Cognitive Interaction Analysis in Human–Robot Collaboration Using an Assembly Task

Round 1

Reviewer 1 Report

The paper presents a cognitive interaction analysis in human-robot collaboration. The paper is interesting and easy to read. The authors should improve the following points of the manuscript:

1. The novelty of the approach should be better explained with respect to the present literature.
2. It would be interesting to evaluate metrics of task performance and collaborative fluency in the assembly task.
3. More details on the participants should be included in the text (age, gender, previous experience with similar experiments).
4. Maximum robot speed and acceleration during the task should be mentioned in the text. How was the robot programmed and which safety features have been implemented for the collaborative operation?
5. Literature review should be improved. Some suggested references on the topic:

Scalera, L., Giusti, A., Vidoni, R., Cosmo, V. D., Matt, D. T., & Riedl, M. (2020). Application of dynamically scaled safety zones based on the ISO/TS 15066: 2016 for collaborative robotics. Int. J. Mech. Control, 21, 41-50.

Hoffman, G. (2019). Evaluating fluency in human–robot collaboration. IEEE Transactions on Human-Machine Systems, 49(3), 209-218.

Zanchettin, A. M., Casalino, A., Piroddi, L., & Rocco, P. (2018). Prediction of human activity patterns for human–robot collaborative assembly tasks. IEEE Transactions on Industrial Informatics, 15(7), 3934-3942.

 

Author Response

Dear Reviewer,

my co-authors and I would like to thank you for your time and comments to enrich our manuscript. We appreciate your thorough review and constructive suggestions. 

We have carefully reviewed your comments and made revisions to accommodate them. We really believe each point raised significantly improved the original manuscript. Although changes are throughout the document, detailed responses to comments are given in the following page. We have responded to each question separately and we hope to have soundly addressed your concerns.

Thank you again for your consideration.

********

The paper presents a cognitive interaction analysis in human-robot collaboration. The paper is interesting and easy to read. The authors should improve the following points of the manuscript:

1. The novelty of the approach should be better explained with respect to the present literature.

The description of the objective has been completed and suggested references have been added.

1. It would be interesting to evaluate metrics of task performance and collaborative fluency in the assembly task.

These metrics have been evaluated in Section “3.2. Task Performance”

1. More details on the participants should be included in the text (age, gender, previous experience with similar experiments).

Section “2.3.1. Participants” has been added.

1. Maximum robot speed and acceleration during the task should be mentioned in the text. How was the robot programmed and which safety features have been implemented for the collaborative operation?

Section “2.2. Safety conditions” has been generated.

1. Literature review should be improved. Some suggested references on the topic:

Scalera, L., Giusti, A., Vidoni, R., Cosmo, V. D., Matt, D. T., & Riedl, M. (2020). Application of dynamically scaled safety zones based on the ISO/TS 15066: 2016 for collaborative robotics. Int. J. Mech. Control, 21, 41-50.

Hoffman, G. (2019). Evaluating fluency in human–robot collaboration. IEEE Transactions on Human-Machine Systems, 49(3), 209-218.

Zanchettin, A. M., Casalino, A., Piroddi, L., & Rocco, P. (2018). Prediction of human activity patterns for human–robot collaborative assembly tasks. IEEE Transactions on Industrial Informatics, 15(7), 3934-3942.

Suggested references have been introduced in Section 2.2 and 3.2.

Reviewer 2 Report

Manuscript entitled Cognitive Interaction Analysis in Human-Robot
Collaboration using an Assembly Task focuses primarily on the problem of human-robot cooperation in solving tasks that involve the use of higher mental concentration. Within the manuscript, the authors stated the hypothesis "Our hypothesis is that when the operator performs the collaborative task with the robot, the mental workload value is not very far from the mental workload
of the main task. Moreover, both values ​​would be in an intermediate comfort zone of mental workload. "The authors defend their hypothesis with the results obtained from the course of the experiment. I consider the greatest weakness of the article to be the generalization of the hypothesis based on the results of a behavioral experiment on 18 participants. Despite the fact that the authors have tried to classify the various groups that participated in the experiment, the question still remains unanswered, what are the findings? Namely, the results speak more about the potential of the participants to focus on the solved task than about the overall impact of cooperation with the robot. Personally, I think that in order to reflect the real experience within the deployment in industry, special scenarios must be created depending on the work performed and the work role of the participants. Also, the selection of experimental tasks to be solved within the cooperation, I think it was not chosen correctly. While the first task is focused primarily on the cognitive ability to solve the problem, the second task adds a situation to the activity of working with the robot. The problem occurs while in the first case the participant is primarily focused on solving the problem, in the second case when the participant has already created learned solution patterns, the task during cooperation with the robot during the assembly process is almost as demanding as the first task.   In this case, I get the impression that it is a reflection of the feelings of the participants within the tasks and the effort of the human participants to look better, while perceiving the robot as a competition. For this reason, a new set of specific tasks must be created that reflect the typical production routine as much as possible. This is also related to the role of the employee, his mental state before the task and the influence of other parameters such as motivation and relationship to work with the robot instead of a human.   Therefore, I ask the authors to complete a deeper analysis of the overall problem.

Author Response

Dear Reviewer,

my co-authors and I would like to thank you for your time and comments to enrich our manuscript. We appreciate your thorough review and constructive suggestions. 

We have carefully reviewed your comments and made revisions to accommodate them. We really believe each point raised significantly improved the original manuscript. Although changes are throughout the document, detailed responses to comments are given in the following page. We have responded to your questions and we hope to have soundly addressed your concerns.

Thank you again for your consideration.

********

….   Therefore, I ask the authors to complete a deeper analysis of the overall problem.

We worked on your concerns by:

• Highlighting the novelty of our proposal in the Motivation
• Adding evaluation metrics in Section “3.2. Task Performance”
• Showing more information about the participants in Section “3.2. Task Performance”
• Showing more information about the robotics part, specificaclly safety issues in Section “2.2. Safety conditions”
• Improving ‘Discussion’ and ‘Conclusions’ sections having in mind your concerns. Specially, the Discussion section includes a deeper analysis.
•  Adding some references suggested by other reviewers

 

Round 2

Reviewer 1 Report

The paper was improved following my previous comments and remarks. I suggest the paper to be accepted for publication.