IP Library › Granted Patent US 12,399,500
Granted Patent B1
US 12,399,500 · App. 17/742,655 · Granted Aug 26, 2025

Endpoint approach and localization for autonomous robotic vehicles

Inventors: John Enright (Bedford, MA); Gabriel Hebert (Wakefield, MA); Jaimie Marie-Michelle Carlson (Boston, MA); Sadat Ali Shaik (Downingtown, PA)
Assignee: Amazon Technologies, Inc.
G05D1/0234
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 12,399,500
App. No.
17/742,655
Granted
Aug 26, 2025
Kind
B1
Abstract

Systems and methods are disclosed for improved endpoint approach and localization for autonomous mobile robots. In one embodiment, an example system may include a floor-mounted guide disposed on a floor of an environment, and an autonomous mobile robot having a camera and a controller. The autonomous mobile robot may be configured to autonomously navigate in the environment, where the controller can be configured to detect a first edge of the floor-mounted guide using the camera, detect a second edge of the floor-mounted guide using the camera, determine a location of the autonomous mobile robot based at least in part on the first edge and the second edge, and update a navigation path based at least in part on the location.

Claims (44)

1. An autonomous mobile robot navigation system comprising:

a floor-mounted guide disposed on a floor of an environment, wherein the floor-mounted guide has a fiducial disposed at a center of the floor-mounted guide, and comprises a bright colored border surrounding the fiducial; and

an autonomous mobile robot comprising a camera and a controller, the autonomous mobile robot configured to autonomously navigate in the environment, wherein the controller is configured to:

detect a first edge of the floor-mounted guide using the camera;

detect a second edge of the floor-mounted guide using the camera;

determine that a confidence interval associated with at least one of the first edge or the second edge is greater than a threshold;

determine a location of the autonomous mobile robot based at least in part on the first edge and the second edge;

determine a pose of the autonomous mobile robot based at least in part on the first edge and the second edge; and

update a navigation path based at least in part on the location and the pose.

2. The autonomous mobile robot navigation system of claim 1 , wherein the bright colored border has a first area that is at least ten times greater than a second area of the fiducial.

3. The autonomous mobile robot navigation system of claim 1 , wherein the floor-mounted guide occupies at least 0.5% of a field of view of the camera at a distance of between 0.5 and 1.0 meters between the camera and the floor-mounted guide.

4. A system comprising:

a floor-mounted guide disposed on a floor of an environment; and

an autonomous mobile robot comprising a camera and a controller, the autonomous mobile robot configured to autonomously navigate in the environment, wherein the controller is configured to:

detect a first edge of the floor-mounted guide using the camera;

detect a second edge of the floor-mounted guide using the camera;

determine that a confidence interval associated with at least one of the first edge or the second edge is greater than a threshold;

determine a pose of the autonomous mobile robot based at least in part on the first edge and the second edge; and

update a navigation path based at least in part on the pose.

5. The system of claim 4 , wherein the floor-mounted guide comprises a fiducial disposed at a center of the floor-mounted guide, and comprises a border surrounding the fiducial.

6. The system of claim 5 , wherein the border has a first area that is at least ten times greater than a second area of the fiducial.

7. The system of claim 5 , wherein the controller is further configured to:

detect the fiducial; and

determine a location of the autonomous mobile robot based at least in part on the fiducial.

8. The system of claim 4 , wherein the floor-mounted guide is at least one of: a single piece sticker assembly, or a painted floor feature.

9. The system of claim 4 , wherein the camera is a first camera, and the autonomous mobile robot further comprises a second camera, and wherein the controller is further configured to:

determine that the autonomous mobile robot is on top of a center of the floor-mounted guide using the second camera.

10. The system of claim 4 , wherein an angle between a camera plane along which the camera is oriented and a floor plane along which the floor-mounted guide is mounted is less than 45 degrees.

11. The system of claim 4 , wherein the floor-mounted guide comprises an anti-glare coating, and wherein the camera is a front-facing camera.

12. The system of claim 4 , wherein the floor-mounted guide occupies at least 0.5% of a field of view of the camera at a distance of between 0.5 and 1.0 meters between the camera and the floor-mounted guide.

13. A method comprising:

navigating, by an autonomous mobile robot, through an ambient environment from a first location to a second location;

detecting a first edge of a floor-mounted guide;

detecting a second edge of the floor-mounted guide;

determining that a confidence interval associated with at least one of the first edge or the second edge is greater than a threshold;

determining a pose of the autonomous mobile robot based at least in part on the first edge and the second edge; and

updating a navigation path based at least in part on the pose.

14. The method of claim 13 , further comprising:

determining that the autonomous mobile robot is within a predetermined distance of the second location prior to detecting the first edge of the floor-mounted guide.

15. The method of claim 13 , wherein the floor-mounted guide comprises a fiducial disposed at a center of the floor-mounted guide, and comprises a border surrounding the fiducial.

16. The method of claim 15 , further comprising:

detecting the fiducial; and

determining a location of the autonomous mobile robot based at least in part on the fiducial.

17. The method of claim 15 , wherein the border has a first area that is at least ten times greater than a second area of the fiducial.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 25, 2024
From: ENRIGHT, JOHN; HEBERT, GABRIEL; CARLSON, JAIMIE MARIE-MICHELLE; ALI SHAIK, SADAT
To: AMAZON TECHNOLOGIES, INC.
Reel/Frame 068085/0493 →
References Cited (17)
US 9152149B1 · Palamarchuk · 2015 [cited by examiner]
US 11555703B2 · Syrstad · 2023 [cited by examiner]
US 11685603B1 · Serstad · 2023 [cited by examiner]
US 20020186884A1 · Shaked · 2002 [cited by examiner]
US 20150371181A1 · Palamarchuk · 2015 [cited by examiner]
US 20190332096A1 · Porter · 2019 [cited by examiner]
US 20200017135A1 · Carter · 2020 [cited by examiner]
US 20210045379A1 · Grant · 2021 [cited by examiner]
US 20210149416A1 · Srivastava · 2021 [cited by examiner]
US 20210294347A1 · Chen · 2021 [cited by examiner]
US 20210382494A1 · Park · 2021 [cited by examiner]
US 20210405646A1 · Park · 2021 [cited by examiner]
US 20220097238A1 · Martel · 2022 [cited by examiner]
US 20220266867A1 · Ballard · 2022 [cited by examiner]
US 20230256959A1 · Chiba · 2023 [cited by examiner]
US 20240370983A1 · Schwartz · 2024 [cited by examiner]
M. Fiala, “Designing Highly Reliable Fiducial Markers,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, No. 7, pp. 1317-1324, Jul. 2010, doi: 10.1109/TPAMI.2009.146 (Year: 2010). [cited by examiner]