In this article, we investigate using explanations to improve decision-making for robotic scientific data collection missions. We propose the Preference Elicitation with contrasting Feature-based eXplanations (PrEFeX) method, which combines preferences with contrasting explanations focused on a single explanatory feature. We first provide a verification of the contrasting explanations by themselves using a planner prediction user study with 16 expert participants (Phase 1). This study showed that there was no increase in understanding of robot plans using contrasting explanations without preferences. To elucidate what information the autonomous measurement selection system was missing to be useful, we interviewed 4 planetary scientists and 2 oceanographers (Phase 2). We found that scientists focused heavily on understanding the objectives of the system and wanted explanations that (1) grounded the explanations to tradeoffs the system made, (2) connected the explanations to an ability to modify the behavior of the decision making, and (3) attached the explanation system’s features to comparable features the scientists considered. To this end, we propose combining explanations with user preference learning of the reward function in an iterative design process of the measurement plans with scientists in the loop. We tested our proposed preference and explanation system in a field deployment with planetary scientists on Mt. Hood, Oregon, and performed a post-data collection survey on the quality of the plans with 22 experts (Phase 3). We found the experts preferred the measurement plan selected by our proposed PrEFeX method over a baseline without explanations or preferences.

We present a coactive algorithm for learning a human expert's preferences in planning trajectories for information gathering in scientific autonomy domains. The algorithm learns these preferences by iteratively presenting solutions to the expert and updating an estimated utility function based on the expert's improvements. We apply these algorithms, in the context of underwater data collection, using a pair of risk and reward maps. In simulated trials, the algorithm successfully learns the underlying weighting behind a utility map used by a human planning trajectories. We also present experimental trials demonstrating the algorithm using a temperature and depth monitoring task in an inland lake with an autonomous surface vehicle. This work shows it is possible to design algorithms for autonomous navigation with reward functions that capture the essence of a human's preferences.