Autonomous operation for an autonomous vehicle objective in a multi-vehicle environment

A method comprising:

• selecting an autonomous vehicle objective for a vehicle environment;
• identifying a set of autonomous vehicle states related to the autonomous vehicle objective;
• determining whether another vehicle of the vehicle environment affects the autonomous vehicle objective;
• when the another vehicle of the vehicle environment affects the autonomous vehicle objective, for each state progression of the set of autonomous vehicle states:
• discerning a vehicular state of the another vehicle to produce a discerned vehicular state;
• forming an adaptive policy to a present one of the set of autonomous vehicle states relative to the discerned vehicular state of the another vehicle;
• forming an autonomous vehicle action based on the adaptive policy to progress to a subsequent one of the set of autonomous vehicle states of the autonomous vehicle objective;
• and
• transmitting the autonomous vehicle action for effecting a progression to the subsequent one of the set of autonomous vehicle states.

A vehicle control unit for autonomous vehicle operation in a multi-vehicle environment, the vehicle control unit comprising:

• a wireless communication interface to service communication with a vehicle network;
• a processor communicably coupled to the wireless communication interface and to a plurality of vehicle sensor devices;
• and
• memory communicably coupled to the processor and storing, for each state progression of a set of autonomous vehicle states for an autonomous vehicle objective:
• a multi-vehicle detection module including instructions that, when executed by the processor, cause the processor to:
• based on a first portion of the plurality of vehicle sensor devices, discern a vehicular state of another vehicle of the multi-vehicle environment to produce a discerned vehicular state of the another vehicle, wherein the another vehicle operates to affect the autonomous vehicle objective;
• a reinforcement learning module including instructions that, when executed by the processor, cause the processor to:
• retrieve passive dynamic data for the autonomous vehicle operation relating the multi-vehicle environment related to a second portion of the plurality of the vehicle sensor devices;
• form an adaptive policy, based on the discerned vehicular state and the passive dynamic data, to a present one of a plurality of autonomous vehicle states related to the autonomous vehicle objective;
• form an autonomous vehicle action command from the adaptive policy to progress to a subsequent one of the set of autonomous vehicle states;
• and
• transmit the autonomous vehicle action command to effect a progression to the subsequent one of the autonomous vehicle states.