When to Seek Help: Trust-Aware Assistance-Seeking in Human-Supervised Autonomy

Our goal is to model and experimentally assess trust evolution to predict future beliefs and behaviors of human–robot teams in dynamic environments. Research suggests that maintaining an appropriate level of trust among team members in a human–robot team is vital for team success. Indeed, research suggests that trust is a multidimensional and latent entity that relates to past experiences and future actions in a complex manner. Employing a human–robot collaborative task, we model human behavior using Input–Output Hidden Markov Model (IOHMM) and design an optimal assistance-seeking strategy for the robot using a Partially Observable Markov Decision Process (POMDP) framework. In this task, the human partner supervises an autonomous mobile manipulator collecting objects in an environment. The supervisor’s responsibility is to ensure that the robot safely executes its task. The robot can either choose to attempt to autonomously collect the object or seek human assistance. The human supervisor actively monitors the robot’s activities, offering assistance upon request, and intervening if they perceive that the robot may fail. In this setting, human trust is the hidden state, and the primary objective is to optimize team performance. We conduct two sets of human–robot interaction experiments. The data from the first experiment are used to estimate POMDP parameters, which are used to compute an optimal assistance-seeking policy evaluated in the second experiment. The estimated POMDP parameters reveal that, for most participants, human intervention is more probable when trust is low, particularly in high-complexity tasks. Notably, our estimates suggest that the robot’s action of asking for human assistance in high-complexity tasks can positively impact human trust. Our experimental results show that the proposed trust-aware policy results in a better performance as compared to an optimal trust-agnostic policy. By comparing model estimates of human trust, obtained using only behavioral data, with the collected self-reported trust values, we show that model estimates are isomorphic to self-reported responses.