IP Library › Granted Patent US 12,333,456
Granted Patent B2
US 12,333,456 · App. 17/848,723 · Granted Jun 17, 2025

Decentralized parking fulfillment service

Inventors: Rohit Gupta (Mountain View, CA); Nejib Ammar (Mountain View, CA); Prashant Tiwari (Mountain View, CA)
G06Q10/047G06Q2240/00H04W4/40
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 12,333,456
App. No.
17/848,723
Granted
Jun 17, 2025
Kind
B2
Abstract

In some implementations, a method for providing a decentralized parking fulfillment service may include executing, by a first processor of a connected computing device, a first artificial intelligence network. In addition, the decentralized parking fulfillment service may include executing, by a second processor of a connected vehicle, a second artificial intelligence network. The decentralized parking fulfillment service may include providing the decentralized parking fulfillment service including solving, by the first artificial intelligence network and the second artificial intelligence network, a function that determines a parking space for the connected vehicle. In some implementations, a decentralized parking fulfillment system for providing the decentralized parking fulfillment system includes a parking lot agent stored in a first non-transitory memory of the connected computing device and a vehicle parking agent stored in a second non-transitory memory of the connected vehicle.

Claims (39)

1. A method for providing a decentralized parking fulfillment service by a decentralized parking fulfillment system, the method comprising:

executing, by a first processor of a connected computing device included in the decentralized parking fulfillment system, a first artificial intelligence network whose execution optimizes a function to solve for a first set of first personalization elements that improve an operation of a parking lot;

executing, by a second processor of a connected vehicle included in the decentralized parking fulfillment system, a second artificial intelligence network whose execution optimizes the function to solve for a second set of personalization elements that benefit a driver of the connected vehicle;

providing the decentralized parking fulfillment service including solving, by the first artificial intelligence network and the second artificial intelligence network, the function whose solution outputs a parking space for the connected vehicle and wherein the connected computing device and the connected vehicle each store separate instances of the function and output digital data to one another and the first artificial intelligence and the second artificial intelligence communicate to one another their progress solving the function so that the outputted parking space is optimized to the first artificial intelligence and the second artificial intelligence to benefit the driver of the connected vehicle and the operation of the parking lot; and

autonomously navigating the connected vehicle to the parking space by providing the digital data to an autonomous driving system of the connected vehicle, wherein the autonomous driving system drives the connected vehicle to the parking space based on the digital data.

2. The method of claim 1 , wherein the connected computing device includes an edge server.

3. The method of claim 1 , wherein the computing device includes a roadside unit.

4. The method of claim 1 , wherein one or more of the first intelligence network and the second intelligence network includes a neural network.

5. The method of claim 1 , wherein the function includes a cost function.

6. The method of claim 1 , further comprising providing a notification to the connected vehicle describing the parking space.

7. The method of claim 1 , wherein the first artificial intelligence network is included in a parking lot agent that is operable to solve the function based on a first set of parameters prioritized by an operator of a parking lot that includes the parking space.

8. The method of claim 1 , wherein the first artificial intelligence network is stored in a first non-transitory memory of the connected computing device.

9. The method of claim 1 , wherein the second artificial intelligence network is included in a vehicle agent that is operable to solve the function based on a second set of parameters prioritized by a driver of the connected vehicle.

10. The method of claim 1 , wherein the second artificial intelligence network is stored in a second non-transitory memory of the connected vehicle.

11. The method of claim 1 , further comprising the connected computer device and the connected vehicle wireless communicating with one another via wireless communication to solve the function.

12. A non-transitory computer program product stored across a connected computing device and an onboard unit of a connected vehicle that form a decentralized parking fulfillment system, the computer program product including code and routines that are operable, when executed by the onboard unit, to cause a processor of the connected computing device and the onboard unit to execute routines including:

executing, by the processor included in the decentralized parking fulfillment system, a first artificial intelligence network whose execution optimizes a function to solve for a first set of first personalization elements that improve an operation of a parking lot;

executing, by the onboard unit included in the decentralized parking fulfillment system, a second artificial intelligence network whose execution optimizes the function to solve for a second set of personalization elements that benefit a driver of the connected vehicle;

solving, by the first artificial intelligence network and the second artificial intelligence network, the function whose solution outputs a parking space for the connected vehicle and wherein the connected computing device and the connected vehicle each store separate instances of the function and output digital data to one another and the first artificial intelligence and the second artificial intelligence communicate to one another their progress solving the function so that the outputted parking space is optimized to the first artificial intelligence and the second artificial intelligence to benefit the driver of the connected vehicle and the operation of the parking lot;

providing a notification to the connected vehicle describing the parking space responsive to solving the function; and

autonomously navigating the connected vehicle to the parking space by providing the digital data to an autonomous driving system of the connected vehicle, wherein the autonomous driving system drives the connected vehicle to the parking space based on the digital data.

13. The non-transitory computer program product of claim 12 , wherein the connected computing device includes an edge server.

14. The non-transitory computer program product of claim 12 , wherein the computing device includes a roadside unit.

15. The non-transitory computer program product of claim 12 , wherein one or more of the first intelligence network and the second intelligence network includes a neural network.

16. The non-transitory computer program product of claim 12 , wherein the function includes a cost function.

17. The non-transitory computer program product of claim 12 , wherein the notification is provided via an interface of the connected vehicle to a driver of the connected vehicle.

