Multi-Objective Navigation Strategy for Guide Robot Based on Machine Emotion

Round 1

Reviewer 1 Report

This manuscript presents a study to include human emotion as an input to a guide robot to optimize its navigation strategy through multi-objective optimization.

 

The manuscript is well-written but has some major issues that need to be addressed.

 

 

1. Line 50-53: “(1) In the navigation scene, the number of navigation robots is often far smaller than the number of tourists, and only a small number of people can be selected for service. Therefore, how to make the guide robot choose the service object reasonably needs to be studied.” How? This is not explained in the manuscript. If yes, please be specific. For example, how can a robot take multiple inputs from different tourists and make a decision on its navigation task?

 

2. Line 68-71: “(1) This paper proposes a tourist emotions-oriented navigation strategy for tourist guide robots. Machine emotions are established according to tourists' emotional states, and machine emotions give the robot the ability of "empathy" with tourists, so as to find the target points most expected by tourists.” This part is not clear to the reviewer. What is exactly the “machine emotions” referred by the authors? It occurred to the reviewer that they are nothing more than a direct input from the end user. For example, what exactly are the inputs available to the user? Are the emotion states listed in Table 1 representing all the options provided to the tourist? What are the connections between human emotion and machine emotion? And why?

 

3. Chapter 2 is very loose. What are the logic and linkage between these studies? Please don’t just list them in test, instead, please try to find the connections and inform the readers/reviewers what you learned from these studies and what is the technology gap between the current state-of-the-art implementations and what is desired in the ideal situation.

 

4. Section 2.2, please discuss why empathy is important in improving human-machine interface and why including human emotions as an input in the navigation strategy of guide robots is necessary.

 

5. Line 202, what is P0 and what is A0? For eq. (1), you may give some examples in figures. Also in Table 1, no idea what are P and A.

 

6. Section 3.1.3, after eq. (2) & (3), please explain these two equations.

 

7. Line 234, “This method takes machine emotion as the optimization target of navigation strategy.” Why? How?

 

8. Section, 3.2.1, algorithm? Pseudo-code?

 

9. Line 287-291, “Our method can provide the weight judgment basis for the linear weighting method. The linear weighted multi-objective optimization algorithm based on machine emotion has a set of dynamic and personalized weight judgment methods, which can transform the multi-objective optimization into a single objective optimization problem for machine emotion.” Why? How?

 

10. Line 302-303, “Prior to this, the emotional atmosphere field was used to analyze the communication atmosphere of different groups[28], so as to determine the target group of services.” and Line 78-80, “(3) In view of the situation that the number of tourists is much larger than the number of guiding robots, the group that needs guiding robots most is identified through the evaluation of the communication atmosphere field of different groups.” What is the so-called “communication atmosphere field”? Please be specific and don’t simply skip it.

 

11. Figure 6, this figure is not clear. How does it reflect the proposed multi-objective optimization method?

 

12. Line 348, what is a Unicom target point?

 

13. No performance metrics are given to benchmark the proposed approach. It is very hard to evaluate how good the proposed approach is and if it has indeed improved the user experience.

 

14. No real-world applications or demonstrations are presented. This study is not completed without further discussion about the actual implementation of the proposed algorithm. Please perform further validation testing to prove the usefulness and practicality of the proposed method.

 

 

Below are some good references the authors should take a look:

 

1. Emotion Detection for Social Robots. (Sensors 2021, 21, 1322. https://doi.org/10.3390/s21041322)

 

2. Artificial Empathy in Social Robots. (James J, Watson CI, MacDonald B. Artificial empathy in social robots: An analysis of emotions in speech. In2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN) 2018 Aug 27 (pp. 632-637). IEEE.

DOI: 10.1109/ROMAN.2018.8525652)

 

3. A tour-guide robot that interacts with humans. (Vásquez BP, Matía F. A tour-guide robot: moving towards interaction with humans. Engineering Applications of Artificial Intelligence. 2020 Feb 1;88:103356. https://doi.org/10.1016/j.engappai.2019.103356)

 

4. Machine emotion-enabled HCI. (Xiao G, Ma Y, Liu C, Jiang D. A machine emotion transfer model for intelligent human-machine interaction based on group division. Mechanical Systems and Signal Processing. 2020 Aug 1;142:106736. https://doi.org/10.1016/j.ymssp.2020.106736)

 

5. Socially Assistive Robots. (Tapus A, Mataric MJ. Socially Assistive Robots: The Link between Personality, Empathy, Physiological Signals, and Task Performance. In AAAI spring symposium: emotion, personality, and social behavior 2008 Mar (pp. 133-140).)

 

 

In addition, there are numerous places where English editing is needed. Please at least proofread it for spelling, grammar and punctuation errors before resubmission. Some of the mistakes are:

 

(1). Line 66, formatting error.

(2). Line 85, summaries.

(3). Line 88, emotional model or model of emotion.

(4). Line 121-126, background color not white.

(5). Line 127, why a new paragraph?

(6). Line 137, avoid repetition of “based on” in a single sentence.

(7). Line 127, social force model.

(8). Line 153, social relation model.

(9). Line 161-165, background color not white.

(10). Line 184, no citation?

(11). Line 220, such point.

(12). Line 231, guide robot or guided robot, please be consistent.

(13). Line 295-299, background color not white.

(14). Line 309, Robotics.

(15). Line 320, one can…

(16). Line 350, “… direction and walk the route to the destination.”

(17). Line 116, people’s daily life.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The authors present an interesting case study on the application of a Multi-objective Navigation Strategy for the Guide Robot “Pepper”, based on a simplified two-dimensional machine emotion algorithm. The presentation needs further improvement and significant expansion of sections 4.1 and 4.2, which presents the main contribution (testing and validation of the procedure). The revised manuscript will need further assessment.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

This is an interesting paper. It needs following revisions:

1. The literature review must be enriched preferable from this journal to solidify the synchronization of the article with aims/scope of the journal.

2. Highlight the proposed technique and its innovative traits in the Introduction section in an interactive manner.

3. Use credible test cases and add their experimental/simulation results to validate the efficacy of the proposed technique.

4. Use extensive qualitative/quantitative comparative analysis of the results.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The idea of “machine emotion” is too abstract and is very hard to assess its actual effect on improving human-machine interaction.

 

The proposed method in the present study is very simple and straightforward, which does not make significant contribution to the relevant field.

 

The implementation part of the study is too weak to validate the proposed method. There is obviously a gap between the proposed model and the its actual application. The only valuable demonstration is added to the new section 4.2 Authentication on Pepper, which is very sketchy and is not scientifically sound.

 

As such, the reviewer does not expect the authors to complete the whole story in the given time but does encourage the authors to take their time to continue working on the implementation part of the study and resubmit the revised manuscript for consideration.

Reviewer 2 Report

It can be published in the revised form

Reviewer 3 Report

Good Luck