Exploiting the Internet Resources for Autonomous Robots in Agriculture

Round 1

Reviewer 1 Report

A good overview of equipment and technologies is made. However, there are a number of remarks:

1. The names in the application and pdf are different.

2. Baseline levels of productivity, cost and other indicators that are planned to be improved are not presented.

3. The levels of growth of target indicators due to the applied technologies and equipment are not presented.

4. In terms of training models, the required sample sizes for training, validation and testing are not presented. There is also no assessment of the adequacy of models and other indicators of accuracy.

Author Response

Response to Reviewer 2 Comments

 

Point 1

The names in the application and pdf are different.

Response 1

That’s right. We removed the middle name (Emilia) of the second author.

Point 2

Baseline levels of productivity, cost and other indicators that are planned to be improved are not presented.

Response 2

This article relies on the accepted advantages of using the new ICT technologies (especially cloud computing) and develops a control architecture for autonomous robots to take advantage of them. We do not try to demonstrate this accepted fact of the cloud advantages. In any case, we have included the following text to clarify this point (see new text in the introduction to section 3) as follows:

“The characteristics obtained are not compared with similar robotic systems due to the lack of such information in the literature. No publications report results in autonomous robots or weeding applications; therefore, it is difficult to compare, and the indicators have been geared towards general cloud computing and mobile robotics characteristics. Therefore, cross-validation has been carried out comparing the features of the autonomous robot with the general performance of the robot and the cloud communication. Productivity, cost, and other indicators of the presented architecture are those of the general use of cloud computing.”

 

Point 3

The levels of growth of target indicators due to the applied technologies and equipment are not presented.

Response 3

This comment is closely related to the previous one. This article presents a way of communicating autonomous robots with the cloud and leveraging all the features of a system connected to the cloud. In addition, the related literature needs examples; so a comparison with applied technologies is hard to do. We have tried to explain it in the previous comment.

 

 

 

Point 4

In terms of training models, the required sample sizes for training, validation and testing are not presented. There is also no assessment of the adequacy of models and other indicators of accuracy.

Response 4

3. Some parameters of the training procedure have been added in section 3.2 for the guiding vision system:

“The maize and wheat datasets were built with 450 and 125 labeled images, respectively. Data augmentation techniques (rotating, blurring, image cropping, and brightness changes) were used to increase the size of the datasets. For both crops, 80% of the data was destined for training, 10% for validation, and 10% for testing.”

and the Weed-meristem Vision System:

“The dataset used for training the weed/crop discrimination was generated in fields in several European countries. It contains 4000 images, 1000 of which are fully labeled. Distinctions are made according to the processing steps to be applied: weeds, grasses, and crops. In addition, the dataset was expanded to three times its original size through augmentation measures. Besides generating new training data, this enables robustness against changing environmental influences such as changing color representation, motion blur, and camera distortion. The Yolov7 network achieved a mean average precision (mAP) of 0.891 after 300 epochs of training. The dataset was divided into 80%, 10%, and 10% for training, validation, and testing subsets”.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors (will be shown to authors)

·      The paper “Exploiting the Internet resources for autonomous robots in agriculture” states that the world population has reached over 8 billion by year 2022, and estimate that the food production will need to increase by 70% by 2050, stressing thus the need of optimizing the available resources.

·      The paper presents the concept of Precision Agriculture (PA), the concept (introduced step by step since the late 1980s) of farm management founded on observation, measurement, and response to crop variability, it assembles different methods to manage variations in a farm to enhance crop yield, improve commercial profit and guarantee eco-environmental sustainability through the use of information and communication technology, automation and robots to

o  Monitor the crop growth

o  Predict the weather accurately

o  Perform optimal irrigation

o  Apply fertilizers smartly

o  Manage weeds and pests accurately

o  Test soil quality precisely

 

·      The authors claim to have presented an architecture to configure robots for agriculture using new ICT technologies-based Robot Operating System (ROS) which is operating system of a set of software libraries and tools that include drivers and advanced algorithms to help developer build robotic operation.

·      The necessary interfaces (bridges) are developed to establish communication with the Autonomous Vehicle, the Perception System, and the Laser-based Weeding Tool. Because of ROS versatility and its Publisher/Subscriber communication model, it is possible to adapt the messages to protocols commonly used in IoT, such as Message Queuing Telemetry Transport (MQTT).

