Generating training data using simulated environments and training machine learning models for vehicle guidance

An apparatus, comprising:

• a memory configured to store data;
• and
• a processing device coupled to the memory, the processing device configured to:
• generate a first simulated environment, wherein the first simulated environment comprises a route for a simulated vehicle;
• determine a set of locations within the first simulated environment for a set of objects, wherein the set of locations is determined non-deterministically;
• determine a path for the simulated vehicle based on the route;
• generate a set of simulated environments based on the first simulated environment and the set of locations, wherein:
• the set of simulated environments comprise the route for the simulated vehicle;
• and
• each simulated environment of the set of simulated environments comprises a set of non-deterministically generated objects located at the set of locations;
• generate a set of images based on the set of simulated environments, the path, and the set of non-deterministically generated objects;
• and
• train an end-to-end vehicle guidance model based on the set of images.

A non-transitory computer-readable storage medium including instructions that, when executed by a processing device, cause the processing device to perform operations comprising:

• generating a first simulated environment, wherein the first simulated environment comprises a route for a simulated vehicle;
• determining a set of locations within the first simulated environment for a set of objects, wherein the set of locations is determined non-deterministically;
• determining a path for the simulated vehicle based on the route;
• generating a set of simulated environments based on the first simulated environment and the set of locations, wherein:
• the set of simulated environments comprise the route for the simulated vehicle;
• and
• each simulated environment of the set of simulated environments comprises a set of non-deterministically generated objects located at the set of locations;
• generating a set of images based on the set of simulated environments, the path, and the set of non-deterministically generated objects;
• and
• training an end-to-end vehicle guidance model based on the set of images.