IP Library › Granted Patent US 12,439,431
Granted Patent B2
US 12,439,431 · App. 17/354,045 · Granted Oct 7, 2025

Methods and systems for scheduling mmWave communications using reinforcement learning

Inventors: Hongsheng Lu (San Jose, CA); Chenyuan He (Jiangsu, CN); Bin Cheng (New York, NY); Takayuki Shimizu (Santa Clara, CA)
Assignee: Toyota Motor Engineering & Manufacturing North America, Inc.
H04W72/30G05B13/0265H04W4/40
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 12,439,431
App. No.
17/354,045
Granted
Oct 7, 2025
Kind
B2
Abstract

A controller for scheduling mmWave communication is provided. The controller is programmed to identify a plurality of states, each of the plurality of states indicating status of mmWave communication links among a plurality of nodes, calculate an updated value for each of the plurality of states iteratively based on a value iteration algorithm and a previous value for each of the plurality of states until the updated value for each of the plurality of states converges, and select one of the plurality of states based on the converged values for the plurality of states.

Claims (40)

1. A controller which is configured to:

receive an intent to communicate from one or more of a plurality of nodes;

identify a plurality of states based at least in part on the one or more intents to communicate, each of the plurality of states indicating status of mmWave communication links among the plurality of nodes;

calculate an updated value for each of the plurality of states iteratively based on a value iteration algorithm and a previous value for each of the plurality of states until the updated value for each of the plurality of states converges; and

select one of the plurality of states based on the converged values for the plurality of states, wherein:

the updated value for each of the plurality of states is calculated at least based on a reward value and a transition probability from a first state to a second state; and

the reward value is calculated based on a weight value related to a link to be added or removed and a number of conflicts due to an addition or a removal of the link.

2. The controller of claim 1 , wherein the controller is configured to:

broadcast information about the selected state over a V2X channel.

3. The controller of claim 1 , wherein the updated value for each of the plurality of states is calculated using Bellman equation.

4. The controller of claim 1 , wherein:

each of the mm Wave communication links is associated with a weight parameter; and

the updated value for each of the plurality of states is calculated further based on the weight parameter.

5. The controller of claim 1 , wherein the controller is configured to:

broadcast information about the selected state over a 5.9 GHz V2X channel.

6. The controller of claim 1 , wherein the plurality of nodes include a plurality of connected vehicles.

7. The controller of claim 1 , wherein the plurality of nodes include an edge server.

8. The controller of claim 1 , wherein one or more of the plurality of states include mm Wave communication links that conflict each other.

9. A method comprising:

receiving an intent to communicate from one or more of a plurality of nodes;

identifying a plurality of states based at least in part on the one or more intents to communicate, each of the plurality of states indicating status of mm Wave communication links among the plurality of nodes;

calculating an updated value for each of the plurality of states iteratively based on a value iteration algorithm and a previous value for each of the plurality of states until the updated value for each of the plurality of states converges; and

selecting one of the plurality of states based on the converged values for the plurality of states, wherein:

the updated value for each of the plurality of states is calculated at least based on a reward value and a transition probability from a first state to a second state; and

the reward value is calculated based on a weight value related to a link to be added or removed and a number of conflicts due to an addition or a removal of the link.

10. The method of claim 9 , further comprising:

broadcasting information about the selected state over a V2X channel.

11. The method of claim 9 , wherein the updated value for each of the plurality of states is calculated using Bellman equation.

12. The method of claim 9 , wherein:

each of the mm Wave communication links is associated with a weight parameter; and

the updated value for each of the plurality of states is calculated further based on the weight parameter.

13. A vehicle system comprising:

a controller which is configured to:

receive an intent to communicate from one or more of a plurality of nodes;

identify a plurality of states based at least in part on the one or more intents to communicate, each of the plurality of states indicating status of mmWave communication links among the plurality of nodes;

calculate an updated value for each of the plurality of states iteratively based on a value iteration algorithm and a previous value for each of the plurality of states until the updated value for each of the plurality of states converges;

select one of the plurality of states based on the converged values for the plurality of states; and

broadcast the selected state over a V2X channel, wherein:

the updated value for each of the plurality of states is calculated at least based on a reward value and a transition probability from a first state to a second state; and

the reward value is calculated based on a weight value related to a link to be added or removed and a number of conflicts due to an addition or a removal of the link.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 23, 2025
From: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.
To: TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 072659/0201 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 22, 2021
From: LU, HONGSHENG; HE, CHENYUAN; CHENG, BIN; SHIMIZU, TAKAYUKI
To: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.
Reel/Frame 056616/0274 →
Continuity (1)
Related Publication 20220408408A1 · Dec 22, 2022
References Cited (14)
US 10530451B1 · Bansal et al. · 2020 [cited by applicant]
US 12099357B1 · Ebrahimi Afrouzi · 2024 [cited by examiner]
US 20190238658A1 · Shimizu et al. · 2019 [cited by applicant]
US 20200128597A1 · Shimizu et al. · 2020 [cited by applicant]
US 20200235997A1 · Shimizu et al. · 2020 [cited by applicant]
US 20230090593A1 · Kim · 2023 [cited by examiner]
CN 112224202A · 2021 [cited by applicant]
GB 2577741A · 2020 [cited by examiner]
Sim et al., “An Online Context-Aware Machine Learning Algorithm for 5G mmWave Vehicular Communications,” in IEEE/ACM Transactions on Networking, vol. 26, No. 6, pp. 2487-2500, Dec. 2018 (Year: 2018). [cited by examiner]
Javier Gozalvev, et al., “Heterogeneous V2X Networks for Connected and Automated Vehicles”, IEEE Intelligent Transportation Systems; Universidad Miguel Hernández de Elche (Spain), Accessed Feb. 2021, URL: http://5gsummi… [cited by applicant]
Seungmo Kim, et al., “Reinforcement Learning for Accident Risk-Adaptive V2X Networking”, Virginia Polytechnic Institute and State University, Apr. 6, 2020, URL: https://www.semanticscholar.org/paper/Reinforcement-Learni… [cited by applicant]
B. Coll-Perales, et al., “Sub-6GHZ Assisted MAC for Millimeter Wave Vehicular Communications”, IEEE Communications Magazine, Mar. 2019, vol. 57, No. 3, pp. 125-131, URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&ar… [cited by applicant]
Akihito Taya, et al., “Concurrent Transmission Scheduling for Perceptual Data Sharing in mmWave Vehicular Networks”, IEICE Transactions on Information and Systems, Mar. 2019, vol. E102-D, No. 5. [cited by applicant]
Ioannis Mavromatis, et al., “MmWave System for Future ITS: A MAC-layer Approach for V2X Beam Steering”, Article; 2017 IEEE 86th Vehicular Technology Conference (VTC—Fall), Toronto, ON, May 24, 2017, pp. 1-6, URL: https:… [cited by applicant]