Josh Mosier
Papers
1
Total Citations
34
H-Index
1
About
Josh Mosier explores the intersection of robotics, human-robot interaction, and assistive technologies, with a focus on how robots can better infer and communicate human goals during shared tasks. His most-cited work, "Communicating Inferred Goals with Passive Augmented Reality and Active Haptic Feedback" (2021, 34 citations), tackles a critical challenge in teleoperation: as a human guides a robot arm, the robot learns the user's intent, but the human remains uncertain about what the robot has inferred. Mosier's innovative solution combines passive augmented reality cues with active haptic feedback, creating a bidirectional communication channel that makes robot learning transparent and intuitive. This work bridges gaps in transparency and trust in assistive robotics, enabling more fluid human-robot collaboration. By addressing the fundamental problem of mutual understanding in learning-from-demonstration systems, Mosier's research has implications for assistive devices used by individuals with motor impairments, as well as broader applications in collaborative manufacturing and rehabilitation robotics. His contributions highlight the importance of designing robots that not only learn but also clearly communicate their evolving understanding back to human partners.
Research Focus
Key Achievements
Top Papers
- 1