Subjective route comfort modeling and prediction

Patent metadata

Field	Value
Publication number	US-11548518-B2
Application number	US-201916457678-A
Country	US
Kind code	B2
Filing date	Jun 28, 2019
Priority date	Jun 28, 2019
Publication date	Jan 10, 2023
Grant date	Jan 10, 2023

Abstract

In one embodiment, a method by a computing system of a vehicle includes determining an environment of the vehicle. The method includes generating, based on the environment, multiple proposed vehicle actions with associated operational data. The method includes determining a comfort level for each proposed vehicle action by processing the environment and operational data using a model for predicting comfort levels of vehicle actions. The model is trained using records of performed vehicle actions. The record for each performed vehicle action includes environment data, operational data, and a perceived passenger comfort level for the performed vehicle action. The method includes selecting a vehicle action from the proposed vehicle actions based on the determined comfort level. The method includes causing the vehicle to perform the selected vehicle action.

First claim

What is claimed is:

1. A method comprising, by a computing system of a vehicle:
determining an external environment of the vehicle based on data received from external environmental sensors of the vehicle;
generating a plurality of proposed vehicle actions associated with vehicle status data based on the external environment of the vehicle;
determining a respective comfort level for each proposed vehicle action of the plurality of proposed vehicle actions based on the external environment of the vehicle and the vehicle status data using a model; and a perceived passenger comfort level for the performed vehicle action;
in response to determining that a response urgency does not indicate a heightened sensitivity, selecting a vehicle action from the plurality of proposed vehicle actions based on the determined respective comfort level,
wherein the response urgency indicates an urgency for the vehicle in the external environment to perform the vehicle action, and wherein selecting the vehicle action is an estimate of which of the proposed vehicle actions satisfies the comfort level when the response urgency does not indicate the heightened sensitivity;
in response to determining that the response urgency indicates the heightened sensitivity, selecting the vehicle action by bypassing the respective comfort level; and
causing the vehicle to perform the selected vehicle action.

2. The method of claim 1 , wherein the selected vehicle action is selected based further on a ride preference of a passenger of the vehicle.

3. The method of claim 2 , wherein the ride preference is generated using a model for inferring a ride preference based on an identity of the passenger of the vehicle, wherein the model is trained using records of performed vehicle actions.

4. The method of claim 1 , wherein the model is a machine learning model that is trained using records of performed vehicle actions, wherein each of the records for each performed vehicle action comprises external environment data, vehicle status data, and a perceived passenger comfort level for the performed vehicle action.

5. The method of claim 1 , further comprising:
after the selected vehicle action has been performed by the vehicle, receiving an indication of a perceived comfort level for the selected vehicle action from a passenger of the vehicle.

6. The method of claim 1 , wherein records of performed vehicle actions comprise vehicle actions performed by autonomous vehicles, non-autonomous vehicles, or simulated vehicles.

7. The method of claim 4 , wherein the external environment data for a performed vehicle action in records for the performed vehicle actions comprises:
data collected by an external environmental sensor associated with a vehicle that performed the vehicle action at a time associated with the vehicle action;
a representation of the external environment of the vehicle that performed the vehicle action at the time associated with the vehicle action; or
communication data transmitted or received by a communication module of the vehicle that performed the vehicle action or by a vehicle management system at the time associated with the vehicle action.

8. The method of claim 1 , wherein the vehicle status data comprises:
a kinematic property of a vehicle; an occupancy of a vehicle; or a communication status of a vehicle.

9. The method of claim 1 , wherein the model for predicting comfort levels of proposed vehicle actions is retrained by: comparing the determined respective comfort level for one or more of the vehicle actions to a perceived comfort level of records of the vehicle action.

10. The method of claim 1 , wherein selecting the vehicle action from the plurality of proposed vehicle actions based on the determined respective comfort level comprises:
identifying an expected comfort level of a passenger of the vehicle; and
comparing the determined respective comfort level of each proposed vehicle action of the plurality of proposed vehicle actions to the expected comfort level.

11. A system comprising: one or more processors of a computing system of a vehicle and one or more computer-readable non-transitory storage media in communication with the one or more processors, the one or more computer readable non-transitory storage media comprising instructions that, when executed by the one or more processors, are configured to cause the system to perform operations comprising:
determining an external environment of the vehicle based on data received from external environmental sensors of the vehicle;
generating, a plurality of proposed vehicle actions associated with vehicle status data;
determining a respective comfort level for each proposed vehicle action of the plurality of proposed vehicle actions based on the external environment of the vehicle and the vehicle status data using a model;
in response to determining that a response urgency does not indicate a heightened sensitivity, selecting a vehicle action from the plurality of proposed vehicle actions based on the determined respective comfort level,
wherein the response urgency indicates an urgency for the vehicle in the external environment to perform the vehicle action, and wherein selecting the vehicle action is an estimate of which of the proposed vehicle actions satisfies the comfort level when the response urgency does not indicate the heightened sensitivity;
in response to determining that the response urgency indicates the heightened sensitivity, selecting the vehicle action by bypassing the respective comfort level; and
causing the vehicle to perform the selected vehicle action.

12. The system of claim 11 , wherein the selected vehicle action is selected based further on a ride preference of a passenger of the vehicle.

13. The system of claim 12 , wherein the ride preference is generated using a model for inferring a ride preference based on an identity of the passenger of the vehicle, wherein the model is trained using records of performed vehicle actions.

14. The system of claim 11 , wherein the model is a machine learning model that is trained using records of performed vehicle actions, wherein each of the records for each performed vehicle action comprises external environment data, vehicle status data, and a perceived passenger comfort level for the performed vehicle action.

15. The system of claim 11 , wherein the instructions are further configured, when executed by the one or more processors, to cause the system to perform further operations comprising:
after the selected vehicle action has been performed by the vehicle, receiving an indication of a perceived comfort level for the selected vehicle action from a passenger of the vehicle.

16. One or more computer-readable non-transitory storage media including instructions that, when executed by one or more processors of a computing system of a vehicle, are configured to cause the one or more processors to perform operations comprising:
determining an external environment of the vehicle based on data received from external environmental sensors of the vehicle;
generating a plurality of proposed vehicle actions associated with vehicle status data;
determining a respective comfort level for each proposed vehicle action of the plurality of the proposed vehicle actions based on the external environment of the vehicle and the vehicle status data using a model;
in response to determining that a response urgency does not indicate a heightened sensitivity, selecting a vehicle action from the plurality of proposed vehicle actions based on the determined respective comfort level, wherein the resp

Assignees

• Woven Planet North America Inc

Inventors

• Omari Sammy
• Praun Emil
• Qureshi Sameer
• Vitelli Matt

Classifications

• B60W2540/043

  Identity of occupants · CPC title

• B60W2540/22

  Psychological state; Stress level or workload · CPC title

• B60W2556/50

  of positioning data, e.g. GPS [Global Positioning System] data · CPC title

• B60W2552/53

  Road markings, e.g. lane marker or crosswalk · CPC title

• B60W50/0098 Primary

  Details of control systems ensuring comfort, safety or stability not otherwise provided for · CPC title