IP Library Granted Patent US 12,221,098
Granted Patent B2
US 12,221,098 · App. 18/178,605 · Granted Feb 11, 2025

Methods and systems for autonomous vehicle inference of routes for actors exhibiting unrecognized behavior

Inventors: Greydon Foil (Pittsburgh, PA); Andrew T. Hartnett (West Hartford, CT); Constantin Savtchenko (Sewickley, PA)
Assignee: Volkswagen Group of America Investments, LLC
B60W30/0956B60W30/09B60W60/001B60W2552/53B60W2554/4043
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 12,221,098
App. No.
18/178,605
Granted
Feb 11, 2025
Kind
B2
Abstract

Systems and methods for operating a robot. The methods comprise: performing, by a processor, operations to detect an object that is moving; identifying, by the processor, detected behavior of the object that constitutes an unrecognized behavior; predicting, by the processor, future movement of the object based on a circle having a radius that is function of a velocity of the object; and controlling operations of the robot based on the predicting.

Claims (47)

1. A method for operating a robot, comprising:

performing, by a processor, operations to detect an object that is moving;

identifying, by the processor, detected behavior of the object that constitutes an unrecognized behavior;

predicting, by the processor, future movement of the object based on a circle having a radius that is function of a velocity of the object; and

controlling operations of the robot based on the predicting;

wherein the radius represents a distance at which the object will merge into a route along which other objects are moving.

2. A method for operating a robot, comprising:

performing, by a processor, operations to detect an object that is moving;

identifying, by the processor, detected behavior of the object that constitutes an unrecognized behavior;

predicting, by the processor, future movement of the object based on a circle having a radius that is function of a velocity of the object; and

controlling operations of the robot based on the predicting;

wherein the predicting further comprises identifying one or more points on a circumference of the circle for consideration as candidate target points for the object.

3. The method according to claim 2 , wherein one or more points are identified based on a lane in which the object is traveling.

4. The method according to claim 3 , wherein the one or more points comprise points on the circumference of the circle that are intersected by a centerline of the lane.

5. The method according to claim 2 , wherein the predicting further comprises assigning a score to each of the candidate target points based on at least one of a heading of the object, a feasibility of a reference path from a location of the object to one of the candidate target points, a lateral acceleration of the object, a curvature of the circuit, and a minimum curvature that the robot can accommodate.

6. The method according to claim 5 , wherein the predicting further comprises selecting one of the candidate target points associated with the score with a lowest value of a plurality of scores respectively assigned to the candidate target points.

7. The method according to claim 6 , wherein the predicting further comprises generating a reference path from a location of the object to the candidate target point which was selected.

8. The method according to claim 6 , wherein the reference path comprises a curve or a spline generated using a Bernstein polynomial.

9. The method according to claim 1 , wherein the robot comprises an autonomous vehicle and the controlling operation of the robot comprises adjusting one or more driving operations of the autonomous vehicle.

10. A system, comprising:

a processor; and

a non-transitory computer-readable storage medium comprising programming instructions that are configured to cause the processor to implement a method for operating a robot, wherein the programming instructions comprise instructions to:

detect an object that is moving;

identify detected behavior of the object that constitutes an unrecognized behavior;

predict future movement of the object based on a circle having a radius that is function of a velocity of the object; and

control operations of the robot based on the predicting;

wherein the radius represents a distance at which the object will merge into a route along which other objects are moving.

11. A system, comprising:

a processor; and

a non-transitory computer-readable storage medium comprising programming instructions that are configured to cause the processor to implement a method for operating a robot, wherein the programming instructions comprise instructions to:

detect an object that is moving;

identify detected behavior of the object that constitutes an unrecognized behavior;

predict future movement of the object based on a circle having a radius that is function of a velocity of the object; and

control operations of the robot based on the predicting;

wherein the future movement of the object is predicted by identifying one or more points on a circumference of the circle for consideration as candidate target points for the object.

12. The system according to claim 11 , wherein one or more points are identified based on a lane in which the object is traveling.

13. The system according to claim 12 , wherein the one or more points comprise points on the circumference of the circle that are intersected by a centerline of the lane.

14. The system according to claim 11 , wherein the future movement of the object is predicted by further assigning a score to each of the candidate target points based on at least one of a heading of the object, a feasibility of a reference path from a location of the object to one of the candidate target points, a lateral acceleration of the object, a curvature of the circle, and a minimum curvature that the robot can accommodate.