18. The non-transitory computer program product of claim 12 , wherein the first artificial intelligence network is included in a parking lot agent that is operable to solve the function based on a first set of parameters prioritized by an operator of a parking lot that includes the parking space.

19. The non-transitory computer program product of claim 12 , wherein the second artificial intelligence network is included in a vehicle agent that is operable to solve the function based on a second set of parameters prioritized by a driver of the connected vehicle.

20. A system for providing a decentralized parking fulfillment service by a decentralized parking fulfillment system, the system comprising:

a first processor of a connected computing device communicatively coupled a first communication unit and a first non-transitory memory, wherein the connected computing device is included in the decentralized parking fulfillment system;

a second processor of a connected vehicle communicatively coupled to a second communication unit and a second non-transitory memory, wherein the connected vehicle is included in the decentralized parking fulfillment system;

wherein the first processor is operable to retrieve first computer-executable code from the first non-transitory memory and execute the first computer-executable code;

wherein the second processor is operable to retrieve second computer-executable code from the second non-transitory memory and execute second computer-executable code;

wherein the first processor and the second processor are operable to wirelessly communicate with one another during the execution of the first computer-executable code and the second computer-executable code using the first communication unit and the second communication unit so that the first processor and the second processor are communicatively coupled to one another;

wherein execution of the first computer-executable code and the second computer-executable code is operable to cause the first processor and the second processor to execute steps including:

executing, by the first processor, a first artificial intelligence network whose execution optimizes a function to solve for a first set of first personalization elements that improve an operation of a parking lot;

executing, by a second processor, a second artificial intelligence network whose execution optimizes the function to solve for a second set of personalization elements that benefit a driver of the connected vehicle;

solving, by the first artificial intelligence network and the second artificial intelligence network, a function whose solution outputs a parking space for the connected vehicle and wherein the connected computing device and the connected vehicle each store separate instances of the function and output digital data to one another and the first artificial intelligence and the second artificial intelligence communicate to one another their progress solving the function so that the outputted parking space is optimized to the first artificial intelligence and the second artificial intelligence to benefit the driver of the connected vehicle and the operation of the parking lot; and

autonomously navigating the connected vehicle to the parking space by providing the digital data to an autonomous driving system of the connected vehicle, wherein the autonomous driving system drives the connected vehicle to the parking space based on the digital data.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 15, 2025
From: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.
To: TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 072260/0551 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 27, 2022
From: GUPTA, ROHIT; TIWARI, PRASHANT; AMMAR, NEJIB
To: TOYOTA JIDOSHA KABUSHIKI KAISHA; TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.
Reel/Frame 060325/0794 →
Continuity (1)
Related Publication 20230419200A1 · Dec 28, 2023
References Cited (19)
US 10755570B1 · Zhou · 2020 [cited by examiner]
US 11287829B2 · Johnston · 2022 [cited by examiner]
US 11425530B2 · Hayes · 2022 [cited by examiner]
US 20190043083A1 · Ornstein · 2019 [cited by examiner]
US 20190088128A1 · Adireddy · 2019 [cited by examiner]
US 20200258386A1 · Lu · 2020 [cited by examiner]
US 20210133603A1 · Zhu et al. · 2021 [cited by applicant]
CN 110525428B · 2020 [cited by applicant]
CN 112068515A · 2020 [cited by applicant]
CN 112419775A · 2021 [cited by applicant]
CN 111645673B · 2021 [cited by applicant]
“Decentralized Hybrid Neural Networks,” by Uri Yerushalmi, Apr. 11, 2018 (Year: 2018). [cited by examiner]
“Improving Parking Availability Information Using Deep Learning Techniques,” by Jamie Arjona, M. Paz Linares, Josep Casanovas-Garcia, and Juan Jose Vazquez, Sep. 18-20, 2019 (Year: 2019). [cited by examiner]
“Deep Learning for decentralized parking lot occupancy detection,” by Giuseppe Amato, Fabio Carrara, Fabrizio Falchi, Claudio Gennaro, Carlo Meghini, and Claudio Vairo, Oct. 29, 2016 (Year: 2016). [cited by examiner]
“Collaborative Autonomous Driving—A survey of Solution Approaches and Future Challenges,” by Sumbal Malik, Manzoor Ahmed Khan, and Hesham El-Sayed, May 29, 2021 (Year: 2021). [cited by examiner]
“Park my Car! Automated Valet Parking with Different Vehicle Automation Levels by V2X Connected Smart Infrastructure,” by Philip Schorner, Marcus Conzelmann, tobias Fleck, Marc Zofka, and J. Marius Zollner, Sep. 19-21, … [cited by examiner]
Khalid, et al., “A Reinforcement Learning based Path Guidance Scheme for Long-range Autonomous Valet Parking in Smart Cities,” https://ieeexplore.ieee.org/document/9306103, Oct. 2020, 7 pages. [cited by applicant]
Nguyen, et al., “Vacant Parking Space Detection based on Task Consistency and Reinforcement Learning,” https://ieeexplore.ieee.org/document/9412152, Jan. 2021, 8 pages. [cited by applicant]
Özelǒglu, et al., “SoC Architecture of Autonomous Parking with RL-based Neural Network Compute Accelerators,” Proceedings of the 2020 Ulusal Yüksek Basar?ml? Hesaplama Konferans?, BA S, ARIM2020 (202), 6 pages. [cited by applicant]