IP Library Granted Patent US 12,735,066
Granted Patent B2
US 12,735,066 · App. 18/173,524 · Granted Sep 15, 2026

Systems and methods to improve knowledge cycles in vehicular knowledge networking

Inventors: Seyhan Ucar (Mountain View, CA); Takamasa Higuchi (Mountain View, CA); Onur Altintas (Mountain View, CA)
Assignees: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.; TOYOTA JIDOSHA KABUSHIKI KAISHA
B60W60/0015B60W50/14G06N5/022B60W2050/146B60W2555/60
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 12,735,066
App. No.
18/173,524
Granted
Sep 15, 2026
Kind
B2
Abstract

Systems and methods are provided for vehicular knowledge networking, including an improved knowledge cycle process. Vehicular knowledge networking employs vehicular networking capabilities, such as vehicle-to-vehicle (V2) communication, to create and distribute contextual knowledge of risky zones. The knowledge is received by a vehicle as early guidance, allowing the driver to be preemptively prepared before entering the risky zone and safely maneuver once driving inside of the zone. The improved knowledge cycle process involves creating associated metadata in each stage of the knowledge cycle. The metadata can be analyzed and ultimately used to derive at least one path within the knowledge cycle that is known to have a high performance. Consequently, any degradation of subsequent iterations of the knowledge cycle, are improved by employing only the “beneficial” stages of the knowledge cycle, based on the metadata, in a manner that enhances the usefulness of the knowledge cycle.

Claims (54)

1 . A vehicle, comprising:

one or more processors configured to execute a knowledge cycle, the knowledge cycle executed to create and distribute knowledge in a vehicular knowledge network, wherein executing the knowledge cycle comprises creating knowledge associated with a geographic area and creating metadata relating to the knowledge cycle, the knowledge cycle comprising a plurality of stages, the plurality of stages comprising a knowledge creation stage and a knowledge networking stage, further wherein:

the knowledge creation stage comprises formation of knowledge using a selected knowledge creation technique, the selected knowledge creation technique being a knowledge creation path for the execution of the knowledge cycle; and

the knowledge networking stage comprises distribution of knowledge through the vehicular knowledge network using a selected knowledge networking technique, the selected knowledge networking technique being a knowledge networking path for the execution of the knowledge cycle; and

a controller configured to receive knowledge associated with the geographic area and causing the vehicle to perform one or more autonomous safety maneuvers based on the received knowledge when the vehicle is approaching the geographic area;

wherein at least one beneficial path is determined for a new execution of the knowledge cycle by analyzing the metadata relating to the knowledge cycle, wherein the beneficial path comprises a composite of the knowledge creation path and the knowledge networking path that are determined to be beneficial, wherein use of the beneficial path for the new execution improves the knowledge cycle.

2 . The vehicle of claim 1 , further comprising circuitry communicatively connected to the vehicular knowledge network.

3 . The vehicle of claim 2 , wherein the vehicular knowledge network comprises one or more entities communicating knowledge within the vehicular knowledge network.

4 . The vehicle of claim 3 , wherein the one or more entities comprise at least one of:

connected vehicles;

an edge network; and

a cloud.

5 . The vehicle of claim 4 , wherein the controller receives the communicated knowledge from the one or more entities of the vehicular knowledge network.

6 . The vehicle of claim 5 , wherein the circuitry receives knowledge from connected vehicles via vehicle-to-vehicle (V2V) communication.

7 . The vehicle of claim 6 , wherein the circuitry receives knowledge from the edge network via vehicle-to-cloud (V2C) communication.

8 . The vehicle of claim 1 , wherein the received knowledge is associated with risk reasoning of the geographic area.

9 . The vehicle of claim 8 , wherein performing the one or more autonomous safety maneuvers is based on the risk reasoning of the geographic area.

10 . The vehicle of claim 1 , wherein the one or more processors dynamically modify the knowledge cycle based on the metadata associated with the knowledge cycle.