15. The system according to claim 14 , wherein the future movement of the object is predicted by further selecting one of the candidate target points associated with the score with a lowest value of a plurality of scores respectively assigned to the candidate target points.

16. The system according to claim 15 , wherein the future movement of the object is predicted by further generating a reference path from a location of the object to the candidate target point which was selected.

17. The system according to claim 15 , wherein the reference path comprises a curve or a spline generated using a Bernstein polynomial.

18. A non-transitory computer-readable medium that stores instructions that, when executed by at least one computing device, will cause the at least one computing device to perform operations comprising:

detecting an object that is moving;

identifying detected behavior of the object that constitutes an unrecognized behavior;

predicting future movement of the object based on a circle having a radius that is function of a velocity of the object; and

controlling operations of the robot based on the predicting;

wherein (i) the radius represents a distance at which the object will merge into a route along which other objects are moving, and or (ii) the future movement of the object is predicted by identifying one or more points on a circumference of the circle for consideration as candidate target points for the object.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 9, 2024
From: ARGO AI, LLC
To: VOLKSWAGEN GROUP OF AMERICA INVESTMENTS, LLC
Reel/Frame 069177/0099 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 6, 2023
From: FOIL, GREYDON; HARTNETT, ANDREW T.; SAVTCHENKO, CONSTANTIN
To: ARGO AI, LLC
Reel/Frame 062887/0262 →
Continuity (3)
Continuation 17207889 · Mar 22, 2021
Continuation 17060817 · Oct 1, 2020
Related Publication 20230202472A1 · Jun 29, 2023
References Cited (97)
US 6510388B1 · Sporrong et al. · 2003 [cited by applicant]
US 6820006B2 · Patera · 2004 [cited by applicant]
US 8146703B2 · Baumann et al. · 2012 [cited by applicant]
US 8340883B2 · Arbitmann et al. · 2012 [cited by applicant]
US 8755998B2 · Braennstroem et al. · 2014 [cited by applicant]
US 9229453B1 · Lee · 2016 [cited by applicant]
US 9248834B1 · Ferguson et al. · 2016 [cited by applicant]
US 9428196B2 · Ono · 2016 [cited by applicant]
US 9495874B1 · Zhu et al. · 2016 [cited by applicant]
US 9517767B1 · Kentley et al. · 2016 [cited by applicant]
US 9555781B2 · Breuer et al. · 2017 [cited by applicant]
US 9630619B1 · Kentley et al. · 2017 [cited by applicant]
US 9669827B1 · Ferguson et al. · 2017 [cited by applicant]
US 9824589B1 · Ramirez · 2017 [cited by applicant]
US 10005464B2 · Toyoda et al. · 2018 [cited by applicant]
US 10026318B2 · Maeda et al. · 2018 [cited by applicant]
US 10037694B2 · Lee · 2018 [cited by applicant]
US 10046761B2 · Meyer et al. · 2018 [cited by applicant]
US 10360800B2 · Bender et al. · 2019 [cited by applicant]
US 10496091B1 · Ross et al. · 2019 [cited by applicant]
US 10509413B2 · Mou · 2019 [cited by applicant]
US 10564639B1 · Zhu et al. · 2020 [cited by applicant]
US 10745003B2 · Kentley-Klay et al. · 2020 [cited by applicant]
US 10928820B1 · Tao et al. · 2021 [cited by applicant]
US 12049226B2 · Pietzsch · 2024 [cited by examiner]
US 20030055563A1 · Jonas Lars et al. · 2003 [cited by applicant]
US 20030200067A1 · Johnson · 2003 [cited by examiner]
US 20080084283A1 · Kalik · 2008 [cited by applicant]
US 20110213513A1 · Naderhirn · 2011 [cited by applicant]
US 20110246156A1 · Zecha et al. · 2011 [cited by applicant]
US 20130253816A1 · Caminiti et al. · 2013 [cited by applicant]
US 20160185347A1 · Lefevre et al. · 2016 [cited by applicant]
US 20160299509A1 · Ueda · 2016 [cited by examiner]
US 20170039855A1 · Maeda et al. · 2017 [cited by applicant]
