Robotics

18 pages, 1837 KiB

Open AccessArticle

Real-Time Dolphin Whistle Detection on Raspberry Pi Zero 2 W with a TFLite Convolutional Neural Network

by Rocco De Marco, Francesco Di Nardo, Alessandro Rongoni, Laura Screpanti and David Scaradozzi

Robotics 2025, 14(5), 67; https://doi.org/10.3390/robotics14050067 - 19 May 2025

Viewed by 121

The escalating conflict between cetaceans and fisheries underscores the need for efficient mitigation strategies that balance conservation priorities with economic viability. This study presents a TinyML-driven approach deploying an optimized Convolutional Neural Network (CNN) on a Raspberry Pi Zero 2 W for real-time [...] Read more.

The escalating conflict between cetaceans and fisheries underscores the need for efficient mitigation strategies that balance conservation priorities with economic viability. This study presents a TinyML-driven approach deploying an optimized Convolutional Neural Network (CNN) on a Raspberry Pi Zero 2 W for real-time detection of bottlenose dolphin whistles, leveraging spectrogram analysis to address acoustic monitoring challenges. Specifically, a CNN model previously developed for classifying dolphins’ vocalizations and originally implemented with TensorFlow was converted to TensorFlow Lite (TFLite) with architectural optimizations, reducing the model size by 76%. Both TensorFlow and TFLite models were trained on 22 h of underwater recordings taken in controlled environments and processed into 0.8 s spectrogram segments (300 × 150 pixels). Despite reducing model size, TFLite models maintained the same accuracy as the original TensorFlow model (87.8% vs. 87.0%). Throughput and latency were evaluated by varying the thread allocation (1–8 threads), revealing the best performance at 4 threads (quad-core alignment), achieving an inference latency of 120 ms and sustained throughput of 8 spectrograms/second. The system demonstrated robustness in 120 h of continuous stress tests without failure, underscoring its reliability in marine environments. This work achieved a critical balance between computational efficiency and detection fidelity (F1-score: 86.9%) by leveraging quantized, multithreaded inference. These advancements enable low-cost devices for real-time cetacean presence detection, offering transformative potential for bycatch reduction and adaptive deterrence systems. This study bridges artificial intelligence innovation with ecological stewardship, providing a scalable framework for deploying machine learning in resource-constrained settings while addressing urgent conservation challenges. Full article

(This article belongs to the Section Sensors and Control in Robotics)

► Show Figures

Graphical abstract

22 pages, 4481 KiB

Open AccessArticle

Hybrid Deep Learning Framework for Eye-in-Hand Visual Control Systems

by Adrian-Paul Botezatu, Andrei-Iulian Iancu and Adrian Burlacu

Robotics 2025, 14(5), 66; https://doi.org/10.3390/robotics14050066 - 19 May 2025

Viewed by 137

Abstract

This work proposes a hybrid deep learning-based framework for visual feedback control in an eye-in-hand robotic system. The framework uses an early fusion approach in which real and synthetic images define the training data. The first layer of a ResNet-18 backbone is augmented [...] Read more.

This work proposes a hybrid deep learning-based framework for visual feedback control in an eye-in-hand robotic system. The framework uses an early fusion approach in which real and synthetic images define the training data. The first layer of a ResNet-18 backbone is augmented to fuse interest-point maps with RGB channels, enabling the network to capture scene geometry better. A manipulator robot with an eye-in-hand configuration provides a reference image, while subsequent poses and images are generated synthetically, removing the need for extensive real data collection. The experimental results reveal that this enriched input representation significantly improves convergence accuracy and velocity smoothness compared to a baseline that processes real images alone. Specifically, including feature point maps allows the network to discriminate crucial elements in the scene, resulting in more precise velocity commands and stable end-effector trajectories. Thus, integrating additional, synthetically generated map data into convolutional architectures can enhance the robustness and performance of the visual servoing system, particularly when real-world data gathering is challenging. Unlike existing visual servoing methods, our early fusion strategy integrates feature maps directly into the network’s initial convolutional layer, allowing the model to learn critical geometric details from the very first stage of training. This approach yields superior velocity predictions and smoother servoing compared to conventional frameworks. Full article

(This article belongs to the Special Issue Visual Servoing-Based Robotic Manipulation)

► Show Figures

Figure 1

34 pages, 20595 KiB

Open AccessArticle

Collision-Free Path Planning in Dynamic Environment Using High-Speed Skeleton Tracking and Geometry-Informed Potential Field Method

by Yuki Kawawaki, Kenichi Murakami and Yuji Yamakawa

Robotics 2025, 14(5), 65; https://doi.org/10.3390/robotics14050065 - 17 May 2025

Viewed by 135

Abstract

In recent years, the realization of a society in which humans and robots coexist has become highly anticipated. As a result, robots are expected to exhibit versatility regardless of their operating environments, along with high responsiveness, to ensure safety and enable dynamic task [...] Read more.