·      The ROSLink protocol as an efficient and reliable communication link of ROS is used to establish an asynchronous communication link between users and the robots through cloud, however this link is not used for high level data messages for making intelligent robots scalable

·      The paper states that using FIWARE as the core could-based communication architecture has been presented open source software that provides free development modules that has the enablers developing and integrating solutions for smart agriculture

·      FIWARE is a curated platform fostered by the European Commission and European Information and Communication Technology industry for the development of Future Internet Applications. It offers interaction with the cloud using cloud services to provide a completely open, public, and free architecture and a collection of specifications that allows organizations (designers, service providers, businesses, etc.) to develop open and innovative applications and services on the Internet that fulfill their needs.

·      Also, the paper uses Kafka that is a robust distributed framework for streaming data that allows producers to send data and consumers to subscribe to and process such updates. Kafka enables the processing of streams of events/messages in a scalable and fault-tolerant manner so that the consumer can process data even after a producer has gone offline. Hadoop Distributed File System (HDFS) HDFS allows the download of batches of data at any time and replicates each data in 3 copies to prevent data loss.

·      The robotic systems are connected with the cloud through using specific data models to represent the different robotic elements, following the guidelines of FIWARE and its intelligent data models with the overall architecture as shown in Figure 6.

 Query 1.         The paper titled “Exploiting the Internet resources for autonomous robots in agriculture” describes the architecture of the paper, while readers of the paper are interested in how architecture can be used to get results from applications in some innovative research pursuits.

 

·      The system developed for this study has been tested with respect to wheat (Triticum 724 aestivum L.) and maize (Zea mays L.). The experiments are conducted in an experimental field located in Madrid, Spain (40°18'45".166, -3°28’51.096’’).

·      The experimental field consisted of two areas of 60 × 20 m² area, each divided into three sections of 20×20 m². In our study, the two areas grew wheat and maize. The crop rows are made at a distance of 0.10 m for wheat and 0.50 m for maize. The sections in one area were seeded in consecutive weeks, allowing us to conduct experiments in three-week windows. Figure 7 shows the experimental field and the distribution of the areas and sections. The climate of the study site is classified as a hot summer Mediterranean climate with an average annual temperature of 14.3 °C and precipitation of 473 mm.

·       

Is the subject matter presented in a comprehensive manner?

·      The 33-page paper is very extensively and descriptively presented by the authors in their efforts to support the title ““Exploiting the Internet resources for autonomous robots in agriculture”, and in fact full of technical details.

·      There is not enough theoretical support and related explanation to cover the so extensive details described, also there is functional or technical discussion

·      The contribution is not summarized, and the paper needs to have a flow and threading it needs to tempt the readers for reading it.

 

Are the references provided applicable and sufficient?

·      The authors take support from eleven (11) references most of them as reports and few recent journals with none from MDPI or from Science Direct only three from IEEE.

 Query 2.     The application scenario is presented, but no results are obtained for specific application and no comparison are drawn for cross validation to support “Exploiting the Internet resources for autonomous robots in agriculture” is of current research interest.

Author Response

Response to Reviewer 2 Comments

 

Point 1:

The paper “Exploiting the Internet resources for autonomous robots in agriculture” states that the world population has reached over 8 billion by year 2022, and estimate that the food production will need to increase by 70% by 2050, stressing thus the need of optimizing the available resources.

The paper presents the concept of Precision Agriculture (PA), the concept (introduced step by step since the late 1980s) of farm management founded on observation, measurement, and response to crop variability, it assembles different methods to manage variations in a farm to enhance crop yield, improve commercial profit and guarantee eco-environmental sustainability through the use of information and communication technology, automation and robots to

• Monitor the crop growth
• Predict the weather accurately
• Perform optimal irrigation
• Apply fertilizers smartly
• Manage weeds and pests accurately
• Test soil quality precisely

The authors claim to have presented an architecture to configure robots for agriculture using new ICT technologies-based Robot Operating System (ROS) which is operating system of a set of software libraries and tools that include drivers and advanced algorithms to help developer build robotic operation.

The necessary interfaces (bridges) are developed to establish communication with the Autonomous Vehicle, the Perception System, and the Laser-based Weeding Tool. Because of ROS versatility and its Publisher/Subscriber communication model, it is possible to adapt the messages to protocols commonly used in IoT, such as Message Queuing Telemetry Transport (MQTT).

