IP Library › Granted Patent US 12,535,559
Granted Patent B2
US 12,535,559 · App. 18/020,814 · Granted Jan 27, 2026

Method for recognizing road users in an environment of a vehicle on the basis of measurements of a radar sensor, by identifying faulty detections, and computing device

Inventor: Dominik Kellner (Dachau, DE)
Assignee: Bayerische Motoren Werke Aktiengesellschaft
G01S7/414G01S13/931
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,535,559
App. No.
18/020,814
Granted
Jan 27, 2026
Kind
B2
Abstract

A method for recognizing road users in an environment of a vehicle includes determining detections that describe potential objects in the environment, identifying faulty detections within the detections, and recognizing the road users on the basis of the detections other than the faulty detections. Identifying the faulty detections further includes, for each detection, checking, on the basis of the spatial position with respect to other detections, whether the detection originates from a reflection effect of a plurality of predefined reflection effects of the radar signal, wherein the plurality of predefined reflection effects describes at least one additional reflection of the radar signal after a first reflection of the radar signal by an object.

Claims (55)

1 . A method for recognizing road users in an environment of a vehicle, the method comprising:

determining detections that describe potential objects in the environment of the vehicle,

wherein the detections are each determined for chronologically successive measurement cycles of a radar sensor of the vehicle, and wherein, in a measurement cycle, the radar sensor emits a radar signal and the radar sensor receives the radar signal reflected in the environment;

identifying faulty detections within the detections; and

recognizing the road users on a basis of the detections other than the faulty detections;

wherein identifying the faulty detections further comprises checking, for respective detections on a basis of a spatial location in relation to other detections, whether the detection originates from a reflection effect of a plurality of predetermined reflection effects of the radar signal, wherein checking whether the detection originates from the predetermined reflection effect is performed only for detections that are assigned to dynamic objects in the environment, and

wherein the plurality of predetermined reflection effects describes at least one additional reflection of the radar signal after an initial reflection of the radar signal on an object.

2 . The method according to claim 1 , further comprising:

assigning detections from at least two of the successive measurement cycles to one another, wherein detections in which an assignment does not take place are assumed to be faulty detections.

3 . The method according to claim 1 ,

wherein one of the predetermined reflection effects describes at least two reflections of the radar signal on the same object, and

wherein the method further comprises assuming a detection to be a faulty detection in response to the detection being arranged behind another detection originating from the radar sensor.

4 . The method according to claim 3 , further comprising:

assuming the detection to be a faulty detection in response to the detection being arranged outside a predetermined object range that is assigned to the another detection.

5 . The method according to claim 3 , further comprising:

assuming the detection to be a faulty detection in response to velocity values of the detection and the another detection being essentially equal.

6 . The method according to claim 1 ,

wherein one of the predetermined reflection effects describes a multiple reflection of the radar signal between the vehicle and an object, and

wherein the method further comprises assuming a detection to be a faulty detection in response to a distance value and/or a velocity value of the detection being approximately a multiple of a distance value and/or a velocity value of another detection.

7 . The method according to claim 1 ,

wherein one of the predetermined reflection effects describes the at least one additional reflection of the radar signal on an object, and

wherein the method further comprises assuming a detection to be a faulty detection if the detection describes a mirroring of another detection on the object.

8 . The method according to claim 1 ,

wherein checking whether the detection originates from one of the reflection effects of the plurality of predetermined reflection effects further comprises sorting the detections as a function of a distance value assigned to the detections.

9 . A computing device for a sensor system of a vehicle, wherein the computing device is configured to:

determine detections that describe potential objects in the environment of the vehicle,

wherein the detections are each determined for chronologically successive measurement cycles of a radar sensor of the vehicle, and wherein, in a measurement cycle, the radar sensor emits a radar signal and the radar sensor receives the radar signal reflected in the environment;

identify faulty detections within the detections; and

recognize the road users on a basis of the detections other than the faulty detections;

wherein the computing device is configured to identify the faulty detections by checking, for respective detections on a basis of a spatial location in relation to other detections, whether the detection originates from a reflection effect of a plurality of predetermined reflection effects of the radar signal, wherein checking whether the detection originates from the predetermined reflection effect is performed only for detections that are assigned to dynamic objects in the environment, and

wherein the plurality of predetermined reflection effects describes at least one additional reflection of the radar signal after an initial reflection of the radar signal on an object.

10 . The computing device according to claim 9 , wherein the computing device is configured to:

assign detections from at least two of the successive measurement cycles to one another, wherein detections in which an assignment does not take place are assumed to be faulty detections.

11 . The computing device according to claim 9 ,

wherein one of the predetermined reflection effects describes at least two reflections of the radar signal on the same object, and

wherein the computing device is configured to assume a detection to be a faulty detection in response to the detection being arranged behind another detection originating from the radar sensor.

