Generating autonomous vehicle simulation data from logged data
Logged data from an autonomous vehicle is processed to generate augmented data. The augmented data describes an actor in an environment of the autonomous vehicle, the actor having an associated actor type and an actor motion behavior characteristic. The augmented data may be varied to create different sets of augmented data. The sets of augmented data can be used to create one or more simulation scenarios that in turn are used to produce machine learning models to control the operation of autonomous vehicles.
1. A method for generating simulation data, the method comprising:
receiving logged data including that of from one or more autonomous driving subsystems of an autonomous vehicle;
generating augmented data from the logged data, the augmented data describing an actor in an environment of the autonomous vehicle, the actor having an associated actor type and an actor motion behavior characteristic;
generating a simulation scenario as the simulation data, the simulation scenario generated from the augmented data;
training a machine learning model of the autonomous vehicle using the simulation data by:
executing a simulation based on the simulation scenario to generate a simulated output;
providing the simulation scenario as a training input to the machine learning model to generate a predicted output of the machine learning model; and
updating one or more weights in the machine learning model based on a difference between the predicted output and the simulated output of the simulation scenario; and
performing, using the trained machine learning model, an autonomous vehicle task corresponding to autonomous driving by the autonomous vehicle during a real-world operation of the autonomous vehicle.
2. The method of claim 1 , wherein generating the simulation scenario further comprises:
generating a variation of the augmented data; and
generating the simulation scenario as the simulation data, the simulation scenario generated from the variation of the augmented data.
3. The method of claim 1 , wherein the logged data includes raw sensor data and one of data from a video game and data from film.
4. The method of claim 1 , wherein the logged data is time-series logged data including localization data and tracking data.
5. The method of claim 1 , wherein the logged data includes one of raw sensor data from any one or more sensors, state or localization data from a localization subsystem, state or perception data from a perception subsystem, state or planning data from a planning subsystem and state or control data from a control subsystem.
6. The method of claim 1 , further comprising:
mapping the logged data to a coordinate system to produce mapped logged data;
performing smoothing of the mapped logged data to produce smoothed data; and
wherein the smoothed data is used in generating augmented data.
7. The method of claim 1 , wherein the simulation data comprises a simulation scenario that describes motion behavior of a simulated autonomous vehicle and at least one simulated actor.
8. The method of claim 1 , wherein generating the augmented data comprises:
identifying, from the logged data, actors and generating actor states to create an initial augmented data;
sampling the initial augmented data; and
generating a variation of the sampled augmented data.
9. The method of claim 8 , wherein the generating the variation includes changing one from a group of actor velocity, actor type, actor size, actor geometric shape, and actor reflectivity or color, actor path, lateral offset of motion, longitudinal offset of motion, adding an actor, deleting an actor and actor behavior response.
10. The method of claim 8 , wherein the generating the variation includes generating a plurality of sets of sampled augmented data, and wherein the generating the simulation scenario from the augmented data includes generating a plurality of simulation scenarios each one corresponding to one set of the plurality of sets of sampled augmented data.
11. A system comprising one or more processors and memory operably coupled with the one or more processors, wherein the memory stores instructions that, in response to an execution of the instructions by one or more processors, cause the one or more processors to perform the following operations:
receiving logged data including that of from one or more autonomous driving subsystems of an autonomous vehicle;
generating augmented data from the logged data, the augmented data describing an actor in an environment of the autonomous vehicle, the actor having an associated actor type and an actor motion behavior characteristic;
generating a simulation scenario as simulation data, the simulation scenario generated from the augmented data;
training a machine learning model of the autonomous vehicle using the simulation data by:
executing a simulation based on the simulation scenario to generate a simulated output;
providing the simulation scenario as a training input to the machine learning model to generate a predicted output of the machine learning model; and
updating one or more weights in the machine learning model based on a difference between the predicted output and the simulated output of the simulation scenario; and
performing, using the trained machine learning model, an autonomous vehicle task corresponding to autonomous driving by the autonomous vehicle during a real-world operation of the autonomous vehicle.
12. The system of claim 11 , wherein generating the simulation scenario further comprises:
generating a variation of the augmented data; and
generating the simulation scenario as the simulation data, the simulation scenario generated from the variation of the augmented data.
13. The system of claim 11 , wherein the logged data is time-series logged data including localization data and tracking data.
14. The system of claim 11 , wherein the logged data includes one of raw sensor data from any one or more sensors, state or localization data from a localization subsystem, state or perception data from a perception subsystem, state or planning data from a planning subsystem and state or control data from a control subsystem.
15. The system of claim 11 , wherein the operations further comprise:
mapping the logged data to a coordinate system to produce mapped logged data;
performing smoothing of the mapped logged data to produce smoothed data; and
wherein the smoothed data is used in generating augmented data.
16. The system of claim 11 , wherein the simulation data comprises a simulation scenario that describes motion behavior of a simulated autonomous vehicle and at least one simulated actor.
17. The system of claim 11 , wherein generating the augmented data comprises:
identifying, from the logged data, actors and generating actor states to create an initial augmented data;
sampling the initial augmented data; and
generating a variation of the sampled augmented data.
18. The system of claim 17 , wherein the generating the variation includes changing one from a group of actor velocity, actor type, actor size, actor geometric shape, actor reflectivity or color, actor path, lateral offset of motion, longitudinal offset of motion, adding an actor, deleting an actor and actor behavior response.
19. The system of claim 17 , wherein the generating the variation includes generating a plurality of sets of sampled augmented data, and wherein the generating the simulation scenario from the augmented data includes generating a plurality of simulation scenarios each one corresponding to one set of the plurality of sets of sampled augmented data.
20. A non-transitory computer readable storage medium storing computer instructions executable by one or more processors to perform a method of generating simulation data for an autonomous vehicle, the method comprising:
receiving logged data including that of from one or more autonomous driving subsystems of the autonomous vehicle;
generating augmented data from the logged data, the augmented data describing an actor in an environment of the autonomous vehicle, the actor having an associated actor type and an actor motion behavior characteristic;
generating a simulation scenario as simulation data, the simulation scenario generated from the augmented data;
training a machine learning model of the autonomous vehicle using the simulation data by:
executing a simulation based on the simulation scenario to generate a simulated output;
providing the simulation scenario as a training input to the machine learning model to generate a predicted output of the machine learning model; and
updating one or more weights in the machine learning model based on a difference between the predicted output and the simulated output of the simulation scenario; and
performing, using the trained machine learning model, an autonomous vehicle task corresponding to autonomous driving by the autonomous vehicle during a real-world operation of the autonomous vehicle.