The ROSLink protocol as an efficient and reliable communication link of ROS is used to establish an asynchronous communication link between users and the robots through cloud, however this link is not used for high level data messages for making intelligent robots scalable

The paper states that using FIWARE as the core could-based communication architecture has been presented open source software that provides free development modules that has the enablers developing and integrating solutions for smart agriculture

FIWARE is a curated platform fostered by the European Commission and European Information and Communication Technology industry for the development of Future Internet Applications. It offers interaction with the cloud using cloud services to provide a completely open, public, and free architecture and a collection of specifications that allows organizations (designers, service providers, businesses, etc.) to develop open and innovative applications and services on the Internet that fulfill their needs.

Also, the paper uses Kafka that is a robust distributed framework for streaming data that allows producers to send data and consumers to subscribe to and process such updates. Kafka enables the processing of streams of events/messages in a scalable and fault-tolerant manner so that the consumer can process data even after a producer has gone offline. Hadoop Distributed File System (HDFS) HDFS allows the download of batches of data at any time and replicates each data in 3 copies to prevent data loss.

The robotic systems are connected with the cloud through using specific data models to represent the different robotic elements, following the guidelines of FIWARE and its intelligent data models with the overall architecture as shown in Figure 6.

Query 1. The paper titled “Exploiting the Internet resources for autonomous robots in agriculture” describes the architecture of the paper, while readers of the paper are interested in how architecture can be used to get results from applications in some innovative research pursuits.

Response 1:

The following text has been inserted at the end of the introduction section to remark on the main objectives and advance the readers why the article is worth reading:

“This article presents an architecture to integrate new technologies and Internet trends in agricultural autonomous robotic systems and has two main objectives. The first objective is to provide an example of designing control architectures to connect autonomous robots to the cloud. It is oriented toward robot designers and gives significant technical details. The second objective is to disclose to farmers the advantages of integrating the new technologies in autonomous robots that can provide farmers with significant advantages regarding (i) data storage, which is a secure and efficient way to store, but also access, and share data, eliminating the need of physical storage and thus reducing the risk of data loss; (ii) scalability, which allow the farmers to be expanded or reduced their storage needs efficiently optimizing their resources, and (iii) analytics services, i.,e., analyze farmer own data for making informed decisions taking advantage of the AI tools available on the cloud. These are general advantages of using the cloud, but autonomous robots have great potential for collecting data and must facilitate communicating those data to the cloud.”

Regarding how to use the proposed architecture, it has been included in the new section 2.2.4 “Operation procedure” as follows:

“2.2.4 Operation procedure

To use the proposed architecture and method, the user must follow the method below.

- Creating the map: The user creates the field map following the procedure described in the MapBuilder module (see section 2.1.9).

- Creating the mission: The user creates the mission by selecting the mission’s initial point (Home garage) and destination field (study site).

- Sending the mission: The user selects the mission to be executed with the HMI (all defined missions are stored in the system) and sends it to the robot using the cloud services (see section 2.1.5).

- Executing the mission: The mission is executed autonomously following the scheme described in section 2.2.1. The user does not need to act except for alarms or collision situations detected and warned by the robot.

- Applying the treatment: When the robot reaches the crop field during the mission, it sends a command to activate the weeding tool, which works autonomously. The tool is deactivated when the robot performs the turns at the headland of the field and is started again when it re-enters. The implement was designed to work with its own sensory and control systems, only requiring the mobile platform for mobility and information when it must be activated/deactivated.

- Supervising the mission: When the robotic system reaches the crop field, it also sends a command to the IoT sensors, warning that the treatment is in progress. Throughout the operation, the Mission Supervisor module analyzes all the information collected by the cloud computing system, generated by both the robotic system and the IoT sensors. It evaluates if there is a possible deviation from the trajectory or risk of failure.

- Ending the mission: The mission ends when the robot reaches the last point in the field map computed by the MapBuilder. Optionally, the robot can stay in the field or return to the home garage. During the mission execution, the user can stop, resume and abort the mission through the HMI.”

Point 2

The system developed for this study has been tested with respect to wheat (Triticum aestivum L.) and maize (Zea mays L.). The experiments are conducted in an experimental field located in Madrid, Spain (40°18'45".166, -3°28’51.096’’).

