Data sparse inference of operator spatial reward models in uncertain environments

Human–machine teaming allows people to leverage the impressive capabilities of autonomous robotic teammates to safely accomplish challenging tasks. Although users may be experts in their fields, robotic interfaces need to be intuitive to the general population and able to quickly interpret minimal user input from multiple modalities in directing autonomous teammates toward key locations for information-based tasking. This work presents a flexible multimodal algorithmic and visual interface that enables dynamic reprogramming of autonomous planning algorithms, focusing on the use of uncrewed aerial systems engaged in outdoor search and rescue. The Responsive Interface for iNtuitive Aircraft Operation (RINAO) leverages known geographic database information, such as trail networks, in conjunction with a variable set of user-defined features, such as search areas and landmarks, to efficiently infer a mission-specific, uncertainty-aware geospatial interest distribution that informs optimal planning algorithms through reward shaping. The approach is validated using 10 experts in public safety with 13.5 years of median operational experience. Results of this user evaluation show that the system enables effective and efficient alignment of geospatial interest and above-average usability. Evaluating the system’s performance against an inverse reinforcement learning (IRL) baseline, we find that our approach meets or exceeds the baseline’s value alignment while performing inference in substantially less time and with less user input. These results demonstrate that multimodal preference inference can enable rapid and intuitive mission specification for human—robot teams operating in time-critical environments.