Advanced Power Converters and Learning in Diverse Robotic Innovation: A Review

Round 1

Reviewer 1 Report

The manuscript presents an overview of power electronic devices with applications in robotics, as well as related training. Various topologies of electronic converters, the application of various artificial intelligence techniques for training and efficient use in industry, and also the possibilities of energy efficiency in robot control are successively examined. The manuscript is on a very topical subject and has great potential for development. My main observations, questions and comments are as follows:

- since many symbols and abbreviations are used in the text, I recommend the authors to add a list of symbols used at the beginning or end of the manuscript;

- There is no discussion section where comments, analysis and conclusions from the review can be made, as well as trends for the development of the field can be outlined;

- it would be useful to comment on the economic aspect of the optimal control of robots in different applications and to make recommendations on the most suitable structures to be implemented.

Author Response

Dear Reviewer,

We would like to express our gratitude for taking the time to review our manuscript titled " Advanced Power Converters and Learning in Diverse Robotic Innovation: A Review". Your constructive feedback is greatly appreciated, and we have carefully considered your comments. Below are our responses to your specific observations, questions, and comments:

Comment 1: Since many symbols and abbreviations are used in the text, I recommend the authors to add a list of symbols used at the beginning or end of the manuscript.

Response: Thank you for the suggestion. We have now included a list of symbols and abbreviations at the end of the manuscript Page 20, Line 680, to improve readability and comprehension.

Comment 2: There is no discussion section where comments, analysis and conclusions from the review can be made, as well as trends for the development of the field can be outlined.

Response: Thank you for the comment. We have incorporated a discussion section in the revised manuscript Page 17, Line 560, to Page 18, Line 614, where we provide analysis, conclusions, and outline trends in the field.

Discussion and Future Trends in Robotics

From the above review on various critical aspects of robotics, including the role of advanced power converters, learning approaches, and energy harvesting methods, it's evident that the field of robotics is experiencing significant advancements that are reshaping the landscape of robotic systems. The review on power converters emphasized their pivotal role in robotics. Voltage regulation, current management, waveform shaping, and energy efficiency are key aspects of power converters. These capabilities are essential for optimizing the performance and energy efficiency of robotic systems. The trend in power converter development is towards greater efficiency and adaptability. As robotics applications become more diverse and demanding, the need for advanced power converters that can handle different voltage requirements and provide precise control over current and waveforms is increasing. Additionally, as energy efficiency and sustainability gain importance, power converters are evolving to minimize energy losses and contribute to prolonged operational times. Moreover, various types of power converters used in robotics, from DC-DC converters to matrix converters and soft-switching converters are identified. These diverse converter types cater to different robotic applications and requirements. The trend in this field is towards specialization and innovation in converter design. With the growing demand for robotics in various industries, specialized converters that meet the specific needs of each application are expected to become more prevalent. Further, the review of articles on learning approaches highlighted the crucial role of ML and AI in enhancing robotic perception and decision-making. Reinforcement learning, supervised learning, and unsupervised learning are key paradigms in this field. The trend in learning approaches is towards increased autonomy and adaptability. Robots are becoming more capable of perceiving and interpreting their environments, making informed decisions, and adapting to dynamic situations. As AI algorithms continue to advance, we can expect further breakthroughs in robotic autonomy and adaptability. Lastly, the review of articles on energy harvesting underlines the importance of energy sources such as solar, thermoelectrical, and supercapacitors in powering robotic systems. The trend in energy harvesting is towards sustainability and efficiency. As the world shifts towards greener energy solutions, the integration of renewable energy sources into robotics aligns with environmental and economic considerations. Furthermore, the development of fuel cell technology presents promising opportunities for larger robotic systems like UAVs, offering higher energy density and longer operational times.