In recent years, the realization of a society in which humans and robots coexist has become highly anticipated. As a result, robots are expected to exhibit versatility regardless of their operating environments, along with high responsiveness, to ensure safety and enable dynamic task execution. To meet these demands, we design a comprehensive system composed of two primary components: high-speed skeleton tracking and path planning. For tracking, we implement a high-speed skeleton tracking method that combines deep learning-based detection with optical flow-based motion extraction. In addition, we introduce a dynamic search area adjustment technique that focuses on the target joint to extract the desired motion more accurately. For path planning, we propose a high-speed, geometry-informed potential field model that addresses four key challenges: (P1) avoiding local minima, (P2) suppressing oscillations, (P3) ensuring adaptability to dynamic environments, and (P4) handling obstacles with arbitrary 3D shapes. We validated the effectiveness of our high-frequency feedback control and the proposed system through a series of simulations and real-world collision-free path planning experiments. Our high-speed skeleton tracking operates at 250 Hz, which is eight times faster than conventional deep learning-based methods, and our path planning method runs at over 10,000 Hz. The proposed system offers both versatility across different working environments and low latencies. Therefore, we hope that it will contribute to a foundational motion generation framework for human–robot collaboration (HRC), applicable to a wide range of downstream tasks while ensuring safety in dynamic environments. Full article

(This article belongs to the Special Issue Visual Servoing-Based Robotic Manipulation)

► Show Figures

Figure 1

20 pages, 5640 KiB

Open AccessArticle

H_∞ Control for Systems with Mechanical Constraints Based on Orthogonal Decomposition

by Ahmad Aldaher and Sergei Savin

Robotics 2025, 14(5), 64; https://doi.org/10.3390/robotics14050064 - 16 May 2025

Viewed by 85

Abstract

In this paper, we study

H_{\infty}

control for systems with explicit mechanical constraints and a lack of state information, such as walking robots. This paper proposes an

H_{\infty}

control design scheme based on solving an optimization problem with linear matrix inequality [...] Read more.

In this paper, we study

H_{\infty}

control for systems with explicit mechanical constraints and a lack of state information, such as walking robots. This paper proposes an

H_{\infty}

control design scheme based on solving an optimization problem with linear matrix inequality constraints. Our method is based on the orthogonal decomposition of the state variables and the use of two linear controllers and a Luenberger observer, tuned to achieve the desired properties of the closed-loop system. The method takes into account static linear additive disturbance, which appears due to the uncertainties associated with the mechanical constraints. We propose a dynamics linearization procedure for systems with mechanical constraints, taking into account the inevitable lack of information about the environment; this procedure allows a nonlinear system to be transformed into a form suitable for the application of the proposed control design method. The method is tested on a constrained underactuated three-link robot and a flat quadruped robot, showing the desired behavior in both cases. Full article

(This article belongs to the Section Sensors and Control in Robotics)

► Show Figures

Figure 1

44 pages, 823 KiB

Open AccessReview

A Systematic Literature Review of DDS Middleware in Robotic Systems

by Muhammad Liman Gambo, Abubakar Danasabe, Basem Almadani, Farouq Aliyu, Abdulrahman Aliyu and Esam Al-Nahari

Robotics 2025, 14(5), 63; https://doi.org/10.3390/robotics14050063 - 14 May 2025

Viewed by 371

Abstract

The increasing demand for automation has led to the complexity of the design and operation of robotic systems. This paper presents a systematic literature review (SLR) focused on the applications and challenges of Data Distribution Service (DDS)-based middleware in robotics from 2006 to [...] Read more.