The experimental field consisted of two areas of 60 × 20 m2 area, each divided into three sections of 20×20 m2. In our study, the two areas grew wheat and maize. The crop rows are made at a distance of 0.10 m for wheat and 0.50 m for maize. The sections in one area were seeded in consecutive weeks, allowing us to conduct experiments in three-week windows. Figure 7 shows the experimental field and the distribution of the areas and sections. The climate of the study site is classified as a hot summer Mediterranean climate with an average annual temperature of 14.3 °C and precipitation of 473 mm.

Is the subject matter presented in a comprehensive manner?

Response 2

The reviewer is right. We have rewritten the text as follows:

“The system developed for this study was tested in an experimental field located in Madrid, Spain (40°18'45".166, -3°28’51.096’’). The climate of the study site is classified as a hot summer Mediterranean climate with an average annual temperature of 14.3 °C and precipitation of 473 mm.

The experimental field consisted of 2 areas of 60 × 20 m² that grew wheat (Triticum aestivum L.), with crop rows at a distance of 0.10 m, and maize (Zea mays L.), with crop rows at a distance of 0.50 m, respectively. Each area was divided into three sections of 20 × 20 m². The sections in one area were seeded in consecutive weeks, allowing us to conduct experiments in three-week windows. Figure 7 shows the experimental field and the distribution of the areas and sections.”

Point 3

The 33-page paper is very extensively and descriptively presented by the authors in their efforts to support the title “Exploiting the Internet resources for autonomous robots in agriculture”, and in fact full of technical details.

Response 3

This is basically a technical paper and thus technical descriptions are needed. To make clear this objective, we have tried to clarify this fact at the end of the introduction section (see response 1).

Nevertheless, subsystem characteristics in tables have been reduced to the minimum to understand the procedure.

Point 4

There is not enough theoretical support and related explanation to cover the so extensive details described, also there is functional or technical discussion

Response 4

The paper presents details of the system used for integrating the architecture with the objective of stating the Material & Methods section. In any case, some technical details in the tables have been reduced.

Regarding technical discussion, we have included in section 3 the following text:

“The characteristics obtained are not compared with similar robotic systems due to the need for such information in the literature. No publications report results in weeding applications, so it is difficult to compare, and our indicators have been geared towards general cloud computing and mobile robotics characteristics. Therefore, cross-validation has been carried out comparing the features of the autonomous robot with the general performance of the robot and the cloud communication.”

Point 5

The contribution is not summarized, and the paper needs to have a flow and threading it needs to tempt the readers for reading it.

Response 5

The contributions have been indicated/reinforced in the abstract

“This study presents an architecture to integrate the different components of an autonomous robot that provides access to the cloud, taking advantage of the services provided regarding data storage, scalability, accessibility, data sharing, and data analytics. In addition, the study reveals the advantages of integrating new technologies into autonomous robots that can bring significant benefits to farmers.”

The “objectives and outcomes” at the end of the introduction section highlight two essential contributions: (i) to offer an example of an architecture for designers of autonomous robots and (ii) to disclose to farmers the potential offered by communicating autonomous robots with the cloud (See the text referred in Response 1).

The contributions have also been remarked in the Conclusions:

“In addition, using these types of architectures disclose to farmers the advantages of communicating autonomous robots with the cloud providing them with leading benefits for storing data securely and efficiently, eliminating physical storage, which reduces the risk of data loss. Data stored on the cloud also ease data access from everywhere and data sharing with other farmers or platforms. Moreover, services offered on the cloud are very flexible for hiring the actual storage needed at any time, optimizing farmer resources. Finally, farmers can use the analytics tools available on the cloud to make their own decisions. In any case, working on the cloud has an initial investment, which is usually quickly recovered.”

 

Point 6

The authors take support from eleven (11) references most of them as reports and few recent journals with none from MDPI or from Science Direct only three from IEEE.

Are the references provided applicable and sufficient?

Response 6

They are 16 journal articles; 1 book chapter, 3 conference articles; and 10 publications on the internet including websites and datasets.

Reference 21 is an MDPI publication;

References 11, 13, 14, 16, and 26 are ScienceDirect publications.

References 4, 6, and 12 are IEEE publications.

We understand the references are applicable and enough. We would be glad to study and discuss any specific reference if reported.

Point 7

Query 2. The application scenario is presented, but no results are obtained for specific application and no comparison are drawn for cross validation to support “Exploiting the Internet resources for autonomous robots in agriculture” is of current research interest.

Response 7

The introduction to section 3 in the previous version stated that

“The obtained features are not compared with similar robotic systems because of the lack of such information in the literature.”

