver intent recognition, especially due to the large amount of interfering data affecting the structure and correlation of driving data.

Method used

By preprocessing and filtering historical vehicle power and operation data, a short-term driving data prediction model based on the Mamba module is established. The model is trained using target data, and driving intentions are identified through preset rules, thereby reducing computational costs and improving prediction accuracy and reliability.

Benefits of technology

It achieves reduced computational costs, improved prediction accuracy and reliability, reduced interference from data, enhanced data correlation and structural clarity, and adaptability to the complexities of different driving scenarios in driving intent recognition.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119116971B_ABST
    Figure CN119116971B_ABST
Patent Text Reader

Abstract

Embodiments of the present application provide a driving intention recognition method, device and equipment, and a storage medium, and relate to the technical field of intelligent driving. The method comprises the following steps: obtaining and preprocessing historical vehicle power data and historical operation data of an actual vehicle to obtain standardized data, performing filtering processing on the standardized data to obtain target data, establishing a short-time driving data prediction model based on a Mamba module, training the short-time driving data prediction model by using the target data to obtain a target short-time driving data prediction model; obtaining vehicle power data and operation data of the actual vehicle and inputting the data into the target short-time driving data prediction model for processing to obtain a prediction result; obtaining preset rules corresponding to a plurality of driving intentions, and identifying the prediction result by using the preset rules to obtain a target driving intention. The method is used to reduce the calculation cost in the driving intention recognition process and improve the accuracy and reliability of the driving intention recognition.
Need to check novelty before this filing date? Find Prior Art