Systems and methods for dynamic predictive control of autonomous vehicles

1. An in-vehicle control system for a semi-truck, comprising:

a processor; and

a computer-readable memory in communication with the processor and having stored thereon computer-executable instructions to cause the processor to at least:

receive a desired trajectory for autonomously driving the semi-truck in a forward direction and a vehicle status of the semi-truck,

update a dynamic model of the semi-truck based on the desired trajectory and the vehicle status, wherein the dynamic model is configured to predict movement of the semi-truck in response to a potential control command during autonomous driving of the semi-truck in traffic,

determine at least one quadratic program problem based on the updated dynamic model,

generate at least one control command for controlling movement of the semi-truck in the forward direction by solving the at least one quadratic program problem, and

output the at least one control command for the autonomous driving of the semi-truck in the forward direction along the desired trajectory.

2. The system of claim 1 , wherein the memory further has stored thereon computer-executable instructions to cause the processor to:

update the dynamic model using small angle error assumptions.

3. The system of claim 1 , wherein the dynamic model comprises a lateral dynamics model and a longitudinal kinematic model.

4. The system of claim 3 , wherein the memory further has stored thereon computer-executable instructions to cause the processor to:

determine a first quadratic program problem of the at least one quadratic program problem based on the lateral dynamics model, and

determine a second quadratic program problem of the at least one quadratic program problem based on the longitudinal kinematic model.

5. The system of claim 4 , wherein the memory further has stored thereon computer-executable instructions to cause the processor to:

generate a steering wheel command for controlling a steering wheel position of the semi-truck by solving the first quadratic program problem using an adaptive controller, and

generate a pedal command for controlling an acceleration pedal and/or brake pedal position of the semi-truck by solving the second quadratic program problem using a proportional integral derivative controller.

6. The system of claim 1 , wherein the memory further has stored thereon computer-executable instructions to cause the processor to:

determine a solution to the at least one quadratic program problem, and

generate the at least one control command by smoothing the solution to the at least one quadratic program problem over time.

7. The system of claim 1 , wherein the desired trajectory defines a plurality of waypoints and a speed profile for the semi-truck.

8. The system of claim 1 , wherein the memory further has stored thereon computer-executable instructions to cause the processor to:

solve the at least one quadratic program problem by finding a maximum or minimum solution.

9. The system of claim 1 , wherein determining the dynamic model is based on physical properties of the semi-truck, including at least one of: a mass, a moment of inertia, a trailer angle, a cornering stiffness, and an articulation between a tractor and a trailer of the semi-truck.

10. A semi-truck, comprising:

the in-vehicle control system of claim 1 ; and

one or more control mechanisms configured to control movement of the semi-truck,

wherein the memory further has stored thereon computer-executable instructions to cause the processor to output the at least one control command to the one or more control mechanisms.

11. The system of claim 1 , wherein the dynamic model is further configured to predict the movement of the semi-truck in response to the potential control command at least in part based on modelling a physical response of the semi-truck to the potential control command.

12. A non-transitory computer readable storage medium having stored thereon instructions that, when executed, cause at least one computing device to at least:

receive a desired trajectory for autonomously driving a semi-truck in a forward direction and a vehicle status of the semi-truck,

determine a dynamic model of the semi-truck based on the desired trajectory and the vehicle status, wherein the dynamic model is configured to predict movement of the semi-truck in response to a potential control command during autonomous driving of the semi-truck in traffic,

determine at least one quadratic program problem based on the dynamic model,

generate at least one control command for controlling movement of the semi-truck in the forward direction by solving the at least one quadratic program problem, and

output the at least one control command for the autonomous driving of the semi-truck in the forward direction along the desired trajectory.

13. The non-transitory computer readable storage medium of claim 12 , wherein the dynamic model comprises a lateral dynamics model and a longitudinal kinematic model.

14. The non-transitory computer readable storage medium of claim 13 , further having stored thereon instructions that, when executed, cause at least one computing device to:

determine a first quadratic program problem of the at least one quadratic program problem based on the lateral dynamics model, and

determine a second quadratic program problem of the at least one quadratic program problem based on the longitudinal kinematic model.

15. The non-transitory computer readable storage medium of claim 14 , further having stored thereon instructions that, when executed, cause at least one computing device to:

generate a steering wheel command for controlling a steering wheel position of the semi-truck by solving the first quadratic program problem using an adaptive controller, and

generate a pedal command for controlling an acceleration pedal and/or brake pedal position of the semi-truck by solving the second quadratic program problem using a proportional integral derivative controller.

16. The non-transitory computer readable storage medium of claim 12 , wherein the dynamic model comprises a non-linear dynamic model, the non-transitory computer readable storage medium further having stored thereon instructions that, when executed, cause at least one computing device to:

derive a linear system model from the non-linear dynamic model using small angle error assumptions.

17. A method for controlling movement of a semi-truck, comprising:

receiving a desired trajectory for autonomously driving the semi-truck in a forward direction and a vehicle status of a semi-truck,

determining a dynamic model of the semi-truck based on the desired trajectory and the vehicle status, wherein the dynamic model is configured to predict movement of the semi-truck in response to a potential control command during autonomous driving of the semi-truck in traffic,

determining at least one quadratic program problem based on the dynamic model,

generating at least one control command for controlling movement of the semi-truck in the forward direction by solving the at least one quadratic program problem, and

outputting the at least one control command for the autonomous driving of the semi-truck in the forward direction along the desired trajectory.

18. The method of claim 17 , wherein the dynamic model comprises a lateral dynamics model and a longitudinal kinematic model.

19. The method of claim 18 , further comprising:

determining a first quadratic program problem of the at least one quadratic program problem based on the lateral dynamics model, and

determining a second quadratic program problem of the at least one quadratic program problem based on the longitudinal kinematic model.

20. The method of claim 17 , wherein the quadratic program problem is configured to reduce an error between the desired trajectory and the predicted movement of the semi-truck.