Next Article in Journal
The Effect of the Addition of Hemp Seeds, Amaranth, and Golden Flaxseed on the Nutritional Value, Physical, Sensory Characteristics, and Safety of Poultry Pâté
Next Article in Special Issue
Sim–Real Mapping of an Image-Based Robot Arm Controller Using Deep Reinforcement Learning
Previous Article in Journal
Thermodynamic Analysis of Air-Cycle Refrigeration Systems with Expansion Work Recovery for Compartment Air Conditioning
Previous Article in Special Issue
Remote-Controlled Method with Force and Visual Assists Based on Time to Collision for Mobile Robot
 
 
Article
Peer-Review Record

Autonomous, Digital-Twin Free Path Planning and Deployment for Robotic NDT: Introducing LPAS: Locate, Plan, Approach, Scan Using Low Cost Vision Sensors

Appl. Sci. 2022, 12(10), 5288; https://doi.org/10.3390/app12105288
by Alastair Poole 1,2,*, Mark Sutcliffe 2, Gareth Pierce 1 and Anthony Gachagan 1
Reviewer 1:
Reviewer 2: Anonymous
Appl. Sci. 2022, 12(10), 5288; https://doi.org/10.3390/app12105288
Submission received: 3 May 2022 / Revised: 18 May 2022 / Accepted: 20 May 2022 / Published: 23 May 2022
(This article belongs to the Special Issue Recent Development and Applications of Remote Robot Systems)

Round 1

Reviewer 1 Report

This paper presents a multi-scale and collision-free path planning and implementation methodology enabling rapid deployment of robotised NDT with commercially available sensors. Algorithms are developed to plan paths over noisy and incomplete point clouds. And laser and force feedback are exploited for online path corrections of Conformable-Wedge probe UT. Finally, experimental results indicate the flexible and streamlined pipeline for robotic deployment and demonstrate intuitive data visualisation. Generally speaking, the idea is interesting and it has practical significance for robotic NDT. However, the quality of grammar and symbolic representation in this paper is not high. The detailed comments are given as follows:

1) The abatract should clearly and concisely show the proposed contributions to knowledge.

2) In line 93, an autonomous scanning procedure is introduced for varied parts without accurate digital twins. This part should be explained.

3) In line 145, what does "region of interest" mean? 

4) In Robotic Path Pre-Planning Section, how to process the evironmental data from the RGB/D cameras?

5) In line 288, the main drawback of the method is the potential for error when reflective regions are close to the surface of interest. How to deal with the error? 

6) In Experimental Results Section, why the PI-corrections result in low normal-force errors? 

7) The manuscript also has language and some symbol issues, which need to be checked and corrected in the revision. Such as, in line 12, "…, and…" should be corrected. In line 100, the references "[?]" should be revisised. In line 131, the "significantly" is inappropriate in the sentence. $d$ of the formula (3) should be represented as a standardized form. You should take a careful look on the rest of the paper!

Author Response

Please see attachment

Author Response File: Author Response.docx

Reviewer 2 Report

The authors studied the elimination of predetermined path planning for robotized non-destructive testing. The manuscript is well-written and contains important information and data for the field of computer vision. The complexity of the model and the useful results provide a good novelty research area. This will help future researchers to be able to use it. However, I have some minor comments as listed;

  1. What are the limitations of this study?
  2. I suggest that the authors add a section as an ablation study and explain it.
  3. Figure 9 and figure 10 need to be replaced with higher resolution images.
  4. The reference structure is not good. The authors need to recheck it. Also in Line 100, there are two missing references.

Author Response

Please see attached

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

 This paper presents a multi-scale and collision-free path planning and implementation methodology enabling rapid deployment of robotised NDT with commercially available sensors.  Experimental results indicate the flexible and streamlined pipeline for robotic deployment, and demonstrate intuitive data visualisation to aid highly skilled operators in a wide field of industries. Specific comments are given as follows one by one.

1. The title of the article is very broad, which is unable to reflect the innovative highlights of the article. A good title enables readers to understand the basic content of this article accurately and quickly.

2. There are too many paragraphs in sections 1 and 2, which makes it difficult to  catch logical relationship of the content clarly.

3. It can be seen from the experiment that the author collected the data by an Intel D415 RGB/D camera, and used the collected data to test the method proposed in this paper. What are the details of the experiment? What conditions are the experiment conducted? Please give specific details.

4. Some key parameters are not mentioned in the proposed algorithm. The rationale on the choice of the particular set of parameters should be explained with more details. Have the authors experimented with other sets of values? What are the sensitivities of these parameters on the results? 

Author Response

please see attachment

Author Response File: Author Response.docx

Round 3

Reviewer 1 Report

The authors have corrected the express errors in the revised manuscript. All the questions have been answered in Authors' response to the reviewers. 

Back to TopTop