11 . A system comprising:

at least one memory storing machine-executable instructions; and

at least one processor configured to access the at least one memory and execute the machine-executable instructions to:

execute a knowledge cycle associated with knowledge, the knowledge cycle executed to create and distribute knowledge in a vehicular knowledge network, wherein executing the knowledge cycle comprises creating knowledge related to a geographic area and the knowledge cycle comprises a plurality of stages, the plurality of stages comprising a knowledge creation stage and a knowledge networking stage, further wherein:

the knowledge creation stage comprises formation of knowledge using a selected knowledge creation technique, the selected knowledge creation technique being a knowledge creation path for the execution of the knowledge cycle; and

the knowledge networking stage comprises distribution of knowledge through the vehicular knowledge network using a selected knowledge networking technique, the selected knowledge networking technique being a knowledge networking path for the execution of the knowledge cycle;

create metadata associated with the knowledge cycle, wherein metadata is created for each of the plurality of stages of the knowledge cycle;

determine at least one beneficial path for a new execution of the knowledge cycle by analyzing the metadata associated with the knowledge cycle, wherein the beneficial path comprises a composite of the knowledge creation path and the knowledge networking path that are determined to be beneficial, wherein use of the beneficial path for the new execution improves the knowledge cycle; and

cause a vehicle to perform one or more autonomous safety maneuvers based on the created knowledge when the vehicle is approaching the geographic area.

12 . The system of claim 11 , wherein the at least one processor configured to access the at least one memory further executes the machine-executable instructions to:

detect whether there is degradation of the knowledge cycle; and

upon detecting that there is degradation of the knowledge cycle, perform degradation mitigation of the knowledge cycle.

13 . The system of claim 12 , wherein the degradation mitigation comprises dynamically modifying the knowledge cycle to integrate the beneficial path into executing the knowledge cycle.

14 . The system of claim 13 , wherein the at least one processor configured to access the at least one memory further executes the machine-executable instructions to:

identify a beneficial knowledge cycle, and extract one or more beneficial stages from the beneficial knowledge cycle.

15 . The system of claim 14 , wherein the plurality of stages for the knowledge cycle further comprises one or more of:

a knowledge storage stage; and

a knowledge refining stage.

16 . The system of claim 15 , wherein the metadata corresponding to each of the plurality of stages of the knowledge cycle comprises one or more of:

metadata of creation;

metadata of storage;

metadata of networking; and

metadata of refining.

17 . The system of claim 11 , wherein the one or more autonomous safety maneuvers includes generating a notification for a driver of the vehicle indicating a risk of the geographic area based on the created knowledge.

18 . A method comprising:

executing a knowledge cycle associated with knowledge, the knowledge cycle executed to create and distribute knowledge in a vehicular knowledge network, wherein executing the knowledge cycle comprises creating knowledge related to a geographic area and the knowledge cycle comprises a plurality of stages, the plurality of stages comprising a knowledge creation stage and a knowledge networking stage, further wherein:

the knowledge creation stage comprises formation of knowledge using a selected knowledge creation technique, the selected knowledge creation technique being a knowledge creation path for the execution of the knowledge cycle; and

the knowledge networking stage comprises distribution of knowledge through the vehicular knowledge network using a selected knowledge networking technique, the selected knowledge networking technique being a knowledge networking path for the execution of the knowledge cycle;

creating metadata associated with the knowledge cycle, wherein metadata is created for each of the plurality of stages of the knowledge cycle;

analyzing the metadata associated with the knowledge cycle;

determining at least one beneficial path for a new execution of the knowledge cycle based on analysis of the metadata associated with the knowledge cycle, wherein the beneficial path comprises a composite of the knowledge creation path and the knowledge networking path that are determined to be beneficial, wherein use of the beneficial path for the new execution improves the knowledge cycle; and

causing a vehicle to perform one or more autonomous safety maneuvers based on the created knowledge when the vehicle is approaching the geographic area.

19 . The method of claim 18 , further comprising:

detecting whether there is degradation of the knowledge cycle; and

upon detecting that there is degradation of the knowledge cycle, dynamically modifying the knowledge cycle to integrate the beneficial path into executing the knowledge cycle.

20 . The method of claim 19 , wherein analyzing the metadata comprises applying machine learning (ML).

