Abstract
The number of collaborative robots that perform different tasks in close proximity to humans is increasing. Previous studies showed that enabling non-expert users to program a cobot reduces the cost of robot maintenance and reprogramming. Since this approach is based on an interaction between the cobot and human partners, in this study, we investigate whether making this interaction more transparent can improve the interaction and lead to better performance for non-expert users. To evaluate the proposed methodology, an experiment with 67 participants is conducted. The obtained results show that providing explanation leads to higher performance, in terms of efficiency and efficacy, i.e., the number of times the task is completed without teaching a wrong instruction to the cobot is two times higher when explanations are provided. In addition, providing explanation also increases users’ satisfaction and trust in working with the cobot.
Highlights
The main method to teach a new task to a cobot is reprogramming, i.e., a programmer writes new code for the cobot to achieve a specific objective
As participants were asked to rate the interaction based on two scales of explanation saticification and trust, obtained results show provided explanations increase users’ trust in the cobot (z = − 3.65, p = 0.00012, Table 4), and showed participants were satecified by the provided explanations (z = − 3.86, p = 0.000 26, Table 4)
Participants do not wary the cobot. They believe they can use the system for decision making, which shows how transparent and reliable the provided model is. They believe the output of the cobot is predictable, which might be due to showing the list of the instructions that the cobot follows, i.e., as the proposed Transparent Graphical User Interface (T-GUI) provides the instructions, participants can read and predict what will be the assembly object, which shows how reasonable the cobot’s strategy is
Summary
The main method to teach a new task to a cobot is reprogramming, i.e., a programmer writes new code for the cobot to achieve a specific objective. This approach is expensive (Bloss, 2016) and needs a lot of tuning so that a slight change in the procedure, e.g., changing the order of objects in the case of an assembly task, can cause the cobot to fail in accomplishing the assembly, if the original program is used, even if the cobot is able to perform all necessary sub-tasks One solution to both reduce the cost of teaching cobots new tasks and increase their flexibility (being able to perform different but similar tasks) is enabling their human partners to teach them new tasks, such that a cobot learns new high-level tasks from a nonprogrammer, e.g., an operator in a workshop, who knows the necessary steps to perform the task but does not know how to program the cobot (Billard et al, 2016; Huang and Cakmak, 2017; Stenmark et al, 2017). In this study, a Transparent Graphical User Interface (T-GUI) is designed to provide a bidirectional interaction between a cobot and a human partner such that the cobot can explain why it applies a particular strategy to accomplish a particular task, and the human partner can track the cobot’s actions and provide instructions to it
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
