Physical model and machine learning combined method to simulate autonomous vehicle movement

Patent metadata

Field	Value
Publication number	US-10343685-B2
Application number	US-201615278719-A
Country	US
Kind code	B2
Filing date	Sep 28, 2016
Priority date	Sep 28, 2016
Publication date	Jul 9, 2019
Grant date	Jul 9, 2019

Abstract

In one embodiment, a driving scenario is identified for a next movement for an autonomous vehicle, where the driving scenario is represented by a set of one or more predetermined parameters. A first next movement is calculated for the autonomous vehicle using a physical model corresponding to the driving scenario. A sideslip predictive model is applied to the set of predetermined parameters to predict a sideslip of the autonomous vehicle under the driving scenario. A second next movement of the autonomous vehicle is determined based on the first next movement and the predicted sideslip of the autonomous vehicle. The predicted sideslip is utilized to modify the first next movement to compensate the sideslip. Planning and control data is generated for the second next movement and the autonomous vehicle is controlled and driven based on the planning and control data.

First claim

What is claimed is:

1. A computer-implemented method for operating an autonomous vehicle, the method comprising:
identifying a driving scenario of the autonomous vehicle for a next movement, wherein the driving scenario is represented by a set of one or more predetermined parameters;
calculating a first next movement of the autonomous vehicle under the driving scenario using a physical model;
generating planning and control data based on the first next movement, the planning and control data describing a path to drive the autonomous vehicle from a first point to a second point;
applying a sideslip predictive model to the set of predetermined parameters to determine a sideslip of the autonomous vehicle given a set of driving conditions, the sideslip representing a difference between a first position of the autonomous vehicle and a second position of the autonomous vehicle, wherein the first position is an expected position of the autonomous vehicle calculated using the physical model and the set of predetermined parameters, and wherein the second position is a position where the autonomous vehicle actually ends up due to the set of driving conditions;
determining a second next movement of the autonomous vehicle based on the first next movement and the determined sideslip of the autonomous vehicle, including adjusting at least one position within the path between the first point and the second point based on the determined sideslip of the autonomous vehicle;
modifying the planning and control data based on the second next movement; and
controlling and driving the autonomous vehicle from the first point to the second point according to the path based on the modified planning and control data.

2. The method of claim 1 , wherein the sideslip predictive model is one of a plurality of sideslip predictive models that were generated using machine learning based on sideslips and corresponding driving parameters measured and recorded under a plurality of driving scenarios by a plurality of different types of vehicles.

3. The method of claim 1 , wherein determining the second next movement comprises calculating a final position of the autonomous vehicle by adding an original position, a movement of wheels, and the determined sideslip.

4. The method of claim 1 , wherein the determined sideslip is used to correct the first next movement of the autonomous vehicle calculated based on the physical model.

5. The method of claim 1 , wherein the driving scenario includes a scenario of turning of the autonomous vehicle.

6. The method of claim 1 , wherein the predetermined parameters comprise one or more of a road type, a weather condition, a speed of the autonomous vehicle, a target angle of the autonomous vehicle, an acceleration or deceleration of the autonomous vehicle, and a steering angle of the autonomous vehicle.

7. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations of operating an autonomous vehicle, the operations comprising:
identifying a driving scenario of the autonomous vehicle for a next movement, wherein the driving scenario is represented by a set of one or more predetermined parameters;
calculating a first next movement of the autonomous vehicle under the driving scenario using a physical model;
generating planning and control data based on the first next movement, the planning and control data describing a path to drive the autonomous vehicle from a first point to a second point;
applying a sideslip predictive model to the set of predetermined parameters to determine a sideslip of the autonomous vehicle given a set of driving conditions, the sideslip representing a difference between a first position of the autonomous vehicle and a second position of the autonomous vehicle, wherein the first position is an expected position of the autonomous vehicle calculated using the physical model and the sot of predetermined parameters, and wherein the second position is a position where the autonomous vehicle actually ends UP due to the set of driving conditions;
determining a second next movement of the autonomous vehicle based on the first next movement and the determined sideslip of the autonomous vehicle, including adjusting at least one position within the path between the first point and the second point based on the determined sideslip of the autonomous vehicle;
modifying the planning and control data based on the second next movement; and
controlling and driving the autonomous vehicle from the first point to the second point according to the path based on the modified planning and control data.

8. The machine-readable medium of claim 7 , wherein the sideslip predictive model is one of a plurality of sideslip predictive models that were generated using machine learning based on sideslips and corresponding driving parameters measured and recorded under a plurality of driving scenarios by a plurality of different types of vehicles.

9. The machine-readable medium of claim 7 , wherein determining the second next movement comprises calculating a final position of the autonomous vehicle by adding an original position, a movement of wheels, and the determined sideslip.

10. The machine-readable medium of claim 7 , wherein the determined sideslip is used to correct the first next movement of the autonomous vehicle calculated based on the physical model.

11. The machine-readable medium of claim 7 , wherein the driving scenario includes a scenario of turning of the autonomous vehicle.

12. The machine-readable medium of claim 7 , wherein the predetermined parameters comprise one or more of a road type, a weather condition, a speed of the autonomous vehicle, a target angle of the autonomous vehicle, an acceleration or deceleration of the autonomous vehicle, and a steering angle of the autonomous vehicle.

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 of operating an autonomous vehicle, the operations including
identifying a driving scenario of the autonomous vehicle for a next movement, wherein the driving scenario is represented by a set of one or more predetermined parameters,
calculating a first next movement of the autonomous vehicle under the driving scenario using a physical model,
generating planning and control data based on the first next movement, the planning and control data describing a path to drive the autonomous vehicle from a first point to a second point,
applying a sideslip predictive model to the set of predetermined parameters to determine a sideslip of the autonomous vehicle given a set of driving conditions, the sideslip representing a difference between a first position of the autonomous vehicle and a second position of the autonomous vehicle, wherein the first position is an expected position of the autonomous vehicle calculated using the physical model and the set of predetermined parameters, and wherein the second position is a position where the autonomous vehicle actually ends up due to the set of driving conditions;

determining a second next movement of the autonomous vehicle based on the first next movement and the determined sideslip of the autonomous vehicle, including adjusting at least one position within the path between the first point and the second point based on the determined sideslip of the autonomous vehicle,
modifying the planning and control data based on the second next movement, and
controlling and driving the autonomous vehicle from the first point to the second poin

Assignees

• Baidu Usa Llc

Inventors

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

Classifications

• B60W2552/05

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

• B60W2555/20

  Ambient conditions, e.g. wind or rain · CPC title

• B60W2520/10

  Longitudinal speed · CPC title

• B60W50/0097

  Predicting future conditions · CPC title

• B60W2720/20

  Sideslip angle · CPC title