Using Plays for Human-AI Decision-Making in Remote Autonomous Vehicle Support

An apparatus for traversing a vehicle transportation network by an autonomous vehicle (AV), comprising:

• an autonomous mobility agent comprising a first processor configured to:
• receive a request for remote assistance support from the AV responsive to a condition observed by the AV while traversing from a starting location to an ending location within the vehicle transportation network;
• and
• a human-autonomy teaming manager comprising a second processor configured to:
• initiate a dialogue associated with a predefined dynamic task sequence that is one of a plurality of predefined dynamic task sequences using multiple agents to resolve the condition, the multiple agents including a human agent and the autonomous mobility agent;
• present the dialogue to the human agent at a user interface of the human-autonomy teaming manager;
• receive, from the user interface, an input responsive to the dialogue, wherein the input confirms the predefined dynamic task sequence as a selected predefined dynamic task sequence or selects an other predefined dynamic task sequence of the plurality of predefined dynamic task sequences as the selected predefined dynamic task sequence;
• and
• manage the selected predefined dynamic task sequence by delegating tasks of the selected predefined dynamic task sequence to resolve the condition, wherein the first processor is configured to, responsive to the request, call the human-autonomy teaming manager to select the predefined dynamic task sequence.

A method for traversing a vehicle transportation network by an autonomous vehicle (AV), comprising:

• initiating, by a first processor of a human-autonomy teaming manager, a dialogue associated with a predefined dynamic task sequence that is responsive to a condition experienced by the AV while traversing from a starting location to an ending location within the vehicle transportation network, wherein the predefined dynamic task sequence is one of a plurality of predefined dynamic task sequences using multiple agents to resolve the condition;
• receiving, from an interface accessible to a human agent of the multiple agents, an input responsive to the dialogue, wherein the input confirms the predefined dynamic task sequence as a selected predefined dynamic task sequence or selects an other predefined dynamic task sequence of the plurality of predefined dynamic task sequences as the selected predefined dynamic task sequence;
• and
• managing, by the first processor, the selected predefined dynamic task sequence to resolve the condition.