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 23, 2023
From: UCAR, SEYHAN; HIGUCHI, TAKAMASA; ALTINTAS, ONUR
To: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.; TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 062787/0108 →
Continuity (1)
Related Publication 20240286643A1 · Aug 29, 2024
References Cited (88)
US 8451140B2 · Piccinini · 2013 [cited by applicant]
US 9047773B2 · Chen · 2015 [cited by applicant]
US 9495874B1 · Zhu · 2016 [cited by applicant]
US 9623765B2 · Liu · 2017 [cited by applicant]
US 10678259B1 · Ferguson · 2020 [cited by applicant]
US 10942030B2 · Haque · 2021 [cited by applicant]
US 10970317B2 · Thiel · 2021 [cited by applicant]
US 11085774B2 · Thiel · 2021 [cited by applicant]
US 11145142B2 · Chainer · 2021 [cited by applicant]
US 11282378B2 · Higuchi · 2022 [cited by applicant]
US 11593411B2 · Bruce · 2023 [cited by applicant]
US 11645279B2 · Jiang · 2023 [cited by applicant]
US 12176630B2 · Tran · 2024 [cited by applicant]
US 20050132006A1 · Horvitz · 2005 [cited by applicant]
US 20080077598A1 · Wilmering · 2008 [cited by applicant]
US 20090114463A1 · Devault · 2009 [cited by applicant]
US 20100072954A1 · Kohn · 2010 [cited by applicant]
US 20110153140A1 · Datta · 2011 [cited by applicant]
US 20120083960A1 · Zhu · 2012 [cited by applicant]
US 20120109408A1 · Siy · 2012 [cited by applicant]
US 20120143410A1 · Gallagher · 2012 [cited by applicant]
US 20120164620A1 · Needham · 2012 [cited by examiner]
US 20120179518A1 · Jaipaul · 2012 [cited by applicant]
US 20130024075A1 · Zagorski · 2013 [cited by applicant]
US 20130151058A1 · Zagorski · 2013 [cited by applicant]
US 20130166123A1 · Donald, III · 2013 [cited by applicant]
US 20130238181A1 · James · 2013 [cited by applicant]
US 20130246020A1 · Zeng · 2013 [cited by applicant]
US 20140032017A1 · Anderson · 2014 [cited by applicant]
US 20140074329A1 · Yang · 2014 [cited by applicant]
US 20140379183A1 · Long · 2014 [cited by applicant]
US 20150051763A1 · Enomoto · 2015 [cited by applicant]
US 20150057916A1 · Ishii · 2015 [cited by applicant]
US 20150291036A1 · Ryu · 2015 [cited by applicant]
US 20160321585A1 · Saraswat · 2016 [cited by examiner]
US 20180004206A1 · Lagnemma · 2018 [cited by examiner]
US 20180129205A1 · Choi · 2018 [cited by examiner]
US 20190078899A1 · Iagnemma · 2019 [cited by examiner]
US 20190079659A1 · Adenwala · 2019 [cited by applicant]
US 20190132709A1 · Graefe · 2019 [cited by applicant]
US 20200079382A1 · Boulton · 2020 [cited by examiner]
US 20200236120A1 · Monteil · 2020 [cited by examiner]
US 20200256681A1 · Kim · 2020 [cited by applicant]
US 20210034632A1 · Meyer · 2021 [cited by applicant]
US 20210067369A1 · Wiesenberg · 2021 [cited by applicant]
US 20210374598A1 · Ben-Ezra · 2021 [cited by examiner]
US 20220026919A1 · Micks · 2022 [cited by applicant]
US 20220161815A1 · Van Beek · 2022 [cited by examiner]
US 20220194415A1 · Liu · 2022 [cited by applicant]
US 20230039738A1 · Beaurepaire · 2023 [cited by applicant]
US 20230083598A1 · Daisuke · 2023 [cited by applicant]
US 20230083625A1 · Ucar · 2023 [cited by applicant]
US 20230154323A1 · Yamala · 2023 [cited by applicant]
US 20230159025A1 · Tummala · 2023 [cited by applicant]
US 20230162597A1 · Tummala · 2023 [cited by applicant]
US 20230204378A1 · Fowe · 2023 [cited by examiner]
US 20230267782A1 · Ucar · 2023 [cited by applicant]
US 20230278585A1 · Hammoud · 2023 [cited by examiner]
US 20230386340A1 · Takeyasu · 2023 [cited by applicant]
US 20240046783A1 · Das · 2024 [cited by applicant]