Overall Trends

Driven by the advances in power converters, learning approaches, and energy harvesting methods, some of the key trends can be defined as follows:

• Efficiency and Sustainability: Efficiency and sustainability are at the forefront of robotic system development. Power converters and energy harvesting methods are being designed to minimize energy wastage and utilize renewable energy sources, contributing to more sustainable and eco-friendlier robotics.
• Specialization: With robotics finding applications in a wide range of industries, specialized power converters and learning algorithms are on the rise. These specialized solutions cater to the unique demands of each application, whether it's in healthcare, manufacturing, or autonomous vehicles.
• Increased Autonomy: Learning approaches, particularly reinforcement learning and AI, are empowering robots to become more autonomous and adaptable. This trend is particularly evident in fields like autonomous driving, where robots are learning to navigate complex environments with minimal human intervention.
• Integration of Efficient Energy: The integration of energy sources into robotic systems is a growing trend. Solar, thermoelectrical, and supercapacitors are increasingly being used to power robots, reducing their reliance on traditional energy sources and contributing to longer operational times.
• Fuel Cell Technology: Fuel cell technology, such as polymer electrolyte membrane fuel cells, holds promise for larger robotic systems. They offer higher energy density, longer operational times, and can be a game-changer for applications like UAVs.

Comment 3: It would be useful to comment on the economic aspect of the optimal control of robots in different applications and to make recommendations on the most suitable structures to be implemented.

Response: Thank you for this suggestion. In the revised manuscript, we have expanded on the economic aspects of optimal robot control in Page 19, Line 615-657, and provided recommendations for suitable control structures in various applications.

Economic Aspects of Optimal Control in Robotic Applications

The economic aspect of optimal control in robotic applications is a critical consideration that can significantly impact the viability and adoption of robotic systems across various industries. The economic factors to be taken into account when implementing optimal control in robotic applications include initial costs, operational efficiency, maintenance, and return on investment.

• Initial Costs: The choice of optimal control structures can have a substantial impact on initial costs. For instance, more complex control algorithms or hardware setups may require a larger upfront investment. However, it's essential to balance initial costs with long-term benefits, such as increased productivity, reduced labor costs, and improved product quality.
• Operational Efficiency: Optimal control can enhance operational efficiency by improving accuracy, reducing cycle times, and minimizing energy consumption. The economic benefit lies in increased productivity and reduced operating expenses over time. For example, in manufacturing, optimal control can lead to higher throughput, lower scrap rates, and energy savings, all of which contribute to cost reduction.
• Maintenance: The choice of control structures can also impact maintenance costs. Complex control systems may require more frequent maintenance and specialized expertise, which can increase operating expenses. Simpler control systems with predictive maintenance capabilities can help reduce downtime and maintenance costs.
• Return on Investment (ROI): The economic feasibility of optimal control largely depends on the ROI it offers. While investing in advanced control structures may have a higher upfront cost, it's crucial to evaluate how quickly these investments will pay off through increased productivity and cost savings. Factors like the expected lifespan of the robotic system, industry-specific demands, and potential market growth should be considered when calculating ROI.

Recommendations on the most suitable control structures to be implemented should be made on a case-by-case basis, considering the specific requirements and constraints of the application. However, some general guidelines can be helpful:

• Customization: The optimal control structure should align with the specific needs of the application. Customizing the control system to the unique demands of the task can lead to more efficient and cost-effective solutions.
• Scalability: Consider control structures that can be scaled as needed. This allows for flexibility in adapting to changes in production volume or complexity, ensuring that the investment remains economically viable over time.
• Energy Efficiency: Opt for control structures that prioritize energy efficiency, as this not only reduces operational costs but also aligns with sustainability goals.
• Integration: Ensure that the chosen control structure integrates seamlessly with existing systems and processes. Compatibility can minimize disruptions and reduce integration costs.
• Predictive Maintenance: Implement predictive maintenance capabilities to proactively address issues before they lead to costly downtime. This can extend the lifespan of the robotic system and reduce maintenance expenses.

Author Response File: Author Response.docx

Reviewer 2 Report

The review report of the paper is in the attached file.

Comments for author File: Comments.pdf

Author Response

Dear Reviewer,

We would like to express our gratitude for taking the time to review our manuscript titled " Advanced Power Converters and Learning in Diverse Robotic Innovation: A Review". Your constructive feedback is greatly appreciated, and we have carefully considered your comments. Below are our responses to your specific observations, questions, and comments:

Review Report 2:

Comment 1: It is necessary to correct the numbering of the works in the list of references so that they intervene in the work in ascending order. For example, in lines 205 and 206 from paper 72 it goes to paper 118, and in line 413 paper 94 is cited.  

