IP Library Granted Patent US 12,560,439
Granted Patent B2
US 12,560,439 · App. 18/355,874 · Granted Feb 24, 2026

High integrity path extraction in rail using autonomy sensors

Inventors: Jaewook Jung (Toronto, CA); Veronica Marin (Toronto, CA); Mohamed Helwa (Toronto, CA); Jungwon Kang (Toronto, CA); David Beach (Toronto, CA)
Assignee: Hitachi Rail GTS Canada Inc.
G01C21/28
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 12,560,439
App. No.
18/355,874
Granted
Feb 24, 2026
Kind
B2
Abstract

Path extraction for a vehicle on a guideway, the vehicle having two or more sensors. Two or more sensor inputs are received from two or more sensors including at least one active 3D sensor input from at least one active 3D sensor and at least one passive 2D sensor input from at least one passive 2D sensor. At least one active 3D sensor path is extracted based on the at least one active 3D sensor input and at least one passive 2D sensor path based on the at least one passive 2D sensor input. At least one 3D sensor ground surface model is generated based on the at least one passive 2D sensor path. At least one passive 3D path is generated based on the at least one passive 2D sensor path and the at least one 3D sensor ground surface model. The at least one passive 3D path and the at least one active 3D sensor path are fused to produce a consolidated 3D path. In a path extraction pipeline, at least one supervision check is performed for providing integrity to the consolidated 3D path.

Claims (82)

1 . A method of path extraction for a vehicle on a guideway, comprising:

receiving two or more sensor inputs from two or more sensors including at least one active 3D sensor input from at least one active 3D sensor and at least one passive 2D sensor input from at least one passive 2D sensor;

extracting at least one active 3D sensor path based on the at least one active 3D sensor input and at least one passive 2D sensor path based on the at least one passive 2D sensor input;

generating at least one 3D sensor ground surface model based on the at least one passive 2D sensor path;

generating at least one passive 3D path based on the at least one passive 2D sensor path and the at least one 3D sensor ground surface model;

fusing the at least one passive 3D path and the at least one active 3D sensor path to produce a consolidated 3D path; and

performing, in a path extraction pipeline, at least one supervision check for providing integrity to the consolidated 3D path.

2 . The method of claim 1 , wherein the performing, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path includes, prior to the fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing, in the path extraction pipeline, a 3D path diversity check, the 3D path diversity check incudes:

receiving the at least one active 3D sensor path and the at least one passive 3D path;

performing the 3D path diversity check based on the at least one active 3D sensor path and the at least one passive 3D path to generate a 3D path diversity check status indicating one of success or failure of the 3D path diversity check; and

based on the 3D path diversity check status indicating one of success or failure of the 3D path diversity check, generating the consolidated 3D path.

3 . The method of claim 1 , wherein the performing, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path includes, after the fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing a 3D path plausibility check in the path extraction pipeline, the 3D path plausibility check includes:

receiving the consolidated 3D path; and

performing the 3D path plausibility check on the consolidated 3D path by determining whether the consolidated 3D path satisfies one or more 3D path plausibility parameters.

4 . The method of claim 3 , wherein the determining whether the consolidated 3D path satisfies the one or more 3D path plausibility parameters includes determining whether the consolidated 3D path meets at least one of: is smooth, without kinks of breaks, has a correct track gauge, has an acceptable Radius of Curvature (ROC), has an acceptable grade within predetermined grade bounds, has acceptable hill and sag within predetermined hill and sag bounds, has acceptable track transition curve, or has acceptable superelevation/crosslevel within predetermined superelevation/crosslevel bounds.

5 . The method of claim 1 , wherein the performing, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path includes, after the fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing a 3D path historical diversity check in the path extraction pipeline, the 3D path historical diversity check including:

receiving a past traversed path from a past window of size k;

receiving a past inertial measurements in the window of size k;

based on the past traversed path from the past window of size k and the past inertial measurements in the window of size k, determining a trustworthiness of the past traversed path; and

based on the trustworthiness, determining whether the past traversed path matches the consolidated 3D path.

6 . The method of claim 1 , wherein the performing, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path includes, after the fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing a 3D path consistency check in the path extraction pipeline, the 3D path consistency check includes:

receiving the consolidated 3D path;

receiving a past traversed path; and

verifying the consolidated 3D path includes no continuity breaks.

7 . The method of claim 1 , wherein the performing, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path includes, after the fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing at least one active 3D path similar sensors consistency check for the at least one active 3D sensor path and to check that the at least one active 3D sensor path is within a predetermined active 3D sensor path tolerance, and at least one passive 3D path similar sensors consistency check for the at least one passive 3D path and to check that the at least one passive 3D path is within a predetermined passive 3D path tolerance.

