In human-robot collaboration (HRC), it is crucial for robot agents to consider humans' knowledge of their surroundings. In reality, humans possess a narrow field of view (FOV), limiting their perception. However, research on HRC often overlooks this aspect and presumes an omniscient human collaborator. Our study addresses the challenge of adapting to the evolving subtask intent of humans while accounting for their limited FOV. We integrate FOV within the humanaware probabilistic planning framework. To account for large state spaces due to considering FOV, we propose a hierarchical online planner that efficiently finds approximate solutions while enabling the robot to explore low-level action trajectories that enter the human FOV, influencing their intended subtask. Through user study with our adapted cooking domain, we demonstrate our FOV-aware planner reduces human's interruptions and redundant actions during collaboration by adapting to human perception limitations. We extend these findings to a virtual reality kitchen environment, where we observe similar collaborative behaviors.

Drivers and other road users often encounter situations (e.g., arriving at an intersection simultaneously) where priority is ambiguous or unclear but must be resolved via communication to reach agreement. This poses a challenge for autonomous vehicles, for which no direct means for expressing intent and acknowledgment has yet been established. This paper contributes a minimal model to manage ambiguity and produce actions that are expressive and encode aspects of intent. Specifically, intent is treated as a latent variable, communicated implicitly through a partially observable Markov decision process (POMDP). We validate the model in a simple setting: a simulation of a prototypical crossing with a vehicle and one pedestrian at an unsignalized intersection. We further report use of our self-driving Ford Lincoln MKZ platform, through which we conducted experimental trials of the method involving real-time interaction. The experiment shows the method achieves safe and efficient navigation.

Though autonomous vehicles are currently operating in several places, many important questions within the field of autonomous vehicle research remain to be addressed satisfactorily. In this paper, we examine the role of communication between pedestrians and autonomous vehicles at unsignalized intersections. The nature of interaction between pedestrians and autonomous vehicles remains mostly in the realm of speculation currently. Of course, pedestrian's reactions towards autonomous vehicles will gradually change over time owing to habituation, but it is clear that this topic requires urgent and ongoing study, not least of all because engineers require some working model for pedestrian- autonomous-vehicle communication. Our paper proposes a decision-theoretic model that expresses the interaction between a pedestrian and a vehicle. The model considers the interaction between a pedestrian and a vehicle as expressed an MDP, based on prior work conducted by psychologists examining similar experimental conditions. We describe this model and our simulation study of behavior it exhibits. The preliminary results on evaluating the behavior of the autonomous vehicle are promising and we believe it can help reduce the data needed to develop fuller models.