The increasing demand for automation has led to the complexity of the design and operation of robotic systems. This paper presents a systematic literature review (SLR) focused on the applications and challenges of Data Distribution Service (DDS)-based middleware in robotics from 2006 to 2024. We explore the pivotal role of DDS in facilitating efficient communication across heterogeneous robotic systems, enabling seamless integration of actuators, sensors, and computational elements. Our review identifies key applications of DDS in various robotic domains, including multi-robot coordination, real-time data processing, and cloud–edge–end fusion architectures, which collectively enhance the performance and scalability of robotic operations. Furthermore, we identify several challenges associated with implementing DDS in robotic systems, such as security vulnerabilities, performance and scalability requirements, and the complexities of real-time data transmission. By analyzing recent advancements and case studies, we provide insights into the potential of DDS to overcome these challenges while ensuring robust and reliable communication in dynamic environments. This paper aims to contribute to the transformative impact of DDS-based middleware in robotics, offering a comprehensive overview of its benefits, applications, and security implications. Our findings underscore the necessity for continued research and development in this area, paving the way for more resilient and intelligent robotic systems that operate effectively in real-world scenarios. This review not only fills existing gaps in the literature but also serves as a foundational resource for researchers and practitioners seeking to leverage DDS in the design and implementation of next-generation robotic solutions. Full article

(This article belongs to the Special Issue Innovations in the Internet of Robotic Things (IoRT))

► Show Figures

Figure 1

25 pages, 5822 KiB

Open AccessReview

Analytical Modeling, Virtual Prototyping, and Performance Optimization of Cartesian Robots: A Comprehensive Review

by Yasir Mehmood, Ferdinando Cannella and Silvio Cocuzza

Robotics 2025, 14(5), 62; https://doi.org/10.3390/robotics14050062 - 3 May 2025

Viewed by 298

Abstract

A comprehensive literature review on the kinematics and dynamics modeling and virtual prototyping (V.P) of the Cartesian robots with a flexible configuration is presented in this paper. Different modeling approaches of the main components of the Cartesian robot, which includes linear belt drives [...] Read more.

A comprehensive literature review on the kinematics and dynamics modeling and virtual prototyping (V.P) of the Cartesian robots with a flexible configuration is presented in this paper. Different modeling approaches of the main components of the Cartesian robot, which includes linear belt drives and structural components, are presented and discussed in this paper. Furthermore, the vibrations modeling, trajectory planning, and control strategies of the Cartesian robot are also presented. The performance optimization of the Cartesian robot is discussed here, which is affected by the highly flexible configuration of the robot incurred due to high-mix, low-volume production. The importance of virtual prototyping techniques, like finite element analysis and multi-body dynamics, for modeling Cartesian robots or its components is presented. Design and performance optimization methods for robots with a flexible configuration are discussed, although their application to Cartesian robots is rare in the literature and it presents an exciting opportunity for future research in this area. This review paper focuses on the importance of further research on the virtual prototyping tools for flexibly configured robots and their integration with experimental validation. The findings offer useful insights to industries looking to maximize their production processes while keeping the customization, reliability, and efficiency. Full article

(This article belongs to the Special Issue Integrating Robotics into High-Accuracy Industrial Operations)

► Show Figures

Figure 1

25 pages, 3258 KiB

Open AccessArticle

Singular Configuration Analysis of Modular-Driven 4- and 6-DoF Parallel Topology Robots

by Zoltán Forgó, Ferenc Tolvaly-Roșca and Attila Csobán

Robotics 2025, 14(5), 61; https://doi.org/10.3390/robotics14050061 - 2 May 2025

Viewed by 453

Abstract

The number of applications of parallel topology robots in industry is growing, and the interest of academics in finding new solutions and applications to implement such mechanisms is present all over the world. Industrywide, the most commonly used motion types need four- and [...] Read more.

The number of applications of parallel topology robots in industry is growing, and the interest of academics in finding new solutions and applications to implement such mechanisms is present all over the world. Industrywide, the most commonly used motion types need four- and six-degrees-of-freedom (DoF) robots. While there are commercial variants from different robot vendors, this study offers new alternatives to these. Based on Lie algebra synthesis, symmetrical parallel structures are identified, according to certain rules. Implementing 2-DoF actuation modules, the number of robot limbs is reduced compared to existing commercial robot structures. In terms of the applicability of a parallel mechanism (also concerning the control algorithm), it is important to determine singular configurations. Therefore, in addition to the kinematic schematics of the newly proposed mechanisms, their singular configurations are also discussed. Based on some dimensional simplifications (without a loss of generality), the conditions for the singular configurations are enumerated for the presented parallel topology robots with symmetrical kinematic chains. Finally, a comparison of the proposed mechanism is presented, considering its singular configurations. Full article

