Vehicle path planning

Patent metadata

Field	Value
Publication number	US-11465617-B2
Application number	US-201916687956-A
Country	US
Kind code	B2
Filing date	Nov 19, 2019
Priority date	Nov 19, 2019
Publication date	Oct 11, 2022
Grant date	Oct 11, 2022

Abstract

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine optimal vehicle actions based on a modified version of a Nash equilibrium solution to a multiple agent game, wherein the Nash equilibrium solution is modified by performing an adaptive grid search optimization technique based on calculating rewards and penalties for the agents to determine optimal vehicle actions, wherein the agents include one or more of autonomous vehicles, non-autonomous vehicles, stationary objects, and non-stationary objects including pedestrians and wherein the rewards and the penalties for the agents are determined by simulating behavior of the agents to determine possible future states for the agents to determine the optimal vehicle actions. The instructions can include further instructions to determine a vehicle path based on the optimal vehicle actions and download the vehicle path to the vehicle.

First claim

The invention claimed is:

1. A system, comprising an infrastructure computer and a vehicle computer, the infrastructure computer including a first processor, and a first memory; the vehicle computer including a second processor and a second memory,
the first memory of the infrastructure computer including first instructions executable by the first processor to:
determine optimal vehicle actions based on a modified version of a Nash equilibrium solution to a multiple agent game, wherein the Nash equilibrium solution is modified by performing an adaptive grid search optimization technique based on calculating rewards and penalties for the agents to determine optimal vehicle actions, wherein the agents include one or more of autonomous vehicles, non-autonomous vehicles, stationary objects, and non-stationary objects including pedestrians and wherein the rewards and the penalties for the agents are determined by simulating behavior of the agents to determine possible future states for the agents to determine the optimal vehicle actions;
determine a vehicle path for a vehicle based on the optimal vehicle actions;
download the vehicle path to the vehicle; and
the second memory of the vehicle computer including second instructions executable by the second processor to operate the vehicle on the vehicle path by controlling one or more of vehicle powertrain, vehicle steering, or vehicle brakes.

2. The system of claim 1 , wherein simulating the behavior of the multiple agents to determine one or more estimated states for the agents is based on determining one or more of each of agents' locations, agents' speeds, agents' headings and a plurality of possible paths for each agent.

3. The system of claim 1 , the first instructions including further instructions to determine the optimal vehicle actions by evaluating a utility function including the rewards and the penalties for each of the agents.

4. The system of claim 3 , wherein the utility function for actions of the agents is based on determining estimated states of the stationary and the non-stationary objects determined at time steps t included within a time horizon h and is calculated based on a weighted sum of component utility functions.

5. The system of claim 4 , wherein the utility function includes determining the rewards and the penalties for each of the actions of the agents based on estimated states of the stationary and the non-stationary objects at future time steps t included within the time horizon h.

6. The system of claim 1 , wherein the rewards are based on one or more of moving forward at desired speeds and the penalties are based on deviating from smooth vehicle operation, wherein the smooth vehicle operation also includes limits on agent acceleration, agent steering and agent braking.

7. The system of claim 1 , wherein the penalties are based on one or more of lane departure, out of roadway departure, collisions with the stationary objects, and collisions with the non-stationary objects.

8. The system of claim 1 , the first instructions including further instructions to calculate the rewards and the penalties based on sensor data acquired from sensors included in a traffic infrastructure system arranged to observe the multiple agents.

9. The system of claim 1 , the instructions including further instructions to operate the vehicle along the vehicle path by controlling vehicle powertrain, vehicle steering and vehicle brakes at a frequency of at least 5 Hz.

10. A method, comprising:
determining optimal vehicle actions based on a modified version of a Nash equilibrium solution to a multiple agent game, wherein the Nash equilibrium solution is modified by performing an adaptive grid search optimization technique based on calculating rewards and penalties for the agents to determine optimal vehicle actions, wherein the agents include one or more of autonomous vehicles, non-autonomous vehicles, stationary objects, and non-stationary objects including pedestrians and wherein the rewards and the penalties for the agents are determined by simulating behavior of the agents to determine possible future states for the agents to determine the optimal vehicle actions;
determining a vehicle path based on the optimal vehicle actions;
downloading the vehicle path to a vehicle; and
operating the vehicle on the vehicle path by controlling one or more of vehicle powertrain, vehicle steering, or vehicle brakes.

11. The method of claim 10 , wherein determining one or more future states for the agents to determine the optimal vehicle actions is performed using a computing device in the vehicle.

12. The method of claim 10 , wherein simulating the behavior of the agents to determine one or more estimated states for the agents is based on determining one or more of each of agents' locations, agents' speeds, agents' headings and a plurality of possible paths for each agent.

13. The method of claim 10 , further comprising determining the optimal vehicle actions by evaluating a utility function including the rewards and the penalties for each of the agents.

14. The method of claim 13 , wherein the utility function for actions of the multiple agents is based on determining estimated states of the stationary and the non-stationary objects determined at time steps t included within a time horizon h and is calculated based on a weighted sum of component utility functions.

15. The method of claim 14 , wherein the utility function includes determining the rewards and the penalties for each of the actions of the agents based on estimated states of the stationary and the non-stationary objects at future time steps t included within the time horizon h.

16. A computer for a vehicle, comprising a processor, and a memory, the memory including instructions executable by the processor to:
determine optimal vehicle actions based on a modified version of a Nash equilibrium solution to a multiple agent game, wherein the Nash equilibrium solution is modified by performing an adaptive grid search optimization technique based on calculating rewards and penalties for the agents to determine optimal vehicle actions, wherein the agents include one or more of autonomous vehicles, non-autonomous vehicles, stationary objects, and non-stationary objects including pedestrians and wherein the rewards and the penalties for the agents are determined by simulating behavior of the agents to determine possible future states for the agents to determine the optimal vehicle actions;
determine a vehicle path for the vehicle based on the optimal vehicle actions; and
operate the vehicle on the vehicle path by controlling one or more of vehicle powertrain, vehicle steering, or vehicle brakes.

17. The computer of claim 16 , wherein simulating the behavior of the agents to determine one or more estimated states for the agents is based on determining one or more of each of agents' locations, agents' speeds, agents' headings and a plurality of possible paths for each agent.

18. The computer of claim 16 , the instructions further including instructions to determine the optimal vehicle actions by evaluating a utility function including the rewards and the penalties for each of the agents.

19. The computer of claim 18 , wherein the utility function for actions of the multiple agents is based on determining estimated states of the stationary and the non-stationary objects determined at time steps t included within a time horizon h and is calculated based on a weighted sum of component utility functions.

20. The computer of claim 19 ,

Assignees

• Ford Global Tech Llc

Inventors

• Xu Xunnong
• Guo Wen
• Dai Qi
• Huang Suzhou
• Filev Dimitar Petrov

Classifications

• G08G1/0112 Primary

  from the vehicle, e.g. floating car data [FCD] · CPC title

• B60W2556/45

  External transmission of data to or from the vehicle · CPC title

• B60W10/06

  including control of combustion engines · CPC title

• G08G1/096811

  where the route is computed offboard · CPC title

• B60W2710/06

  Combustion engines, Gas turbines · CPC title