Response: Thank you for this suggestion. We have reviewed and corrected the numbering of references to ensure they are in ascending order throughout the manuscript.

Comment 2: The transfer of electrical energy from the source to the robot through electromagnetic waves provides more degrees of freedom for the robot but the energy efficiency is lower than using the classical system by galvanically connecting the source to the robot. For this reason I think that determining how to power the robots is very important. If the robot is fixed, i.e., not moving, feeding it through galvanic contact with the source is the most efficient. In the case of drones, for example, this power mode is not possible, as it is mandatory to power the robot through electromagnetic waves or using batteries. As a result, I believe that it is not without interest that the paper be completed with a classification of robots according to the way in which their power supply is ensured.

Response: Thank you for this insightful comment. We've addressed your concern in the revised manuscript Page, 14, Line 422, to Page 15, Line 479, which now includes a subsection on the classification of robots based on their power supply methods.

Classification of Robots by Power Supply

Robots can be classified into different categories based on their power supply methods. The choice of power supply is a critical consideration in the design and operation of robots, as it impacts their mobility, energy efficiency, and adaptability to specific applications. Here, we categorize robots into four main groups based on their power supply methods:

• Galvanic Contact-Powered Robots: Galvanic contact-powered robots are stationary or fixed in place, receiving power through direct electrical connections, typically via cords or cables. This method offers high energy efficiency as there is minimal energy loss during power transmission. They are commonly used in industrial settings, such as manufacturing lines and CNC machines, where tasks do not require mobility. The advantages of galvanic contact power include high energy efficiency, continuous operation, and minimal downtime. However, these robots have limited mobility and range due to their fixed power sources.
• Electromagnetic Wave-Powered Robots: Electromagnetic wave-powered robots receive their energy through wireless transfer methods, often using electromagnetic waves like radio waves or microwaves. This approach provides more degrees of freedom for the robot, making it suitable for applications that require mobility, flexibility, or remote operation. Drones and autonomous vehicles are examples of robots that often use electromagnetic wave power transfer. While offering enhanced mobility and adaptability to changing environments, this method may have lower energy efficiency compared to galvanic contact. Potential considerations include lower energy efficiency, the risk of interference, and limitations in energy transfer distance.
• Battery-Powered Robots: Battery-powered robots are equipped with onboard batteries that store and supply electrical energy. They are highly mobile and versatile, suitable for a wide range of applications, including drones, robotic vacuum cleaners, and autonomous rovers. The key advantages of battery power include mobility, autonomy, and the ability to operate in diverse environments. However, they face considerations such as limited battery life, the need for recharging or battery replacement, and challenges related to battery weight and size.
• Hybrid Systems: Hybrid systems combine multiple power supply methods to leverage the strengths of each. For example, a robot may have a primary battery power source and employ energy harvesting techniques or wireless charging to extend its operational capabilities. These systems are found in various applications, including medical robots, solar-powered drones, and remote environmental monitoring robots. Their advantages include enhanced flexibility, extended operational range, and increased energy efficiency. However, they involve complex system integration, potential trade-offs, and the need for advanced power management.
• Efficiency Considerations

Each power supply method has its unique advantages and limitations, and the choice of power source depends on the specific requirements of the robot's application. Efficiency considerations play a vital role in this decision-making process. Here are some key efficiency factors to keep in mind:

• Energy Efficiency: Galvanic contact power supply is highly efficient, while electromagnetic wave power transfer methods may have lower efficiency due to energy losses during wireless transmission.
• Mobility vs. Efficiency: Battery-powered robots offer mobility and autonomy but may have limited operational time between recharges or battery replacements. Electromagnetic wave-powered robots provide mobility but often at the expense of energy efficiency.
• Hybrid Approaches: Hybrid systems allow for a balance between mobility and energy efficiency by combining power supply methods. For example, a drone with a primary battery source can use solar panels for energy harvesting during flight, extending its operational time.
• Application-Specific Considerations: The choice of power supply should align with the specific requirements of the robot's intended application, considering factors such as mobility, energy demand, and operational environment.

Comment 3: Chapter 2 presents the progress achieved in the realization of converters used in the construction of robots. I believe that this chapter can be reduced in size because the data provided in table 1 and 2, as well as figures 1, 2 are conclusive regarding the existing progress in the realization of static converters.  