12 . The computing device according to claim 11 , wherein the computing device is configured to:

assume the detection to be a faulty detection in response to the detection being arranged outside a predetermined object range that is assigned to the another detection.

13 . The computing device according to claim 11 , wherein the computing device is configured to:

assume the detection to be a faulty detection in response to velocity values of the detection and the another detection being essentially equal.

14 . The computing device according to claim 9 ,

wherein one of the predetermined reflection effects describes a multiple reflection of the radar signal between the vehicle and an object, and

wherein the computing device is configured to assume a detection to be a faulty detection in response to a distance value and/or a velocity value of the detection being approximately a multiple of a distance value and/or a velocity value of another detection.

15 . The computing device according to claim 9 ,

wherein one of the predetermined reflection effects describes the at least one additional reflection of the radar signal on an object, and

wherein the computing device is configured to assume a detection to be a faulty detection if the detection describes a mirroring of another detection on the object.

16 . The computing device according to claim 9 , wherein the computing device is configured to:

check whether the detection originates from one of the reflection effects of the plurality of predetermined reflection effects further by sorting the detections as a function of a distance value assigned to the detections.

17 . A non-transitory computer-readable medium, having stored thereon commands that, when executed by a computing device, cause the computing device to carry out a method comprising:

determining detections that describe potential objects in the environment of the vehicle,

wherein the detections are each determined for chronologically successive measurement cycles of a radar sensor of the vehicle, and wherein, in a measurement cycle, the radar sensor emits a radar signal and the radar sensor receives the radar signal reflected in the environment;

identifying faulty detections within the detections; and

recognizing the road users on a basis of the detections other than the faulty detections;

wherein identifying the faulty detections further comprises checking, for respective detections on a basis of a spatial location in relation to other detections, whether the detection originates from a reflection effect of a plurality of predetermined reflection effects of the radar signal, wherein checking whether the detection originates from the predetermined reflection effect is performed only for detections that are assigned to dynamic objects in the environment, and

wherein the plurality of predetermined reflection effects describes at least one additional reflection of the radar signal after an initial reflection of the radar signal on an object.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 13, 2023
From: KELLNER, DOMINIK
To: BAYERISCHE MOTOREN WERKE AKTIENGESELLSCHAFT
Reel/Frame 062669/0912 →
Priority Claims (1)
DE 10 2020 121 108.2 · Aug 11, 2020 · national
Continuity (1)
Related Publication 20230305109A1 · Sep 28, 2023
References Cited (29)
US 8570213B2 · Nishiyama · 2013 [cited by examiner]
US 9810782B2 · Schiffmann · 2017 [cited by examiner]
US 10261172B2 · Lim · 2019 [cited by examiner]
US 10656248B2 · Bilik · 2020 [cited by examiner]
US 11754674B2 · Amizur · 2023 [cited by examiner]
US 20030122703A1 · Kishida · 2003 [cited by examiner]
US 20030179129A1 · Tamatsu · 2003 [cited by examiner]
US 20090009383A1 · Nakanishi · 2009 [cited by examiner]
US 20090121915A1 · Randler · 2009 [cited by examiner]
US 20100214153A1 · Kikuchi · 2010 [cited by examiner]
US 20120119937A1 · Yamada · 2012 [cited by examiner]
US 20130314272A1 · Gross · 2013 [cited by examiner]
US 20160274232A1 · Schiffmann · 2016 [cited by examiner]
US 20170261602A1 · Olshansky · 2017 [cited by examiner]
US 20180259634A1 · Okamoto · 2018 [cited by examiner]
US 20180341012A1 · Takada · 2018 [cited by examiner]
US 20200172108A1 · Ziegler · 2020 [cited by examiner]
US 20200363522A1 · Ishikawa · 2020 [cited by examiner]
US 20210018592A1 · Laghezza · 2021 [cited by examiner]
US 20210055375A1 · Smith · 2021 [cited by examiner]
US 20210104027A1 · Longman · 2021 [cited by examiner]
US 20210192235A1 · Bolduc · 2021 [cited by examiner]
US 20210325510A1 · Bialer · 2021 [cited by examiner]
US 20220163649A1 · Li · 2022 [cited by examiner]
DE 102004047087A1 · 2006 [cited by applicant]
EP 2667219A1 · 2013 [cited by applicant]
JP 2001116839A · 2001 [cited by applicant]
International Search Report (PCT/ISA/210) issued in PCT Application No. PCT/EP2021/072024 dated Nov. 22, 2021 with English translation (five (5) pages). [cited by applicant]
German-language Written Opinion (PCT/ISA/237) issued in PCT Application No. PCT/EP2021/072024 dated Nov. 22, 2021 (six (6) pages). [cited by applicant]