End-to-end perception perturbation modeling system for a vehicle
An end-to-end perception perturbation modeling system for a vehicle includes one or more controllers storing a detection model in memory. The detection model includes a plurality of detection model plots that each indicate a probability value that an object in an environment surrounding the vehicle is detected based on a current weather condition and a distance measured between the vehicle and the object detected in the environment surrounding the vehicle. The one or more controllers execute instructions to receive an input state of the vehicle that is observed during non-inclement weather conditions and indicates one or more vehicle states, the current weather condition, and the distance. The controllers determine a perturbed state of the vehicle observed during the current weather condition.
1. An end-to-end perception perturbation modeling system for a vehicle, the end-to-end perception perturbation modeling system comprises:
one or more controllers storing a detection model in memory, wherein the detection model includes a plurality of detection model plots that each indicate a probability value that an object in an environment surrounding the vehicle is detected based on a current weather condition and a distance measured between the vehicle and the object detected in the environment surrounding the vehicle, and wherein the one or more controllers execute instructions to:
receive an input state of the vehicle, wherein the input state is observed during non-inclement weather conditions and indicates one or more vehicle states, the current weather condition, and the distance;
determine a probability value corresponding to the current weather condition and the distance based on the detection model;
execute a simulation based on the probability value, wherein the simulation determines a probability the object located in the environment is detected based on the current weather condition and the distance, and wherein the simulation is executed by:
drawing a random number;
comparing the random number with the probability value; and
in response to determining the random number is equal to or greater than the probability value, determine the object is detected and the probability is true; and
in response to determining the probability the object located in the environment indicates the object will be detected, determine a perturbed state of the vehicle observed during the current weather condition, wherein the perturbed state of the vehicle indicates the probability that the object located in the environment is detected, and wherein the end-to-end perception perturbation modeling system is integrated with a trajectory prediction system and a final motion planner of an autonomous driving system that execute trajectory prediction and final motion planning of the vehicle based on the probability the object located in the environment is detected.
2. The end-to-end perception perturbation modeling system of claim 1 , wherein the current weather condition indicates an adverse weather condition.
3. The end-to-end perception perturbation modeling system of claim 2 , wherein the adverse weather condition is one of the following: dusk, night, rain, heavy rain, fog, and heavy fog.
4. The end-to-end perception perturbation modeling system of claim 1 , wherein the one or more controllers store a set of vehicle state perturbation models that each correspond to one of the vehicle states in memory.
5. The end-to-end perception perturbation modeling system of claim 4 , wherein each set of vehicle state perturbation models include a plurality of vehicle state perturbation models that each represent a perception error distribution that corresponds to a specific current weather condition and a specific distance measured between the vehicle and the object detected in the environment.
6. The end-to-end perception perturbation modeling system of claim 5 , wherein the one or more controllers execute instructions to:
determine a perception error for each vehicle state during the current weather condition at the distance as indicated by the input state based on the set of vehicle state perturbation models.
7. The end-to-end perception perturbation modeling system of claim 6 , wherein the one or more controllers execute instructions to:
determine a correlation value between two perception errors corresponding to two of the vehicle states at the current weather condition and the distance as indicated by the input state, wherein the correlation value is representative of a functional relationship between two of the vehicle state perturbation models.
8. The end-to-end perception perturbation modeling system of claim 7 , wherein the one or more controllers execute instructions to:
compare the correlation value of the perception errors between the two vehicle states with an expected sensitivity value range, wherein the expected sensitivity value range indicates an expected difference between the perception errors of the two vehicle states; and
in response to determining the correlation value falling within the expected sensitivity value range, determine the perception error between the two vehicle states is valid.
9. The end-to-end perception perturbation modeling system of claim 8 , wherein the one or more controllers execute instructions to:
determine the perturbed state of the vehicle by adding the perception error to each original value of the vehicle state.
10. The end-to-end perception perturbation modeling system of claim 1 , wherein the one or more vehicle states include one or more of the following: speed, a heading angle of the vehicle, and a location of the vehicle.
11. The end-to-end perception perturbation modeling system of claim 1 , wherein the detection model is created based on synthetic data.
12. The end-to-end perception perturbation modeling system of claim 1 , wherein the autonomous driving system is part of one of the following: an automated driving system (ADS) and an advanced driver assistance system (ADAS).