8 . A path extractor, comprises:

a memory storing computer-readable instructions; and

a processor connected to the memory, wherein the processor is configured to execute the computer-readable instructions to perform operations to:

receive two or more sensor inputs from two or more sensors including at least one active 3D sensor input from at least one active 3D sensor and at least one passive 2D sensor input from at least one passive 2D sensor;

extract at least one active 3D sensor path based on the at least one active 3D sensor input and at least one passive 2D sensor path based on the at least one passive 2D sensor input;

generate at least one 3D sensor ground surface model based on the at least one passive 2D sensor path;

generate at least one passive 3D path based on the at least one passive 2D sensor path and the at least one 3D sensor ground surface model;

fuse the at least one passive 3D path and the at least one active 3D sensor path to produce a consolidated 3D path; and

perform, in a path extraction pipeline, at least one supervision check for providing integrity to the consolidated 3D path.

9 . The path extractor of claim 8 , wherein the processor is further configured to perform, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path by:

prior to fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing, in the path extraction pipeline, a 3D path diversity check, wherein the processor performs the 3D path diversity check by:

receiving the at least one active 3D sensor path and the at least one passive 3D path;

performing the 3D path diversity check based on the at least one active 3D sensor path and the at least one passive 3D path to generate a 3D path diversity check status indicating one of success or failure of the 3D path diversity check; and

based on the 3D path diversity check status indicating one of success or failure of the 3D path diversity check, generating the consolidated 3D path.

10 . The path extractor of claim 8 , wherein the processor is further configured to perform, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path by:

after fusing, the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing a 3D path plausibility check in the path extraction pipeline, wherein the processor performs the 3D path plausibility check by:

receiving the consolidated 3D path; and

performing the 3D path plausibility check on the consolidated 3D path by determining whether the consolidated 3D path satisfies one or more 3D path plausibility parameters.

11 . The path extractor of claim 10 , wherein the processor is further configured to determine whether the consolidated 3D path satisfies the one or more 3D path plausibility parameters by determining whether the consolidated 3D path meets at least one of: is smooth, without kinks of breaks, has a correct track gauge, has an acceptable Radius of Curvature (ROC), has an acceptable grade within predetermined grade bounds, has acceptable hill and sag within predetermined hill and sag bounds, has acceptable track transition curve, or has acceptable superelevation/crosslevel within predetermined superelevation/crosslevel bounds.

12 . The path extractor of claim 8 , wherein the processor is further configured to perform, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path by:

after fusing, the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing a 3D path historical diversity check in the path extraction pipeline, the processor performing the 3D path historical diversity check by:

receiving a past traversed path from a past window of size k;

receiving a past inertial measurements in the past window of size k;

based on the past traversed path from the past window of size k and the past inertial measurements in the past window of size k, determining a trustworthiness of the past traversed path; and

based on the trustworthiness, determining whether the past traversed path matches the consolidated 3D path.

13 . The path extractor of claim 8 , wherein the processor is further configured to perform, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path includes, after fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing a 3D path consistency check in the path extraction pipeline, wherein the processor performs the 3D path consistency check by:

receiving the consolidated 3D path;

receiving a past traversed path; and

verifying the consolidated 3D path includes no continuity breaks.

14 . The path extractor of claim 8 , wherein the processor is further configured to perform, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path by, after fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path:

performing at least one active 3D path similar sensors consistency check for the at least one active 3D sensor path to assess a similarity and that the at least one active 3D sensor path is within a predetermined active 3D sensor path tolerance, and

performing at least one passive 3D path similar sensors consistency check for the at least one passive 3D path and to check that the at least one passive 3D path is within a predetermined passive 3D path tolerance.

15 . A non-transitory computer-readable media having computer-readable instructions stored thereon, which when executed by a processor causes the processor to perform operations comprising:

receiving two or more sensor inputs from two or more sensors including at least one active 3D sensor input from at least one active 3D sensor and at least one passive 2D sensor input from at least one passive 2D sensor;

extracting at least one active 3D sensor path based on the at least one active 3D sensor input and at least one passive 2D sensor path based on the at least one passive 2D sensor input;

generating at least one 3D sensor ground surface model based on the at least one passive 2D sensor path;

generating at least one passive 3D path based on the at least one passive 2D sensor path and the at least one 3D sensor ground surface model;

fusing the at least one passive 3D path and the at least one active 3D sensor path to produce a consolidated 3D path; and

performing, in a path extraction pipeline, at least one supervision check for providing integrity to the consolidated 3D path.

