ENVOn: An ontology of 3D environment where a simulated manipulation task takes place

Tracking #: 3323-4537

Yingshen Zhao1
Arkopaul Sarkar
Linda Elmhadhbi
Mohamed Hedi KARRAY

Responsible editor: 
Guest Editors SW for Industrial Engineering 2022

Submission type: 
Full Paper
Thanks to the advent of robotics in shopfloor and warehouse environments, control rooms need to seamlessly exchange information regarding the dynamically changing 3D environment to facilitate tasks and path planning for the robots. Adding to the complexity, this type of environment is heterogeneous as it includes both free space and various types of rigid bodies (equipment, materials, humans etc.). At the same time, 3D environment-related information is also required by the virtual applications (e.g., VR techniques) for the behavioral study of CAD-based product models or simulation of CNC operations. In past research, information models for such heterogeneous 3D environments are often built without ensuring connection among different levels of abstractions required for different applications. To address such multiple points of view and modelling requirements for 3D objects and environments, this paper proposes an ontology model that integrates the contextual, topologic, and geometric information of both the rigid bodies and the free space. The ontology provides an evolvable knowledge model that can support simulated task-related information in general. This ontology aims to greatly improve interoperability as a path planning system (e.g., robot) and will be able to deal with different applications by simply updating the contextual semantics related to some targeted application while keeping the geometric and topological models intact by leveraging the semantic link among the models.
Full PDF Version: 

Minor Revision

Solicited Reviews:
Click to Expand/Collapse
Review #1
Anonymous submitted on 23/Dec/2022
Review Comment:

I am happy with the authors' responses to my original comments and recommend accept.


There is one "typo" that perhaps has snuck in, relating to the definition of OrientedBoundingBox. I suggested, and the authors agree in their rebuttal, to use Point3D instead of AxisPlacement3D to represent the min/max points. However this change does not appear in table 4, where the axiom still uses AxisPlacement3D. As I intended to say in my original comment, this is not wrong but seems overkill once the OrientedBoundingBox receives a LocalReferenceFrame which includes a transform to the world frame.


Review #2
By Andrea Orlandini submitted on 08/Mar/2023
Review Comment:

This is a new version of a paper submitted and previously that I already reviewed.

All the reviewers agreed in considering the paper not ready for publication and requiring further work.

In this regard, the authors made a good work to enhance the the manuscript that it is now improved. Most of the raised issues were addressed considering the raised comments.

In general, the paper now seems to have a better shape and it provides what seems to be a good contribution.

In this regard, I feel the paper suitable for publication.

Review #3
Anonymous submitted on 13/Mar/2023
Minor Revision
Review Comment:

The revised paper has been improved for originality and significance of the results, but the quality of writing can still be enhanced. The online resources have been completed and better documented.
Here below, you can find comments related to specific parts and statements.

1) Section 2 would benefit a more structured organization.

2) Sect.4.1.1. It was already commented that basic mathematical concepts (e.g., Vector3D, RotationMatrix3D, AffineTransformation
Matrix3D) are defined in a verbose way. I'm not satisfied with the answer, since this poses a serious problem for the usability of the ontology, even if calculations and instatiations can be automated or inferred. This is simply not a proper way to design an ontology. Even an ontology automatically generated from STEP would look better with respect to these geometric definitions, and this is critical to justify the development of a new ontology from scratch (i.e. ENVOn). Performance and data storage assessments would also highlight the relevance of this issue.

3) Sect.4.3.1. Tripartite relations are not admitted in OWL, but still there are modelling patterns that enable to represent time dependent relations. For instance, have a look at the OWL version of DOLCE. Since the ambition of the ENVOn ontology is to properly characterize the environment, then it would be expected that also time-variant representations can be handled. The sentence "We leave it to the application developers to handle time while assigning qualities and functions to rigid bodies and areas." is quite surprising.

4) Some further remarks:
- What's the actual meaning of "unique" in "unique contributions" in Sect.1?
- "Section 0" is mentioned at the end of Sect.1.
- Footnote 1 is a broken link and it seems to be a resource in French.
- the text is generally verbose and makes the article too long
- colloquial expressions are used (e.g. "which is also a reason why it is one of the scenarios used in section 5.1 to validate our contribution"; "we can now introduce the key motivations for the works presented here")
- quotation marks should be avoided as much as possible if it's not an actual quotation (e.g. Even a "simple" task; "low level", "high level").
- It would be better to avoid starting a sentence with "To"
- Fig.11 has low resolution.