13. A method for determining a perturbed state of a vehicle by an end-to-end perception perturbation modeling system, the method comprising:
receiving, by one or more controllers, an input state of the vehicle, wherein the input state is observed during non-inclement weather conditions and indicates one or more vehicle states, a current weather condition, and a distance measured between the vehicle and an object detected in an environment surrounding the vehicle;
determining a probability value corresponding to the current weather condition and the distance based on a detection model stored in memory of the one or more controllers, wherein the probability value indicates the object in the environment surrounding the vehicle is detected;
executing a simulation based on the probability value, wherein the simulation determines a probability the object located in the environment is detected based on the current weather condition and the distance, and wherein the simulation is executed by:
drawing a random number;
comparing the random number with the probability value; and
in response to determining the random number is equal to or greater than the probability value, determine the object is detected and the probability is true; and
in response to determining the probability the object located in the environment indicates the object will be detected, determining a perturbed state of the vehicle observed during the current weather condition, wherein the perturbed state of the vehicle indicates the probability that the object located in the environment is detected, and wherein the end-to-end perception perturbation modeling system is integrated with a trajectory prediction system and a final motion planner of an autonomous driving system that execute trajectory prediction and final motion planning of the vehicle based on the probability the object located in the environment is detected.
14. The method of claim 13 , further comprising:
determining a perception error for each vehicle state during the current weather condition at the distance as indicated by the input state based on a set of vehicle state perturbation models saved in memory of the one or more controllers, wherein each set of vehicle state perturbation models include a plurality of vehicle state perturbation models that each represent a perception error distribution that corresponds to a specific current weather condition and a specific distance measured between the vehicle and the object detected in the environment.
15. The method of claim 14 , further comprising:
determining a correlation value between two perception errors corresponding to two of the vehicle states at the current weather condition and the distance as indicated by the input state, where the correlation value is representative of a functional relationship between two of the vehicle state perturbation models.
16. The method of claim 15 , further comprising:
comparing the correlation value of the two perception errors between two of the vehicle states with an expected sensitivity value range, wherein the expected sensitivity value range indicates an expected difference between the perception errors of the two vehicle states; and
in response to determining the correlation value falling within the expected sensitivity value range, determining the perception error between the two vehicle states is valid.
17. The method of claim 16 , further comprising:
determining the perturbed state of the vehicle by adding the perception error to each original value of the vehicle state.
18. An end-to-end perception perturbation modeling system for a vehicle, the end-to-end perception perturbation modeling system comprising:
one or more controllers storing a detection model and a set of vehicle state perturbation models in memory, wherein the detection model is created based on synthetic data and includes a plurality of detection model plots that each indicate a probability value that an object in an environment surrounding the vehicle is detected based on a current weather condition and a distance measured between the vehicle and the object detected in the environment surrounding the vehicle, and wherein each set of vehicle state perturbation models include a plurality of vehicle state perturbation models that each represent a perception error distribution that corresponds to a specific current weather condition and a specific distance measured between the vehicle and the object detected in the environment, and wherein the one or more controllers execute instructions to:
receive an input state of the vehicle, wherein the input state is observed during non-inclement weather conditions and indicates one or more vehicle states, the current weather condition, and the distance;
determine a probability value corresponding to the current weather condition and the distance based on the detection model;
execute a simulation based on the probability value, wherein the simulation determines a probability the object located in the environment is detected based on the current weather condition and the distance, and wherein the simulation is executed by:
drawing a random number;
comparing the random number with the probability value; and
in response to determining the random number is equal to or greater than the probability value, determine the object is detected and the probability is true; and
in response to determining the probability the object located in the environment indicates the object will be detected, determine a perturbed state of the vehicle observed during the current weather condition, wherein the current weather condition indicates an adverse weather condition, wherein the perturbed state of the vehicle indicates the probability that the object located in the environment is detected, and wherein the end-to-end perception perturbation modeling system is integrated with a trajectory prediction system and a final motion planner of an autonomous driving system that execute trajectory prediction and final motion planning of the vehicle based on the probability the object located in the environment is detected.
19. The end-to-end perception perturbation modeling system of claim 18 , wherein the one or more controllers execute instructions to:
determine a perception error for each vehicle state during the current weather condition at the distance as indicated by the input state based on the set of vehicle state perturbation models; and determine a correlation value between two perception errors between two of the vehicle states at the current weather condition and the distance as indicated by the input state, where the correlation value is representative of a functional relationship between two of the vehicle state perturbation models.
20. The end-to-end perception perturbation modeling system of claim 19 , wherein the one or more controllers execute instructions to:
compare the correlation value of the two perception errors between two of the vehicle states with an expected sensitivity value range, wherein the expected sensitivity value range indicates an expected difference between the perception errors of the two vehicle states;
in response to determining the correlation value falling within the expected sensitivity value range, determine the perception error between the two vehicle states is valid; and
determine the perturbed state of the vehicle by adding the perception error to each original value of the vehicle state.