Systems and methods to adapt and optimize human-machine interaction using multimodal user-feedback

A system comprising:

• a body assembly;
• a head assembly mechanically attached to the body assembly via a motor assembly;
• the motor assembly, the motor assembly being constructed to rotate the head assembly about a vertical axis and a horizontal axis;
• at least a first motorized appendage constructed to perform movement in accordance with at least one human-interaction gesture;
• an adaptive behavioral control system communicatively coupled to at least one of the motor assembly, the head assembly, and the appendage;
• a human reaction detection sub-system communicatively coupled to the adaptive behavioral control system;
• and
• an interaction sub-system communicatively coupled to the adaptive behavioral control system,
• wherein the adaptive behavioral control system is constructed to:
• detect a plurality of interaction participants by using at least one sensor,
• store at least one computer-behavioral policy for each detected interaction participant,
• control at least one of the interaction sub-system, the motor assembly, the appendage, the body assembly, and the head assembly to perform actions of a first action type for each detected interaction participant in accordance with a selected computer-behavioral policy for the interaction participant,
• for each detected interaction participant, detect a human reaction of the interaction participant to the performance of each action of the first action type from data received from the human reaction detection sub-system,
• for each detected human interaction participant, store information indicating each detected human reaction in association with information identifying the associated action, and
• for each detected human interaction participant, in a case where stored information indicating detected human reactions for the first action type satisfy an update condition, update the computer-behavioral policy of the interaction participant for the first action type.

A method comprising:

• an adaptive behavioral control system controlling an interaction sub-system to perform a plurality of actions for a first action type in accordance with a computer-behavioral policy, each action being a different alternative action for the action type;
• the adaptive behavioral control system detecting a human reaction to the performance of each action of the first action type from data received from a human reaction detection sub-system;
• the adaptive behavioral control system storing information indicating each detected human reaction in association with information identifying the associated action;
• and
• in a case where stored information indicating detected human reactions for the first action type satisfy an update condition, the adaptive behavioral control system updating the computer-behavioral policy for the first action type.