2019/09/13 by Boris Bogaerts, Bogaerts, Boris, Seppe Sels +5
Computer Science · Engineering · Neuroscience · #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Interactive and Immersive Displays #Robotics (cs.RO) #Robotics and Sensor-Based Localization #Tactile and Sensory Interactions #Visual Attention and Saliency Detection
paper · pdf · doi:10.48550/arxiv.1909.06077
openalex publication_date 2019/09/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this work, we investigate whether humans can manually generate\nhigh-quality robot paths for optical inspections. Typically, automated\nalgorithms are used to solve the inspection planning problem. The use of\nautomated algorithms implies that specialized knowledge from users is needed to\nset up the algorithm. We aim to replace this need for specialized experience,\nby entrusting a non-expert human user with the planning task. We augment this\nuser with intuitive visualizations and interactions in virtual reality. To\ninvestigate if humans can generate high-quality inspection paths, we perform a\nuser study in which users from different experience categories, generate\ninspection paths with the proposed virtual reality interface. From our study,\nit can be concluded that users without experience can generate high-quality\ninspection paths: The median inspection quality of user generated paths ranged\nbetween 66-81 % of the quality of a state-of-the-art automated algorithm on\nvarious inspection planning scenarios. We noticed however, a sizable variation\nin the performance of users, which is a result of some typical user behaviors.\nThese behaviors are discussed, and possible solutions are provided.\n