(This article belongs to the Section Intelligent Robots and Mechatronics)

► Show Figures

Figure 1

25 pages, 3077 KiB

Open AccessEditor’s ChoiceArticle

A Partitioned Operational Space Approach for Singularity Handling in Six-Axis Manipulators

by Craig Carignan and Giacomo Marani

Robotics 2025, 14(5), 60; https://doi.org/10.3390/robotics14050060 - 30 Apr 2025

Viewed by 189

Abstract

Task prioritization for inverse kinematics can be a powerful tool for realizing objectives in robot manipulation. This is particularly true for robots with redundant degrees of freedom, but it can also help address a debilitating singularity in six-axis robots. A roll-pitch-roll wrist is [...] Read more.

Task prioritization for inverse kinematics can be a powerful tool for realizing objectives in robot manipulation. This is particularly true for robots with redundant degrees of freedom, but it can also help address a debilitating singularity in six-axis robots. A roll-pitch-roll wrist is especially problematic for any six-axis robot because it produces a “gimbal-lock” singularity in the middle of the wrist workspace when the roll axes align. A task priority methodology can be used to realize only the achievable components of the commanded motion in the reduced operational space of a manipulator near singularities while phasing out the uncontrollable direction. In addition, this approach allows the operator to prioritize translation and rotation in the region of singularities. This methodology overcomes a significant drawback to the damped least-squares method, which can produce tool motion that deviates significantly from the desired path even in directions that are controllable. The approach used here reduces the operational space near the wrist singularity while maintaining full command authority over tool translation. The methodology is demonstrated in simulations conducted on a six degree-of-freedom Motoman MH250 manipulator. Full article

(This article belongs to the Section Industrial Robots and Automation)

► Show Figures

Graphical abstract

32 pages, 2540 KiB

Open AccessArticle

Formation Control of Wheeled Mobile Robots with Fault-Tolerance Capabilities

by Muhammad Shahab, Ali Nasir and Nezar M. Alyazidi

Robotics 2025, 14(5), 59; https://doi.org/10.3390/robotics14050059 - 27 Apr 2025

Viewed by 256

Abstract

This research investigates the impact of actuator faults on the formation control of multiple-wheeled mobile robots—a critical aspect in coordinating multi-robot systems for applications such as surveillance, exploration, and transportation. When a fault occurs in any of the robots, it can disrupt the [...] Read more.

This research investigates the impact of actuator faults on the formation control of multiple-wheeled mobile robots—a critical aspect in coordinating multi-robot systems for applications such as surveillance, exploration, and transportation. When a fault occurs in any of the robots, it can disrupt the formation and adversely affect the system’s performance, thereby compromising system efficiency and reliability. While numerous studies have focused on fault-tolerant control strategies to maintain formation integrity, there is a notable gap in the literature regarding the relationship between controller gains and settling time under varying degrees of actuator loss. In this paper, we develop a kinematic model of wheeled mobile robots and implement a leader–follower-based formation control strategy. Actuator faults are systematically introduced with varying levels of effectiveness (e.g., 80%, 60%, and 40% of full capacity) to observe their effects on formation maintenance. We generate data correlating controller gains with settling time under different actuator loss conditions and fit a polynomial curve to derive an equation describing this relationship. Comprehensive MATLAB simulations are conducted to evaluate the proposed methodology. The results demonstrate the influence of actuator faults on the formation control system and provide valuable insights into optimizing controller gains for improved fault tolerance. These findings contribute to the development of more robust multi-robot systems capable of maintaining formation and performance despite the presence of actuator failures. Full article

(This article belongs to the Section Intelligent Robots and Mechatronics)

► Show Figures

Figure 1

20 pages, 2603 KiB

Open AccessArticle

A Methodology to Characterize an Optimal Robotic Manipulator Using PSO and ML Algorithms for Selective and Site-Specific Spraying Tasks in Vineyards

by Roni Azriel, Oded Degani and Avital Bechar

Robotics 2025, 14(5), 58; https://doi.org/10.3390/robotics14050058 - 27 Apr 2025

Viewed by 260

Abstract

This paper presents an improved methodology for characterizing task-oriented optimal manipulator configuration, tested on a case study of selective spraying in vineyards. It compares the current approach for optimizing manipulator configurations, which relies on simulation and optimization algorithms, with an improved methodology that [...] Read more.