Response: We appreciate the feedback. While we acknowledge that the data in tables and figures may appear conclusive, we believe that the accompanying textual content in Section 2 adds significant value to our work. It enables readers to comprehend the rationale behind the data and appreciate the nuances and complexities of the subject matter. Furthermore, it provides a foundation for the subsequent sections that build upon the insights established in Section 2.

Comment 4: The DC – AC converter is called an inverter (2.2.2. page 4), and the AC-DC converter is not called an inverter (2.2.3. page 4). What is the justification for the different name?

Response: Thank you for the comment. The different names for DC-AC converters and AC-DC converters, commonly referred to as "inverter" and "rectifier" respectively, are because of their primary functions and the way they operate. Here's a brief explanation for the distinction in names:

Inverter (DC to AC Converter):

An inverter is designed to convert direct current (DC) into alternating current (AC). This is crucial in various applications where AC power is required, such as in household appliances, solar power systems, and electric vehicles. Inverters take the steady, unidirectional flow of electric current (DC) and transform it into the alternating flow commonly used in most electrical devices. This is why it's called an "inverter" as it inverts the current's direction and properties.

Rectifier (AC to DC Converter):

A rectifier serves the opposite purpose; it converts alternating current (AC) into direct current (DC). This is essential for many electronic devices that operate on DC power, like computers and smartphones. Rectifiers take the alternating flow of electric current and "rectify" it, which means they convert it into a unidirectional current. This is typically achieved using diodes.

The key difference in naming reflects their distinct functions and the specific task each device performs. These names make it easier to understand and distinguish between the two types of converters based on their primary function.

 

Author Response File: Author Response.docx

Reviewer 3 Report

Dear Authors,

please refer to the attached document. Thanks!

Comments for author File: Comments.pdf

I have no comments on English language and its style, so this reviewer recommends a minimum control of English language.

Author Response

Dear Reviewer,

We would like to express our gratitude for taking the time to review our manuscript titled " Advanced Power Converters and Learning in Diverse Robotic Innovation: A Review". Your constructive feedback is greatly appreciated, and we have carefully considered your comments. Below are our responses to your specific observations, questions, and comments:

Comment 1: Although in general, the aim of the paper is clear, the abstract should be elegant and well-written highlighting points as the novelty respect the state of art and highlighting their results. It is opinion of this reviewer that the abstract requires a restructuring to have a better fluency. It should be better organized.

Response: Thank you for the suggestion. We have improved the abstract to highlight the novelty and results more effectively.

Abstract: This paper provides a comprehensive review of the integration of advanced power management systems and learning techniques in the field of robotics. It identifies the critical roles these areas play in reshaping the capabilities of robotic systems across diverse applications. To begin, it highlights the significance of efficient power usage in modern robotics. The paper explains how advanced power converters effectively control voltage, manage current, and shape waveforms, thereby optimizing energy utilization. These converters ensure that robotic components receive the precise voltage levels they require, leading to improved motor performance and enabling precise control over motor behavior. Consequently, this results in extended operational times and increased design flexibility. Furthermore, the review explores the integration of learning approaches, emphasizing their substantial impact on robotic perception, decision-making, and autonomy. It discusses the application of techniques such as reinforcement learning, supervised learning, and unsupervised learning, showcasing their applications in areas like object recognition, semantic segmentation, sensor fusion, and anomaly detection. By utilizing these learning methods, robots become more intelligent, adaptable, and capable of autonomous operation across various domains. By examining the interaction between advanced power management and learning integration, this review anticipates a future where robots operate with increased efficiency, adapt to various tasks, and drive technological innovation across a wide range of industries.

Comment 2: The keywords are appropriate. However, this is only a reviewer's opinion, it is better to use keywords that better highlight the focus of the paper. Authors have the possibility to insert a maximum of five keywords and no six keywords.

Response: Thank you for the suggestion. We have revised the keywords to better align with the paper's focus.

Comment 3: I have no comments on English language and its style so this reviewer recommends a minimum control of English language.

Response: Thank you for the suggestion. Steps were taken to keep a minimum control of English language as suggested by the reviewer.

