Designing Multimodal Intent Communication Strategies for Conflict Avoidance in Industrial Human-Robot Teams

Robot-to-human intent communication has been proposed as a method of enabling fluent coordination in human-robot teams. Prior research has focused on identifying modalities by which intent information can be accurately communicated, but has not yet studied whether intent communication enables fluent or safer coordination in human-robot teams in which intent communication is only supportive to the team's primary task. To address this question, we conduct a study (N = 29) in a mock collaborative manufacturing scenario in which motion-based and display-based intent communication approaches are evaluated under varying penalties for failing to coordinate safely. Subjective and objective measures of team fluency suggest that although intent communication supports fluent coordination, using a purely motion-based or a purely display-based approach may not be the most effective strategy. Although multimodal intent communication did not significantly improve upon unimodal approaches, merging both motion-based and display-based intent communication seems to combine the strengths of both approaches. Interestingly, results also suggest that contrary to theoretical predictions, the positive effect of intent communication is generally robust to teaming scenarios that require members to operate concurrently.