Radar anti-deception system for identifying ghost objects resulting from reciprocity-based sensor deception

By using time-matched cluster computation and threshold technology from radar sensors to identify ghost objects, the problem of reciprocity deception in radar sensors is solved, and a highly efficient ghost object identification effect is achieved.

CN116263492BActive Publication Date: 2026-07-21GM GLOBAL TECHNOLOGY OPERATIONS LLC
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
GM GLOBAL TECHNOLOGY OPERATIONS LLC
Filing Date
2022-10-25
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

Existing anti-spoofing technologies struggle to effectively identify ghost objects generated by reciprocity-based sensor spoofing, especially in radar sensors.

Method used

Input detection points generated by multiple radar sensors are used to determine time-matched clusters by executing commands from the controller. The adjusted signal-to-noise ratio (SNR) and velocity ratio are calculated, and ghost objects are identified by thresholding techniques. Object classification is performed by combining fuzzy c-means clustering algorithm and nearest neighbor technique.

Benefits of technology

It achieves efficient identification of ghost objects generated by reciprocity-based sensor deception, with an average classification accuracy of 92.3%, effectively mitigating the impact of radar sensor deception.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116263492B_ABST
    Figure CN116263492B_ABST
Patent Text Reader

Abstract

A radar anti-deception system for an autonomous vehicle includes a plurality of radar sensors that generate a plurality of input detections representing radio frequency (RF) signals reflected from objects, and a controller in electronic communication with the plurality of radar sensors. The controller executes instructions to determine time-matched clusters based on the input detections from the plurality of radar sensors, the time-matched clusters representing objects located in an environment surrounding the autonomous vehicle. The controller determines an adjusted signal-to-noise ratio (SNR) metric for a particular time-matched cluster by dividing an SNR of the particular time-matched cluster by a range measurement of the particular time-matched cluster. The controller determines a velocity ratio metric for the time-matched cluster by dividing a motion-based velocity by a Doppler frequency velocity, and identifies the time-matched cluster as a ghost object or a real object.
Need to check novelty before this filing date? Find Prior Art