US 12,227,202 B2
Adaptive trust calibration
Kumar Akash, Milpitas, CA (US); and Teruhisa Misu, Mountain View, CA (US)
Assigned to Honda Motor Co., Ltd., Tokyo (JP)
Filed by Honda Motor Co., Ltd., Tokyo (JP)
Filed on Jun. 10, 2021, as Appl. No. 17/344,119.
Prior Publication US 2022/0396287 A1, Dec. 15, 2022
Int. Cl. B60W 60/00 (2020.01); B60W 40/09 (2012.01)
CPC B60W 60/001 (2020.02) [B60W 40/09 (2013.01); B60W 2540/221 (2020.02); B60W 2540/225 (2020.02); B60W 2540/229 (2020.02)] 16 Claims
OG exemplary drawing
 
1. A computer-implemented method for adaptive trust calibration for an autonomous vehicle semi-autonomously or autonomously operating or driving through an environment, comprising:
receiving occupant sensor data associated with an occupant of the autonomous vehicle from one or more sensors the autonomous vehicle;
receiving scene context sensor data associated with an environment of the autonomous vehicle at a first time from the sensors, including a scene complexity associated with a scene of the autonomous vehicle;
generating a trust model for the occupant based on the occupant sensor data and the scene context sensor data, including:
analyzing a real-time automation transparency to the occupant based on one or more cues provided to the occupant,
analyzing the scene complexity, and
determining workload dynamics of the occupant, based in part on a relationship between the occupant sensor data, the automation transparency and the scene complexity, to capture a dynamic interaction between occupant trust and occupant workload behavior over time;
receiving second scene context sensor data associated with an environment of the autonomous vehicle at a second time including receiving past over trust scenarios and determining whether the scene context sensor data is the same as one of the past over trust scenarios and updating the trust model based on the same past over trust scenario as current scene context data;
determining an over trust scenario based on the trust model and a trust model threshold; and
generating and implementing a human machine interface (HMI) action or a driving automation action based on the determination of the over trust scenario and e second scene context sensor data,
wherein the HMI action includes one or more of an action to enable, disable, or adjust a vehicle system including one or more of an air conditioning (A/C) system, a fan system, and a seat system.