US 20170057498A1 · Katoh · 2017 [cited by applicant]
US 20170072563A1 · Anderson-Sprecher · 2017 [cited by examiner]
US 20170120803A1 · Kentley et al. · 2017 [cited by applicant]
US 20170120902A1 · Kentley et al. · 2017 [cited by applicant]
US 20170158193A1 · Lopez et al. · 2017 [cited by applicant]
US 20170217431A1 · Class et al. · 2017 [cited by applicant]
US 20170297568A1 · Kentley et al. · 2017 [cited by applicant]
US 20170329332A1 · Pilarski et al. · 2017 [cited by applicant]
US 20170336795A1 · Wei et al. · 2017 [cited by applicant]
US 20180005050A1 · Browning et al. · 2018 [cited by applicant]
US 20180099663A1 · Diedrich et al. · 2018 [cited by applicant]
US 20180099665A1 · You · 2018 [cited by applicant]
US 20180148052A1 · Suto et al. · 2018 [cited by applicant]
US 20180233048A1 · Andersson et al. · 2018 [cited by applicant]
US 20180257647A1 · Jurca et al. · 2018 [cited by applicant]
US 20190025841A1 · Haynes et al. · 2019 [cited by applicant]
US 20190220021A1 · Yasui et al. · 2019 [cited by applicant]
US 20190225150A1 · Nohl et al. · 2019 [cited by applicant]
US 20190225212A1 · Buerkle et al. · 2019 [cited by applicant]
US 20190243371A1 · Nister et al. · 2019 [cited by applicant]
US 20190291726A1 · Shalev-Shwartz et al. · 2019 [cited by applicant]
US 20190291727A1 · Shalev-Shwartz et al. · 2019 [cited by applicant]
US 20190291728A1 · Shalev-Shwartz et al. · 2019 [cited by applicant]
US 20190310644A1 · Zhang · 2019 [cited by applicant]
US 20190333373A1 · Fang et al. · 2019 [cited by applicant]
US 20200026277A1 · Palanisamy et al. · 2020 [cited by applicant]
US 20200079371A1 · Sakamoto · 2020 [cited by examiner]
US 20200086855A1 · Packer et al. · 2020 [cited by applicant]
US 20200111366A1 · Nanri et al. · 2020 [cited by applicant]
US 20200124424A1 · Shibahata · 2020 [cited by applicant]
US 20200201334A1 · Max et al. · 2020 [cited by applicant]
US 20200262418A1 · Lin · 2020 [cited by applicant]
US 20200276988A1 · Graves · 2020 [cited by applicant]
US 20200331470A1 · Nanri et al. · 2020 [cited by applicant]
US 20210026358A1 · Sheu · 2021 [cited by examiner]
US 20210031760A1 · Ostafew et al. · 2021 [cited by applicant]
US 20210035447A1 · Urano et al. · 2021 [cited by applicant]
US 20210107476A1 · Cui · 2021 [cited by applicant]
US 20210114589A1 · Komuro et al. · 2021 [cited by applicant]
US 20210157315A1 · Wray et al. · 2021 [cited by applicant]
US 20210166572A1 · Kim · 2021 [cited by examiner]
US 20210181749A1 · Pan et al. · 2021 [cited by applicant]
US 20210389133A1 · Brizzi et al. · 2021 [cited by applicant]
US 20220105928A1 · Foil et al. · 2022 [cited by applicant]
CN 109080629A · 2018 [cited by applicant]
CN 110462703A · 2019 [cited by applicant]
DE 102013001228A1 · 2014 [cited by applicant]
DE 102013001229A1 · 2014 [cited by applicant]
DE 102018131453A1 · 2020 [cited by applicant]
EP 3410419A1 · 2018 [cited by applicant]
EP 3552921A1 · 2019 [cited by applicant]
JP 2002236994A · 2002 [cited by applicant]
JP 2004301667A · 2004 [cited by applicant]
JP 2010228740A · 2010 [cited by applicant]
JP 2016122308A · 2016 [cited by applicant]
KR 1020180040014A · 2018 [cited by applicant]
KR 20180104496A · 2018 [cited by applicant]
WO 2014053735A2 · 2014 [cited by applicant]
WO 2016094088A1 · 2016 [cited by applicant]
Horst, John et al., “Trajectory Generation for an On-Road Autonomous Vehicle,” The National Institute of Standards and Technolgoy, pp. 1-9, Sep. 2005. [cited by applicant]
Wikipedia Article “Statistical classification” https://en.wikipedia.org/wiki/Statistical_classification, last accessed Oct. 14, 2023, pp. 1-4. [cited by applicant]
Office Action for European patent application No. 20854761.2 dated Jun. 27, 2024, 5 pages. [cited by applicant]
European search report for EP 21876222.7 dated Aug. 7, 2024, 7 pages. [cited by applicant]