Simulated vehicle position errors in driving simulations

Patent metadata

Field	Value
Publication number	US-12415510-B1
Application number	US-202217977644-A
Country	US
Kind code	B1
Filing date	Oct 31, 2022
Priority date	Oct 31, 2022
Publication date	Sep 16, 2025
Grant date	Sep 16, 2025

Abstract

Techniques are described herein for determining simulated vehicle positional errors and correlating the positional errors with vehicle features. Such techniques may include receiving log data comprising trajectories and position data for a real vehicle, and executing a log-based simulated vehicle based on the log data. A simulated vehicle may be controlled to follow a simulation trajectory in a simulated environment based on the trajectory of the real vehicle. A simulation system may determine a difference between the positions of the simulated vehicle and corresponding positions of the real vehicle in the real environment. The techniques may further include determining a vehicle state features correlated to the lateral and/or longitudinal position errors of the simulated vehicle, and determining, based on the vehicle state features, position error distributions and/or models that can be used to control subsequent driving simulations.

First claim

The invention claimed is:

1. A system comprising:
one or more processors; and
non-transitory computer-readable media storing instructions that when executed by the one or more processors, cause the system to perform operations comprising:
receiving log data associated with an operation of a vehicle in a physical environment, wherein the log data includes a trajectory associated with the vehicle and a first position of the vehicle at a first time in the physical environment;
executing a driving simulation, wherein executing the driving simulation comprises controlling a simulated vehicle in a simulated environment to follow the trajectory associated with the vehicle in the physical environment;
receiving simulation data associated with the driving simulation, wherein the simulation data includes a second position of the simulated vehicle in the simulated environment at a second time corresponding to the first time in the physical environment;
determining a lateral position error associated with the driving simulation, wherein the lateral position error represents a lateral position difference between the first position of the vehicle in the physical environment and the second position of the simulated vehicle in the simulated environment;
determining a longitudinal position error associated with the driving simulation, wherein the longitudinal position error represents a longitudinal position difference between the first position of the vehicle in the physical environment and the second position of the simulated vehicle in the simulated environment;
determining a modified safety buffer associated with a second simulated vehicle in a second driving simulation, based at least in part on the lateral position error and the longitudinal position error; and
controlling an execution of the second driving simulation based at least in part on the modified safety buffer.

2. The system of claim 1 , wherein determining the lateral position error associated with the driving simulation comprises:
determining, based at least in part on the simulation data, the second position of the simulated vehicle in the simulated environment, wherein the second position is longitudinally aligned with the first position of the vehicle in the physical environment; and
determining a lateral distance between the first position and the second position.

3. The system of claim 1 , wherein determining the longitudinal position error associated with the driving simulation comprises:
determining a first velocity difference between the vehicle at the first time in the physical environment, and the simulated vehicle at the second time in the simulated environment;
determining a second velocity difference between the vehicle at a third time in the physical environment, and the simulated vehicle at a fourth time in the simulated environment; and
computing a velocity difference integral between the vehicle and the simulated vehicle, based at least in part on the first velocity difference and the second velocity difference.

4. The system of claim 3 , wherein determining the longitudinal position error associated with the driving simulation further comprises:
determining, based at least in part on the log data, a stopping time and an associated stopping position of the vehicle in the physical environment;
determining a simulation position of the simulated vehicle in the simulated environment, at a simulation time associated with the stopping time;
determining a longitudinal distance between the stopping position of the vehicle and the simulation position of the simulated vehicle; and
subtracting the longitudinal distance from the velocity difference integral.

5. The system of claim 1 , the operations further comprising:
determining, based at least in part on at least one of the lateral position error or the longitudinal position error, a position error distribution associated with the driving simulation; and
determining, based at least in part on the log data, a vehicle feature of the vehicle associated with the position error distribution.

6. The system of claim 5 , wherein controlling the execution of the second driving simulation comprises:
determining a simulated vehicle feature associated with the second simulated vehicle; and
determining a modified safety buffer associated with the second simulated vehicle, based at least in part on the simulated vehicle feature and the position error distribution.

7. A method comprising:
receiving log data including associated with an operation of a vehicle in a physical environment, wherein the log data includes a trajectory associated with the vehicle and a first position of the vehicle at a first time in the physical environment;
executing a driving simulation, wherein executing the driving simulation comprises controlling a simulated vehicle in a simulated environment, based at least in part on the trajectory associated with the vehicle;
receiving simulation data associated with the driving simulation, wherein the simulation data includes a second position of the simulated vehicle in the simulated environment at a second time corresponding to the first time in the physical environment;
determining a position error associated with the driving simulation, wherein the position error represents a position difference between the first position of the vehicle in the physical environment and the second position of the simulated vehicle in the simulated environment;
determining, based at least in part on the position error, a safety buffer associated with a second simulated vehicle in a second driving simulation; and
controlling an execution of the second driving simulation, based at least in part on the safety buffer.

8. The method of claim 7 , wherein executing the driving simulation comprises:
determining, based at least in part on the log data, the first position as a spatially closest vehicle position of the vehicle to the second position of the simulated vehicle;
determining, as the trajectory, a trajectory of the vehicle associated with the spatially closest vehicle position; and
controlling the simulated vehicle, at the second time, based at least in part on the trajectory of the vehicle associated with the spatially closest vehicle position.

9. The method of claim 7 , wherein determining the position error associated with the driving simulation comprises:
determining, based at least in part on the simulation data, the second position of the simulated vehicle in the simulated environment, wherein the second position is longitudinally aligned with the first position of the vehicle in the physical environment; and
determining a lateral distance between the first position and the second position.

10. The method of claim 7 , wherein determining the position error associated with the driving simulation comprises:
determining a first velocity difference between the vehicle at the first time in the physical environment, and the simulated vehicle at the second time in the simulated environment;
determining a second velocity difference between the vehicle at a third time in the physical environment, and the simulated vehicle at a fourth time in the simulated environment; and
computing a velocity difference integral between the vehicle and the simulated vehicle, based at least in part on the first velocity difference and the second velocity difference.

11. The method of claim 10 , wherein determining the position error associated with the driving simulation further comprises:
determining, based at least in part on the log data, a stopping time and an associated stopping position of the vehicle in the physical environment;
determining a simulation position

Assignees

• Zoox Inc

Inventors

• Funke Joseph
• Egbert Joshua Dean
• Kabirzadeh Rasoul
• Laurense Vincent Andreas
• Tamjidi Amirhossein
• Thalman Jacob Patrick
• Zlotnik David Evan

Classifications

• G06F30/20 Primary

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• B60W2520/105

  Longitudinal acceleration · CPC title

• B60W2520/125

  Lateral acceleration · CPC title

• B60W2554/4041

  Position · CPC title

• B60W40/105

  Speed · CPC title