US 20240046791A1 · Das · 2024 [cited by applicant]
US 20240062533A1 · Huang · 2024 [cited by applicant]
US 20240092382A1 · Sabatini · 2024 [cited by examiner]
US 20240101128A1 · Bradley · 2024 [cited by applicant]
US 20240112077A1 · Agrawal · 2024 [cited by examiner]
US 20240119369A1 · Cyras · 2024 [cited by examiner]
US 20240166240A1 · Lu · 2024 [cited by examiner]
US 20240220493A1 · Gisby · 2024 [cited by applicant]
US 20240265021A1 · Brown · 2024 [cited by applicant]
CA 3206575 · 2022 [cited by applicant]
CN 203149847U · 2013 [cited by applicant]
CN 105897868A · 2016 [cited by applicant]
WO 2013033098A1 · 2013 [cited by applicant]
WO 2018145786A1 · 2018 [cited by applicant]
WO 2022242842 · 2022 [cited by applicant]
Jin et al., “Advanced Estimation Techniques for Vehicle System Dynamic State: A Survey,” Sensors (Basel), 19(19):4289, Oct. 3, 2019 (https://doi.org/10.3390/s19194289). [cited by applicant]
Wu et al., “Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimization,” Journal of Electronic Science and Technology, 17(1):26-40, Mar. 2019 (https://doi.org/10.11989/JEST.1674-862X.80904120… [cited by applicant]
Ucar et al., “Vehicular Knowledge Networking and Application to Risk Reasoning,” 21st International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (Mobihoc 202… [cited by applicant]
Ucar et al., “Vehicular Knowledge Networking and Mobility-Aware Smart Knowledge Placement,” 2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC), Jan. 2022, 6 pages (https://doi.org/10.1109/CCNC4… [cited by applicant]
Ucar et al., “Driver Support in Confusion Zones,” 6 pages. [cited by applicant]
Madrid et al., “Matrix Profile XX: Finding and Visualizing Time Series Motifs of All Lengths using the Matrix Profile,” 2019 IEEE International Conference on Big Knowledge (ICBK), Nov. 2019, pp. 175-182 (https://doi.org… [cited by applicant]
Mercer et al., “Introducing the Contrast Profile: A Novel Time Series Primitive that Allows Real World Classification,” Data Mining and Knowledge Discovery (DMKD 2022), 36:877-915, Mar. 17, 2022 (https://doi.org/10.1007… [cited by applicant]
Ucar et al., “Risk Avoidance by Vehicular Knowledge Networking,” 2022 IEEE 95th Vehicular Technology Conference (VTC2022-Spring), Jun. 2022, 5 pages (https://doi.org/10.1109/VTC2022-Spring54318.2022.9861035). [cited by applicant]
Vatanparvar et al., “Extended Range Electric Vehicle With Driving Behavior Estimation in Energy Management,” IEEE Transactions on Smart Grid, 10(3):2959-2968, May 2019 (https://doi.org/10.1109/TSG.2018.2815689). [cited by applicant]
Deveaux et al., “Role of Context in Determining Transfer of Risk Knowledge in Roundabouts,” 2022 Transportation Research Part C: Emerging Technologies, Dec. 10, 2021, 40 pages (https://www.eurecom.fr/publication/6759). [cited by applicant]
Betz, “Development of an Explicit Context Data Model for Dynamic Risk Assessment of Autonomous Vehicles,” Master Thesis, Technical University of Kaiserslautern, Department of Computer Science, Nov. 29, 2019, 87 pages (h… [cited by applicant]
Kulkarni et al., “Model and Machine Learning based Caching and Routing Algorithms for Cache-enabled Networks,” Apr. 14, 2020, 7 pages (https://doi.org/10.48550/arXiv.2004.06787). [cited by applicant]
Deveaux et al., “A Knowledge Networking Approach for AI-driven Roundabout Risk Assessment,” 17th Wireless On-Demand Network Systems and Services Conference (WONS), Mar. 30, 2022, 8 pages (https://doi.org/10.23919/WONS54… [cited by applicant]