Toward Adaptive Trust Calibration for Level 2 Driving Automation
This work addresses the challenge of human-automation interaction in driving, but it is incremental as it builds on existing trust calibration methods with a specific modeling approach.
The paper tackles the problem of balancing automation transparency and human workload in Level 2 driving automation by developing a probabilistic POMDP framework to model trust-workload dynamics, demonstrating that it can adapt transparency in real-time to achieve trust calibration.
Properly calibrated human trust is essential for successful interaction between humans and automation. However, while human trust calibration can be improved by increased automation transparency, too much transparency can overwhelm human workload. To address this tradeoff, we present a probabilistic framework using a partially observable Markov decision process (POMDP) for modeling the coupled trust-workload dynamics of human behavior in an action-automation context. We specifically consider hands-off Level 2 driving automation in a city environment involving multiple intersections where the human chooses whether or not to rely on the automation. We consider automation reliability, automation transparency, and scene complexity, along with human reliance and eye-gaze behavior, to model the dynamics of human trust and workload. We demonstrate that our model framework can appropriately vary automation transparency based on real-time human trust and workload belief estimates to achieve trust calibration.