Work

Can this robot pass through that aperture? Learning to make judgments for a tele-operated robot

Year: 2014
Type: dissertation
Abstract: Urban Search and Rescue is exceptionally dangerous. To mitigate that danger rescue \nworkers utilize robots to access areas that are too small or too dangerous to send people. \nHowever, these robots must be tele-operated, and tele-operation contributes to a host of \nperceptual and cognitive problems (Chellali, 2009; Chen, Durlach, Sloan, & Bowens, 2005; Cui, \nTosunoglu, Roberts, Moore, & Repperger, 2003; Darken, Kempster, & Peterson, 2001; \nLichiardopol, 2007; Van Erp, 2000; Vertut & Coiffet, 1985). One such perceptual problem is the \njudgment of pass-ability, or the width of the robot relative to the width of the aperture. \nPrevious research indicates that operators are good at making judgments of pass-ability \n(Jones, Johnson, & Schmidlin, 2011; Moore & Pagano, 2006), but that these judgments may not \nimprove with practice. The present study investigated two questions: (1) Do judgments of passability \nimprove with time, and (2), What sources of information in the environment contribute to \nlearning to make better judgments of pass-ability in a tele-operated environment. \nThe results indicated the following. First, judgments of pass-ability do in fact improve with \ntime. However, the detection of that improvement requires the data be examined as percent \ncorrect rather than the more traditional threshold analysis. Second, participants learn to make \nbetter judgments when they are allowed to explore the environment and receive feedback, when \nthey are only allowed to explore and not receive feedback, and when they are not allowed to \nexplore and instead only receive feedback following a judgment of pass-ability. However, the \nperformance for participants who were allowed to explore was significantly better than that of \nparticipants who were not allowed to explore. These results support the importance of \nexploration when making an affordance judgment. So while the data support that learning can \nhappen without exploration, they also support that the performance with exploration is \nsignificantly better.
Language: English
Open Access status: green
OpenAlex ID: W2255520595
Cites: 104
Cited by: 3
Related to: 10