16 . The non-transitory computer-readable media of claim 15 , wherein the performing, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path includes, prior to the fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing, in the path extraction pipeline, a 3D path diversity check, the 3D path diversity check incudes:

receiving the at least one active 3D sensor path and the at least one passive 3D path;

performing the 3D path diversity check based on the at least one active 3D sensor path and the at least one passive 3D path to generate a 3D path diversity check status indicating one of success or failure of the 3D path diversity check; and

based on the 3D path diversity check status indicating one of success or failure of the 3D path diversity check, generating the consolidated 3D path.

17 . The non-transitory computer-readable media of claim 15 , wherein the performing, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path includes, after the fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing a 3D path plausibility check in the path extraction pipeline, the 3D path plausibility check includes:

receiving the consolidated 3D path; and

performing the 3D path plausibility check on the consolidated 3D path by determining whether the consolidated 3D path satisfies one or more 3D path plausibility parameters,

wherein the determining whether the consolidated 3D path satisfies the one or more 3D path plausibility parameters includes determining whether the consolidated 3D path meets at least one of: is smooth, without kinks of breaks, has a correct track gauge, has an acceptable Radius of Curvature (ROC), has an acceptable grade within predetermined grade bounds, has acceptable hill and sag within predetermined hill and sag bounds, has acceptable track transition curve, or has acceptable superelevation/crosslevel within predetermined superelevation/crosslevel bounds.

18 . The non-transitory computer-readable media of claim 15 , wherein the performing, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path includes, after the fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing a 3D path historical diversity check in the path extraction pipeline, the 3D path historical diversity check including:

receiving a past traversed path from a past window of size k;

receiving a past inertial measurements in the past window of size k;

based on the past traversed path from the past window of size k and the past inertial measurements in the past window of size k, determining a trustworthiness of the past traversed path; and

based on the trustworthiness, determining whether the past traversed path matches the consolidated 3D path.

19 . The non-transitory computer-readable media of claim 15 , wherein the performing, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path includes, after the fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing a 3D path consistency check in the path extraction pipeline, the 3D path consistency check includes:

receiving the consolidated 3D path;

receiving a past traversed path; and

verifying the consolidated 3D path includes no continuity breaks.

20 . The non-transitory computer-readable media of claim 15 , wherein the performing, in the path extraction pipeline, the at least one supervision check for providing the integrity to the consolidated 3D path includes, after the fusing the at least one passive 3D path and the at least one active 3D sensor path to produce the consolidated 3D path, performing at least one active 3D path similar sensors consistency check for the at least one active 3D sensor path to assess a similarity and that the at least one active 3D sensor path is within a predetermined active 3D sensor path tolerance, and at least one passive 3D path similar sensors consistency check for the at least one passive 3D path and to check that the at least one passive 3D path is within a predetermined passive 3D path tolerance.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 9, 2025
From: JUNG, JAEWOOK; MARIN, VERONICA; HELWA, MOHAMED; KANG, JUNGWON; BEACH, DAVID
To: GROUND TRANSPORTATION SYSTEMS CANADA INC.
Reel/Frame 070790/0714 →
CHANGE OF NAME Recorded Sep 6, 2024
From: GROUND TRANSPORTATION SYSTEMS CANADA INC.
To: HITACHI RAIL GTS CANADA INC.
Reel/Frame 068829/0462 →
Continuity (2)
Provisional Application 63368910 · Jul 20, 2022
Related Publication 20240027196A1 · Jan 25, 2024
References Cited (18)
US 10518791B2 · Singh · 2019 [cited by applicant]
US 10549768B2 · Puttagunta et al. · 2020 [cited by applicant]
US 10900793B2 · Jung et al. · 2021 [cited by applicant]
US 11377123B2 · Mortazavi et al. · 2022 [cited by applicant]
US 20140203959A1 · Kriel et al. · 2014 [cited by applicant]
US 20190039633A1 · Li · 2019 [cited by applicant]
US 20190353774A1 · Chondro et al. · 2019 [cited by applicant]
US 20200070859A1 · Green et al. · 2020 [cited by applicant]
US 20200174112A1 · Xing et al. · 2020 [cited by applicant]
US 20210072743A1 · Otaki et al. · 2021 [cited by applicant]
US 20210089055A1 · Tran · 2021 [cited by examiner]
US 20210094595A1 · Kälberer et al. · 2021 [cited by applicant]
US 20210114637A1 · Chung et al. · 2021 [cited by applicant]
US 20210302564A1 · Lee · 2021 [cited by applicant]
US 20210362759A1 · Khosla · 2021 [cited by applicant]
US 20220114752A1 · Kavulya et al. · 2022 [cited by applicant]
US 20220161815A1 · Van Beek et al. · 2022 [cited by applicant]
International Search Report and Written Opinion issued in corresponding International Application No. PCT/IB2023/057427, dated Oct. 25, 2023, Canadian Intellectual Property Office, Gatineau, Quebec, Canada. [cited by applicant]