IP Library Granted Patent US 12,164,296
Granted Patent B2
US 12,164,296 · App. 18/364,587 · Granted Dec 10, 2024

Autonomous vehicle simulation system for analyzing motion planners

Inventors: Liu Liu (San Diego, CA); Yuwei Wang (San Diego, CA); Xing Sun (San Diego, CA); Yufei Zhao (San Diego, CA); Wutu Lin (San Diego, CA)
Assignee: TUSIMPLE, INC.
G05D1/0088G05D1/0212G05D1/0287G06F30/15G06F30/20G06F2111/10
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,164,296
App. No.
18/364,587
Granted
Dec 10, 2024
Kind
B2
Abstract

An autonomous vehicle simulation system for analyzing motion planners is disclosed. A particular embodiment includes: receiving map data corresponding to a real world driving environment; obtaining perception data and configuration data including pre-defined parameters and executables defining a specific driving behavior for each of a plurality of simulated dynamic vehicles; generating simulated perception data for each of the plurality of simulated dynamic vehicles based on the map data, the perception data, and the configuration data; receiving vehicle control messages from an autonomous vehicle control system; and simulating the operation and behavior of a real world autonomous vehicle based on the vehicle control messages received from the autonomous vehicle control system.

Claims (47)

1. A vehicle simulation system, comprising:

a processor configured to:

perform a simulation in which simulation data indicative of a movement of a vehicle is generated based on a message received from the vehicle and modeling data of the vehicle,

wherein the message includes a first information with which the vehicle is controlled, and

wherein the modeling data is received from the vehicle and includes one or more characteristics of the vehicle;

collect, during the simulation, vehicle motion data related to a simulated motion of the vehicle;

perform a playback of the vehicle motion data;

receive perception data that indicates a presence, a position, and a velocity for each of a plurality of vehicles in a vicinity of or proximate to the vehicle; and

generate, based on the perception data, a target position, a speed, and a heading for each vehicle from the plurality of vehicles and at specific points in time.

2. The vehicle simulation system of claim 1 , wherein the perception data includes a second information indicative of another presence and another position of an obstacle.

3. The vehicle simulation system of claim 1 , wherein the perception data includes a third information indicative of a location of an available roadway.

4. The vehicle simulation system of claim 1 , wherein the perception data includes a fourth information indicative of traffic or environmental information.

5. The vehicle simulation system of claim 1 , wherein the plurality of vehicles includes a first vehicle and a second vehicle,

wherein a first heading is generated for the first vehicle having a first pre-configured behavior associated with an aggressive driver,

wherein a second heading is generated for the second vehicle having a second pre-configured behavior associated with a conservative driver, and

wherein a probability of the first heading of the first vehicle being associated with a lane change is greater than that of the second heading of the second vehicle.

6. A method comprising:

performing a simulation in which simulation data indicative of a movement of a vehicle is generated based on a message received from the vehicle and modeling data of the vehicle,

wherein the message includes a first information with which the vehicle is controlled, and

wherein the modeling data is received from the vehicle and includes one or more characteristics of the vehicle;

collecting, during the simulation, vehicle motion data related to a simulated motion of the vehicle;

performing a playback of the vehicle motion data;

receiving perception data that indicates a presence, a position, and a velocity for each of a plurality of vehicles in a vicinity of or proximate to the vehicle; and

generating, based on the perception data, a target position, a speed, and a heading for each vehicle from the plurality of vehicles and at specific points in time.

7. The method of claim 5 , wherein the modeling data of the vehicle includes a type of the vehicle.

8. The method of claim 5 , wherein the modeling data of the vehicle includes characteristics of a control system of the vehicle.

9. The method of claim 5 , wherein the modeling data of the vehicle includes engine performance characteristics.

10. The method of claim 6 , further comprising:

collecting, during the simulation, analytics data, vehicle state information, and timing and configuration information.

11. The method of claim 6 , wherein the first information in the message causes the vehicle to traverse a trajectory with an acceleration or a speed that is generated.

12. The method of claim 6 , wherein the movement includes an action or an effect of throttle, brake, or steering applied on the vehicle.

13. The method of claim 6 , wherein the vehicle motion data includes a time sequenced set of map data, the perception data and one or more messages produced by one or more systems in the vehicle.

14. A non-transitory machine-useable storage medium embodying instructions which, when executed by a machine, causes the machine to perform a method, comprising:

performing a simulation in which simulation data indicative of a movement of a vehicle is generated based on a message received from the vehicle and modeling data of the vehicle,

wherein the message includes a first information with which the vehicle is controlled, and

wherein the modeling data is received from the vehicle and includes one or more characteristics of the vehicle;

collecting, during the simulation, vehicle motion data related to a simulated motion of the vehicle;

performing a playback of the vehicle motion data;

receiving perception data that indicates a presence, a position, and a velocity for each of a plurality of vehicles in a vicinity of or proximate to the vehicle; and

generating, based on the perception data, a target position, a speed, and a heading for each vehicle from the plurality of vehicles and at specific points in time.

15. The non-transitory machine-useable storage medium of claim 14 , wherein the modeling data of the vehicle includes a type of the vehicle.

16. The non-transitory machine-useable storage medium of claim 14 , wherein the modeling data of the vehicle includes characteristics of a control system of the vehicle.

17. The non-transitory machine-useable storage medium of claim 14 , wherein the modeling data of the vehicle includes engine performance characteristics.

18. The non-transitory machine-useable storage medium of claim 14 , wherein the method further comprises:

collecting, during the simulation, analytics data, vehicle state information, and timing and configuration information.

19. The non-transitory machine-useable storage medium of claim 14 , wherein the first information in the message causes the vehicle to traverse a trajectory with an acceleration or a speed of the vehicle that is generated.

20. The non-transitory machine-useable storage medium of claim 14 , wherein the perception data includes another information indicative of a location of an available roadway.

Assignments (3)
CHANGE OF NAME Recorded Dec 3, 2025
From: TUSIMPLE, INC.
To: CREATEAI, INC.
Reel/Frame 073832/0485 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 6, 2023
From: LIU, LIU; WANG, YUWEI; SUN, XING; ZHAO, YUFEI; LIN, WUTU
To: TUSIMPLE
Reel/Frame 064820/0834 →
CHANGE OF NAME Recorded Sep 6, 2023
From: TUSIMPLE
To: TUSIMPLE, INC.
Reel/Frame 064820/0892 →
Continuity (3)
Continuation 17126740 · Dec 18, 2020
Continuation 15827452 · Nov 30, 2017
Related Publication 20230376037A1 · Nov 23, 2023