Comment 4: The authors need to mention and highlight what the current paper adds to the discussion, and in what way it is different from other reviews in this field. In other words, highlight the novelty in this field.

Response: Thank you for the suggestion. In the revised manuscript, we have added the novelty and contributions of our paper compared to existing reviews in the field in Page 3, Line 89-109.

The novel aspects of this review article are as follows:

• The review discusses the integration of various machine learning and AI methods, including reinforcement learning, supervised learning, unsupervised learning, and Bayesian techniques, showcasing the diverse approaches being used to enhance robotic innovation.
• It explores the use of state-of-the-art energy harvesting technologies, highlighting the latest developments in solar energy for robotic applications.
• The review discusses supercapacitors as a fast-charging alternative to batteries, emphasizing their structural flexibility and the potential for integrating them into robotic systems.
• The review mentions the potential use of polymer electrolyte membrane fuel cells for higher energy density in large robots like UAVs, presenting hydrogen fuel as a promising and economical option for renewable energy in robotics.

Comment 5: In your interest, in the case of review manuscript please, you should put much more figures, tables, diagrams in each section of the review. They are need in order to make the review more interesting for the reader.

Response: Thank you for the suggestion. We value your perspective, but due to time constraints and the impending review deadline, we may not be able to incorporate more figures, tables, and diagrams at this stage. Further, we believe the current content is adequate to convey the main points effectively.

Comment 6: The word “Figure 1”is reported only in the caption page 3 of 25 but it is not reported in the text. Please check the whole paper. Thanks!  

Response: Thank you for the suggestion. We have reviewed the entire manuscript to ensure consistency in figure citations.

Comment 7: The potential impact of this work should be better presented in the manuscript.

Response: Thank you for the suggestion. We have incorporated a new section addressing the potential impact of this work in Page 17, Line 560, to Page 18, Line 614.

Discussion and Future Trends in Robotics

From the above review on various critical aspects of robotics, including the role of advanced power converters, learning approaches, and energy harvesting methods, it's evident that the field of robotics is experiencing significant advancements that are reshaping the landscape of robotic systems. The review on power converters emphasized their pivotal role in robotics. Voltage regulation, current management, waveform shaping, and energy efficiency are key aspects of power converters. These capabilities are essential for optimizing the performance and energy efficiency of robotic systems. The trend in power converter development is towards greater efficiency and adaptability. As robotics applications become more diverse and demanding, the need for advanced power converters that can handle different voltage requirements and provide precise control over current and waveforms is increasing. Additionally, as energy efficiency and sustainability gain importance, power converters are evolving to minimize energy losses and contribute to prolonged operational times. Moreover, various types of power converters used in robotics, from DC-DC converters to matrix converters and soft-switching converters are identified. These diverse converter types cater to different robotic applications and requirements. The trend in this field is towards specialization and innovation in converter design. With the growing demand for robotics in various industries, specialized converters that meet the specific needs of each application are expected to become more prevalent. Further, the review of articles on learning approaches highlighted the crucial role of ML and AI in enhancing robotic perception and decision-making. Reinforcement learning, supervised learning, and unsupervised learning are key paradigms in this field. The trend in learning approaches is towards increased autonomy and adaptability. Robots are becoming more capable of perceiving and interpreting their environments, making informed decisions, and adapting to dynamic situations. As AI algorithms continue to advance, we can expect further breakthroughs in robotic autonomy and adaptability. Lastly, the review of articles on energy harvesting underlines the importance of energy sources such as solar, thermoelectrical, and supercapacitors in powering robotic systems. The trend in energy harvesting is towards sustainability and efficiency. As the world shifts towards greener energy solutions, the integration of renewable energy sources into robotics aligns with environmental and economic considerations. Furthermore, the development of fuel cell technology presents promising opportunities for larger robotic systems like UAVs, offering higher energy density and longer operational times.