So, we have tried to reinforce this fact in the text of section 3 as indicated in Response 4.

In addition, Conclusion section 4 has been extended with:

“The system has been tested in a field with two different crops. Data related to cloud communication and robot guidance algorithms have been collated. The communication performance is similar to that obtained using conventional mechanisms, so we benefit from using ROS and FIWARE without compromising performance“.

Author Response File: Author Response.pdf

Reviewer 3 Report

This article introduces in detail the functions that autonomous robots in agriculture can achieve, as well as the technical indicators of these modules. However, it does not address how these modules work together, the algorithmic processes used to solve specific problems, and the criteria for determining functional completion. So the article looks more like a product manual than a technical research paper. 

In the introduction section, the concept and function of the technology involved in the research object are introduced in detail, rather than technical comparisons of similar or related products. Therefore, it is not easy to judge the technical level of the system studied in the paper.

Author Response

Response to Reviewer 3 Comments

 

Point 1

This article introduces in detail the functions that autonomous robots in agriculture can achieve, as well as the technical indicators of these modules. However, it does not address how these modules work together, the algorithmic processes used to solve specific problems, and the criteria for determining functional completion. So the article looks more like a product manual than a technical research paper.

Response 1

How to use the proposed architecture and the relationship among modules have been indicated in the new section “2.2.4 - Operation procedure” as follows:

2.2.4. Operation procedure

To use the proposed architecture and method, the user must follow the method below.

“•        Creating the map: The user creates the field map following the procedure described in the MapBuilder module (see section 2.1.9).

• Creating the mission: The user creates the mission by selecting the mission’s initial point (Home garage) and destination field (study site).
• Sending the mission: The user selects the mission to be executed with the HMI (all defined missions are stored in the system) and sends it to the robot using the cloud services (see section 2.1.5).
• Executing the mission: The mission is executed autonomously following the scheme described in section 2.2.1. The user does not need to act except for alarms or collision situations detected and warned by the robot.
• Applying the treatment: When the robot reaches the crop field during the mission, it sends a command to activate the weeding tool, which works autonomously. The tool is deactivated when the robot performs the turns at the headland of the field and is started again when it re-enters. The implement was designed to work with its own sensory and control systems, only requiring the mobile platform for mobility and information when it must be activated/deactivated.
• Supervising the mission: When the robotic system reaches the crop field, it also sends a command to the IoT sensors, warning that the treatment is in progress. Throughout the operation, the Mission Supervisor module analyzes all the information collected by the cloud computing system, generated by both the robotic system and the IoT sensors. It evaluates if there is a possible deviation from the trajectory or risk of failure.
• Ending the mission: The mission ends when the robot reaches the last point in the field map computed by the MapBuilder. Optionally, the robot can stay in the field or return to the home garage. During the mission execution, the user can stop, resume and abort the mission through the HMI.”

Regarding the algorithms used, we have:

- IoT and cloud computing: They use commercial software packages mainly.

- Guiding vision system: It is based on known AI techniques relying on Real-time Object Detection detectors (YOLOv4) and a convolutional neural network for mobile vision applications (MobileNet) as indicated in the text. The guiding vision system in section 3.2 has been rewritten to better define these applications and improve the description of the Yolov4 and MobileNet training. That is:

“●        Guiding Vision System: This experiment was conducted in the treatment stage, where the crop was detected to adjust the errors derived from planning and the lack of precision of the maps. The models developed by Emmi et al. [9] were used to detect early-stage growth of both maize and wheat. YOLOv4, a real-time object detector based on a one-stage object detection network, was the base model for detecting maize, a wide-row crop [27]. The model was trained using a dataset acquired in an agricultural season before these tests using the same camera system [28]. Moreover, in the case of wheat, which is a narrow-row crop, a different methodology was applied through the use of segmentation models such as MobileNet, a convolutional neural network for mobile vision applications [29], trained using a dataset acquired in an agricultural season before these tests [30], with the same camera system. The detection of both crops was evaluated with regard to the GNSS positions collected manually for the different crop lines.

The maize and wheat datasets were built with 450 and 125 labeled images, respectively. Data augmentation techniques (rotating, blurring, image cropping, and brightness changes) were used to increase the size of the datasets. For both crops, 80% of the data was destined for training, 10% for validation, and 10% for testing.”

