Sideslip compensated control method for autonomous vehicles

Patent metadata

Field	Value
Publication number	US-10809726-B2
Application number	US-201816006814-A
Country	US
Kind code	B2
Filing date	Jun 12, 2018
Priority date	Sep 28, 2016
Publication date	Oct 20, 2020
Grant date	Oct 20, 2020

Abstract

A set of driving scenarios are determined for different types of vehicles. Each driving scenario corresponds to a specific movement of a particular type of autonomous vehicles. For each of the driving scenarios of each type of autonomous vehicles, a set of driving statistics is obtained, including driving parameters used to control and drive the vehicle, a driving condition at the point in time, and a sideslip caused by the driving parameters and the driving condition under the driving scenario. A driving scenario/sideslip mapping table or database is constructed. The scenario/sideslip mapping table includes a number of mapping entries. Each mapping entry maps a particular driving scenario to a sideslip that is calculated based on the driving statistics. The scenario/sideslip mapping table is utilized subsequently to predict the sideslip under the similar driving environment, such that the driving planning and control can be compensated.

First claim

What is claimed is:

1. A computer-implemented method for operating an autonomous vehicle, the method comprising:
determining a first driving scenario based on a next movement of the autonomous vehicle according to a planned route;
searching in a scenario-to-sideslip (scenario/sideslip) mapping table based on the first driving scenario to locate a mapping entry corresponding to a second driving scenario matching the first driving scenario, wherein the scenario/sideslip mapping table includes a plurality of mapping entries, each of the mapping entries mapping a particular driving scenario to a sideslip value representing a sideslip under that particular driving scenario, wherein the sideslip value of each of the mapping entries of the scenario/sideslip mapping table was determined based on driving statistics of a plurality of vehicles driven under a similar driving scenario, and wherein the sideslip of each of the mapping entries of the scenario/sideslip mapping table represents an averaged sideslip of the plurality of vehicles;
generating one or more control commands for the next movement in view of a first sideslip value corresponding to the second driving scenario obtained from the matching entry; and
controlling the autonomous vehicle using the one or more control commands, such that the next movement of the autonomous vehicle is compensated due to sideslip based on the first sideslip value.

2. The method of claim 1 , wherein generating one or more control commands for the next movement in view of a first sideslip value comprises:
calculating a first steering angle based on a speed required the next movement using a predetermined algorithm;
modifying the first steering angle in view of the first sideslip obtained from the located mapping entry and generating a second steering angle; and
generating a steering command to control the autonomous vehicle based on the second steering angle.

3. The method of claim 1 , wherein the next movement comprises one of a left turn, a right turn, or a U-turn.

4. The method of claim 1 , wherein each driving scenario further identifies a type of an autonomous vehicle involved.

5. The method of claim 4 , wherein each driving scenario includes at least one of a type of road or a weather condition.

6. The method of claim 5 , wherein each driving scenario further includes identifying an action to be taken by a vehicle, a speed during the action, or a steering angle during the action.

7. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations for operating an autonomous vehicle, the operations comprising:
determining a first driving scenario based on a next movement of the autonomous vehicle according to a planned route;
searching in a scenario-to-sideslip (scenario/sideslip) mapping table based on the first driving scenario to locate a mapping entry corresponding to a second driving scenario matching the first driving scenario, wherein the scenario/sideslip mapping table includes a plurality of mapping entries, each of the mapping entries mapping a particular driving scenario to a sideslip value representing a sideslip under that particular driving scenario, wherein the sideslip value of each of the mapping entries of the scenario/sideslip mapping table was determined based on driving statistics of a plurality of vehicles driven under a similar driving scenario, and wherein the sideslip of each of the mapping entries of the scenario/sideslip mapping table represents an averaged sideslip of the plurality of vehicles;
generating one or more control commands for the next movement in view of a first sideslip value corresponding to the second driving scenario obtained from the matching entry;
controlling the autonomous vehicle using the one or more control commands, such that the next movement of the autonomous vehicle is compensated due to sideslip based on the first sideslip value.

8. The machine-readable medium of claim 7 , wherein generating one or more control commands for the next movement in view of a first sideslip value comprises:
calculating a first steering angle based on a speed required the next movement using a predetermined algorithm;
modifying the first steering angle in view of the first sideslip obtained from the located mapping entry and generating a second steering angle; and
generating a steering command to control the autonomous vehicle based on the second steering angle.

9. The machine-readable medium of claim 7 , wherein the next movement comprises one of a left turn, a right turn, or a U-turn.

10. The machine-readable medium of claim 7 , wherein each driving scenario further identifies a type of an autonomous vehicle involved.

11. The machine-readable medium of claim 10 , wherein each driving scenario includes at least one of a type of road or a weather condition.

12. The machine-readable medium of claim 11 , wherein each driving scenario further includes identifying an action to be taken by a vehicle, a speed during the action, or a steering angle during the action.

13. A data processing system, comprising:
a processor; and
a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including
determining a first driving scenario based on a next movement of the autonomous vehicle according to a planned route,
searching in a scenario-to-sideslip (scenario/sideslip) mapping table based on the first driving scenario to locate a mapping entry corresponding to a second driving scenario matching the first driving scenario, wherein the scenario/sideslip mapping table includes a plurality of mapping entries, each of the mapping entries mapping a particular driving scenario to a sideslip value representing a sideslip under that particular driving scenario, wherein the sideslip value of each of the mapping entries of the scenario/sideslip mapping table was determined based on driving statistics of a plurality of vehicles driven under a similar driving scenario, and wherein the sideslip of each of the mapping entries of the scenario/sideslip mapping table represents an averaged sideslip of the plurality of vehicles,
generating one or more control commands for the next movement in view of a first sideslip value corresponding to the second driving scenario obtained from the matching entry, and
controlling the autonomous vehicle using the one or more control commands, such that the next movement of the autonomous vehicle is compensated due to sideslip based on the first sideslip value.

14. The system of claim 13 , wherein generating one or more control commands for the next movement in view of a first sideslip value comprises:
calculating a first steering angle based on a speed required the next movement using a predetermined algorithm;
modifying the first steering angle in view of the first sideslip obtained from the located mapping entry and generating a second steering angle; and
generating a steering command to control the autonomous vehicle based on the second steering angle.

15. The system of claim 13 , wherein the next movement comprises one of a left turn, a right turn, or a U-turn.

Assignees

• Baidu Usa Llc

Inventors

• Kong Qi
• Zhu Fan
• Yang Guang
• Wang Jingao

Classifications

• B60W2720/20

  Sideslip angle · CPC title

• B60W2710/207

  Steering angle of wheels · CPC title

• B60W2556/10

  Historical data · CPC title

• B60W2552/05

  Type of road, e.g. motorways, local streets, paved or unpaved roads · CPC title

• B60W2520/20

  Sideslip angle · CPC title