Presentation
Analysis and Modeling of Worker Trust in Automated Guided Vehicles for Manufacturing Workplace
DescriptionDespite being pioneers in streamlining the transportation of parts for manufacturing processes, automated guided vehicles (AGVs) still operate separately from human workers due to a lack of trust. To reach their full potential, AGVs must be integrated into human workspaces where they can sense and respond to workers' trust. This study examined workers' trust and behavior during interactions with AGVs. We considered three within-subject factors: AGV deceleration rate (0.1 or 0.7 m/s²), AGV approaching direction (eight compass directions), and the user's expected crossing path (diagonal or straight across an intersection). A human-subject experiment was conducted with 43 participants acting as workers in a virtual reality-based manufacturing plant. Behavioral data and self-reported trust levels were collected using a VR headset, an omnidirectional treadmill, and hand controllers to track eye gaze, movement, and hand positions. The data was processed and analyzed to identify key factors affecting workers' trust. Analysis of Variance revealed that the AGV's approaching direction, the user's expected crossing path, and their interaction significantly impacted trust. Machine learning models were also trained on behavioral and physiological signals to predict trust, achieving promising accuracy. These findings highlight critical design considerations for developing trust-aware AGVs as stepping stones toward human-centered industrial settings.
Event Type
Lecture
TimeTuesday, October 14th1:50pm - 2:10pm CDT
LocationGrand B
Human AI Robot Teaming (AI)