- AI-vision system:

The following text has been added to section 3.2 to complement the description:

“The dataset used for training the weed/crop discrimination was generated in fields in several European countries. It contains 4000 images, 1000 of which are fully labeled. Distinctions are made according to the processing steps to be applied: weeds, grasses, and crops. In addition, the dataset was expanded to three times its original size through augmentation measures. Besides generating new training data, this enables robustness against changing environmental influences such as changing color representation, motion blur, and camera distortion. The Yolov7 network achieved a mean average precision (mAP) of 0.891 after 300 epochs of training. The dataset was divided into 80%, 10%, and 10% for training, validation, and testing subsets.”

Finally, to determine the functionality of the proposed system, we performed some tests and experiments and concluded that we obtained similar results (cloud transfer speed, latency, delays, etc.) to ordinary cloud computing systems but took advantage of using ROS and FIWARE. The following text has been added to section 4.

“The system has been tested in a field with two different crops. Data related to cloud communication and robot guidance algorithms have been collated. The communication performance is similar to that obtained using conventional mechanisms, so we benefit from using ROS and FIWARE without compromising performance.”

Point 2

In the introduction section, the concept and function of the technology involved in the research object are introduced in detail, rather than technical comparisons of similar or related products. Therefore, it is not easy to judge the technical level of the system studied in the paper.

Response 2

This is basically a technical paper and thus technical descriptions are needed. To make clear this objective, we have tried to clarify this fact at the end of the introduction section (Objectives and outcomes).

“This article presents an architecture to integrate new technologies and Internet trends in agricultural autonomous robotic systems and has two main objectives. The first objective is to provide an example of designing control architectures to connect autonomous robots to the cloud. It is oriented toward robot designers and gives significant technical details. The second objective is to disclose to farmers the advantages of integrating the new technologies in autonomous robots that can provide farmers with significant advantages regarding (i) data storage, which is a secure and efficient way to store, but also access, and share data, eliminating the need of physical storage and thus reducing the risk of data loss; (ii) scalability, which allow the farmers to be expanded or reduced their storage needs efficiently optimizing their resources, and (iii) analytics services, i.,e., analyze farmer own data for making informed decisions taking advantage of the AI tools available on the cloud. These are general advantages of using the cloud, but autonomous robots have great potential for collecting data and must facilitate communicating those data to the cloud.”

Regarding technical comparison with similar developments, the introduction to section 3 in the previous version stated that

“The obtained features are not compared with similar robotic systems because of the lack of such information in the literature.”

So, we have tried to reinforce this fact in the text of section 3 as indicated in Point 4.

“The characteristics obtained are not compared with similar robotic systems due to the need for such information in the literature. No publications report results in weeding applications, so it is difficult to compare, and our indicators have been geared towards general cloud computing and mobile robotics characteristics. Therefore, cross-validation has been carried out comparing the features of the autonomous robot with the general performance of the robot and the cloud communication.”

In addition, Conclusion Section 4 has been extended with (also reported in Response 1):

“The system has been tested in a field with two different crops. Data related to cloud communication and robot guidance algorithms have been collated. The communication performance is similar to that obtained using conventional mechanisms, so we benefit from using ROS and FIWARE without compromising performance.“

 

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Pls see review attached.

Comments for author File: Comments.pdf

Author Response

Query 1. The paper titled “Exploiting the Internet resources for autonomous robots in agriculture” describes the architecture of the paper, while readers of the paper are interested in how architecture can be used to get results from applications in some innovative research pursuits – No results are produced

How to design the architecture has been included in section 2—figures 3 and 5 illustrate the general computing architecture. The methodology has been included in section 2.2.1.

How the architecture can be used is explained in Section 2.1.5-Sequence of action and Section 2.2.5-Operational procedure.

The conclusion section has been rewritten to highlight the advantages of this architecture for developers and users (farmers). The benefits of the proposed architecture are also highlighted in the conclusion section.

 

Query 2. The application scenario is presented, but no results are obtained for specific application and no comparison are drawn for cross validation to support “Exploiting the Internet resources for autonomous robots in agriculture” is of current research interest – No results are obtained

Results based on experiments with two crops are reported in Section 3. The experiments report traffic information, rate of dropped messages, average delay of messages, overheads, etc. These values are in the range of the values get with connection to the cloud using conventional mechanisms. This demonstrates that our approach is as good as the conventional one but easier to implement using tools provided by ROS and FIWARE. The explanation of the experiments has been extended with a figure.