Fleet-level AV simulation system and method

A system comprising:

• a storage configured to store instructions;
• a processor configured to execute the instructions and cause the processor to:
• measure a first set of cost metrics for a first plurality of autonomous vehicles (AVs) associated with a first vehicle route version, wherein the first set of cost metrics comprises energy consumption values and degradation of vehicles parts values for a first plurality of AVs as the first plurality of AVs traverse a first route of an environment, and the first vehicle routing version specifies a preference to travel along streets with less changes in inclines and declines than a second vehicle routing version;
• measure a second set of cost metrics for a second plurality of AVs associated with the second vehicle route version, wherein the second set of cost metrics comprises energy consumption values and degradation of vehicles parts values for a second plurality of AVs as the second plurality of AVs traverse a second route of the environment, and the second vehicle routing version specifies a preference to adjust an average speed of the second plurality of AVs to arrive at a red light when the red light changes to a green light;
• compare the first set of cost metrics with the second set of cost metrics to determine routing updates configured to reduce fleetwide energy consumption;
• generate an optimized heatmap using a machine learning model based on the routing updates that identifies locations with higher power consumption for an AV navigating within the environment, wherein the routing updates are configured to make changes based on road grade;
• and
• navigate the AV in accordance with the routing updates.

A non-transitory computer readable medium comprising instructions, the instructions, when executed by a computing system, cause the computing system to:

• measure a first set of cost metrics for a first plurality of autonomous vehicles (AVs) associated with a first vehicle route version, wherein the first set of cost metrics comprises energy consumption values and degradation of vehicles parts values for a first plurality of AVs as the first plurality of AVs traverse a first route of an environment, and the first vehicle routing version specifies a preference to travel along flatter streets than a second vehicle routing version;
• measure a second set of cost metrics for a second plurality of AVs associated with the second vehicle route version, wherein the second set of cost metrics comprises energy consumption values and degradation of vehicles parts values for a second plurality of AVs as the second plurality of AVs traverse a second route of the environment, and the second vehicle routing version specifies a preference to adjust an average speed of the second plurality of AVs to arrive at a red light when the red light changes to a green light;
• compare the first set of cost metrics with the second set of cost metrics to determine routing updates configured to reduce fleetwide energy consumption, generate an optimized heatmap using a machine learning model based on the routing updates that identifies locations with higher power consumption for an AV navigating within the environment, wherein the routing updates are configured to make changes based on road grade;
• and
• navigate the AV in accordance with the routing updates.