Dynamic Path Visualization for Human-Robot Collaboration

摘要: Augmented reality technology can enable robots to visualize their future actions giving users crucial information avoid collisions and other conflicting actions. Although a robot's entire action plan could be visualized (such as the output of navigational planner), how far into it is appropriate display unknown. We developed dynamic path visualizer that projects motion intent at varying lengths depending on complexity upcoming path. tested our approach in virtual game where participants were tasked collect deliver gems robot moves randomly towards grid markers confined area. Preliminary results small sample size indicate no significant effect task performance; however, open-ended responses reveal preference visuals show longer projections.