UWB-based intent detection for vehicle applications

Through UWB sensor networks and machine learning models, vehicle user intentions can be predicted in real time, solving the problem of vehicle functions requiring user commands in existing technologies, achieving automatic activation of vehicle functions, and improving the level of intelligence.

CN120681152APending Publication Date: 2025-09-23GM GLOBAL TECHNOLOGY OPERATIONS LLC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410670280.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2024-03-22
Filing Date
2024-05-28
Publication Date
2025-09-23

AI Technical Summary

Technical Problem

Existing technologies have difficulty predicting the intentions of vehicle users, resulting in the activation of vehicle functions requiring user command input and a lack of intelligence and automation.

Method used

Using UWB-based sensor networks and machine learning models, it tracks the location and movements of vehicle users in real time, predicts user intentions through UWB sensor data and Bayesian estimation, and uses controllers to automatically activate vehicle functions.

Benefits of technology

It enables automatic activation of vehicle functions without user commands, improves vehicle intelligence and user experience, and enhances the vehicle's autonomous driving capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120681152A_ABST
    Figure CN120681152A_ABST
Patent Text Reader

Abstract

A vehicle user prediction method includes receiving ultra wide band (UWB) sensor data from UWB sensors in real time. The UWB sensor comprises a UWB and a UWB tag. The method further includes tracking motion of the UWB tag in real time using the UWB sensor data to determine whether a user of the vehicle is approaching the vehicle, and determining a real-time location of the UWB tag relative to the vehicle using the Bayesian estimate, the UWB sensor data, and the motion of the UWB tag. The method further includes predicting, using the machine learning model, an intent of the vehicle user using the motion of the UWB tag and the real-time location of the UWB tag relative to the vehicle, and in response to predicting the intent of the vehicle user, controlling, using a controller of the vehicle, actuator actuation of the vehicle.
Need to check novelty before this filing date? Find Prior Art