Overall Trends

Driven by the advances in power converters, learning approaches, and energy harvesting methods, some of the key trends can be defined as follows:

• Efficiency and Sustainability: Efficiency and sustainability are at the forefront of robotic system development. Power converters and energy harvesting methods are being designed to minimize energy wastage and utilize renewable energy sources, contributing to more sustainable and eco-friendly robotics.
• Specialization: With robotics finding applications in a wide range of industries, specialized power converters and learning algorithms are on the rise. These specialized solutions cater to the unique demands of each application, whether it's in healthcare, manufacturing, or autonomous vehicles.
• Increased Autonomy: Learning approaches, particularly reinforcement learning and AI, are empowering robots to become more autonomous and adaptable. This trend is particularly evident in fields like autonomous driving, where robots are learning to navigate complex environments with minimal human intervention.
• Integration of Efficient Energy: The integration of energy sources into robotic systems is a growing trend. Solar, thermoelectrical, and supercapacitors are increasingly being used to power robots, reducing their reliance on traditional energy sources and contributing to longer operational times.
• Fuel Cell Technology: Fuel cell technology, such as polymer electrolyte membrane fuel cells, holds promise for larger robotic systems. They offer higher energy density, longer operational times, and can be a game-changer for applications like UAVs.

Comment 8: I propose adding a list of abbreviations and symbols at the end of the paper before the list of  references.

Response: Thank you for the suggestion. We have now included a list of symbols and abbreviations at the end of the manuscript Page 20, Line 680, to improve readability and comprehension.

Comment 9: Please, highlight the strength, weaknesses, opportunities and threats were derived from yours study.

Response: Thank you for this suggestion. In the revised manuscript, we have incorporated a new section highlighting the strength, weaknesses, opportunities, threats, and future possibilities in Page 17, Line 560, to Page 19, Line 657.

Comment 10: Some following references are good for your paper if you wish to consider them:

• Barrile, V.; Simonetti, S.; Citroni, R.; Fotia, A.; Bilotta, G. Experimenting Agriculture 4.0 with Sensors: A Data Fusion Approach between Remote Sensing, UAVs and Self-Driving Tractors. Sensors 2022, 22, 7910. For agriculture and data fusion
• Citroni, R.; Di Paolo, F.; Livreri, P. A Novel Energy Harvester for Powering Small UAVs: Performance Analysis, Model Validation and Flight Results. Sensors 2019, 19, 1771 for how to extend the flight time of UAV and the concept of energy harvesting.

Response: Thank you for the recommended references. We have reviewed these references and, where appropriate, cited them in the manuscript Ref [209]: Page 12, Line 395-399, and Ref [223], Page 17, Line 511-517.

Comment 11: The review does not fully address the limitations and challenges. A discussion of these limitations and how they can be overcome in future work would strengthen the paper.  

Response: Thank you for this suggestion. In the revised manuscript, we have included a section Page 17, Line 560, to Page 19, Line 657 that discusses the limitations and challenges and suggests ways to overcome them.

Comment 12: The conclusion section should include also the main achievements and pioneering research as well as mention future directions more tangibly.

Response: Thank you for this feedback. In the revised conclusion section, we have highlighted the main achievements, pioneering research, and provided more tangible future directions.

In conclusion, this paper has effectively highlighted the significant impact of advanced power management systems and the integration of learning techniques on the field of robotics. The convergence of efficient power utilization and learning-based control systems has introduced a new era of intelligent, adaptable, and innovative robotic systems, revealing notable achievements and innovative research. One of the key aspects identified in the review is the successful implementation of various energy harvesting methods, such as solar energy, thermoelectrical generation, and supercapacitors, in powering robotic systems. These methods have demonstrated their potential to reduce reliance on conventional power sources and increase the endurance and adaptability of robots, making them well-suited for a wide range of applications. Furthermore, the review explored the learning approaches in robotics and how these techniques have transformed the decision-making processes. This has enabled robots to operate autonomously, navigate through intricate environments, and interact intelligently with their surroundings, significantly enhancing their capabilities. Further, throughout the review process it is identified that the synergies between advanced power management and learning integration for robotic systems are expected to further revolutionize various sectors, such as industrial automation, healthcare, agriculture, and disaster response. The integration of wireless power transfer technology in UAVs is foreseen to hold extended flight times and increased operational efficiency, opening new horizons in aerial robotics. In this developing landscape, the interaction between advancements in the fields of power management, machine learning, and robotics will be crucial in realizing the full potential of robotic systems.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Authors revised manuscripts according to my notes and comments.

Reviewer 3 Report

Dear Authors,

please refer to the attached document. Thanks!

Comments for author File: Comments.pdf