This paper presents an improved methodology for characterizing task-oriented optimal manipulator configuration, tested on a case study of selective spraying in vineyards. It compares the current approach for optimizing manipulator configurations, which relies on simulation and optimization algorithms, with an improved methodology that integrates machine learning models to enhance the optimization process. The simulation tool was developed using the Gazebo simulator and ROS software to evaluate potential robotic configurations within a simulated vineyard. Particle Swarm Optimization (PSO) was employed as the optimization algorithm in a finite solution space, with the performance measure based on maximizing the Manipulability Index of manipulator configurations reaching all targets. In the proposed methodology, XGBoost models were used to replace the simulation stage in the process and predict the manipulator’s ability to reach the target positions in the spraying task. This prediction served as decision support in selecting which configurations should be tested in the simulation, thereby reducing computational time. The integration of machine learning models in the proposed methodology resulted in an average runtime reduction of 59% while maintaining an average manipulability index score in comparison to the original approach, which did not include the XGBoost model. This methodology demonstrates significant enhancements in optimizing robot configuration for a specific task and shows strong potential for broader applications across various industries. Full article

(This article belongs to the Special Issue Intelligent Robotic and Mechatronic Systems in Agricultural and Environmental Education)

► Show Figures

Figure 1

51 pages, 15792 KiB

Open AccessReview

Quadruped Robots: Bridging Mechanical Design, Control, and Applications

by Qimeng Li, Franco Cicirelli, Andrea Vinci, Antonio Guerrieri, Wen Qi and Giancarlo Fortino

Robotics 2025, 14(5), 57; https://doi.org/10.3390/robotics14050057 - 26 Apr 2025

Viewed by 1842

Abstract

Quadruped robots have emerged as a prominent field of research due to their exceptional mobility and adaptability in complex terrains. This paper presents an overview of quadruped robots, encompassing their design principles, control mechanisms, perception systems, and applications across various industries. We review [...] Read more.

Quadruped robots have emerged as a prominent field of research due to their exceptional mobility and adaptability in complex terrains. This paper presents an overview of quadruped robots, encompassing their design principles, control mechanisms, perception systems, and applications across various industries. We review the historical evolution and technological milestones that have shaped quadruped robotics. To understand their impact on performance and functionality, key aspects of mechanical design are analyzed, including leg configurations, actuation systems, and material selection. Control strategies for locomotion, balance, and navigation are all examined, highlighting the integration of artificial intelligence and machine learning to enhance adaptability and autonomy. This review also explores perception and sensing technologies that enable environmental interaction and decision-making capabilities. Furthermore, we systematically examine the diverse applications of quadruped robots in sectors including the military, search and rescue, industrial inspection, agriculture, and entertainment. Finally, we address challenges and limitations, including technical hurdles, ethical considerations, and regulatory issues, and propose future research directions to advance the field. By structuring this review as a systematic study, we ensure clarity and a comprehensive understanding of the domain, making it a valuable resource for researchers and engineers in quadruped robotics. Full article

(This article belongs to the Section Intelligent Robots and Mechatronics)

► Show Figures

Figure 1

20 pages, 29832 KiB

Open AccessEditor’s ChoiceArticle

Human-Centric Robotic Solution for Motor and Gearbox Assembly: An Industry 5.0 Pilot Study

by Aitor Ibarguren, Sotiris Aivaliotis, Javier González Huarte, Arkaitz Urquiza, Panagiotis Baris, Apostolis Papavasileiou, George Michalos and Sotiris Makris

Robotics 2025, 14(5), 56; https://doi.org/10.3390/robotics14050056 - 26 Apr 2025

Viewed by 387

Abstract

The automotive industry is one of the most automatized industries, employing more than one million robots worldwide. Although several steps in car production are completely automated, many steps are still carried out by operators, especially in tasks requiring high dexterity. Additionally, customization and [...] Read more.

The automotive industry is one of the most automatized industries, employing more than one million robots worldwide. Although several steps in car production are completely automated, many steps are still carried out by operators, especially in tasks requiring high dexterity. Additionally, customization and deployability are still pending issues in this industry, where a real collaboration between robots and operators would increase the reconfigurability of the assembly lines. This paper presents an innovative robotic cell focused on the motor and gearbox assembly, including collaborative industrial robots and autonomous mobile manipulators along the different assembly stations. The design also incorporates a human-centered approach, with an enhanced human interface to facilitate the interaction with operators with the complete robotic cell. The proposed approach has been deployed and validated on a real automotive industrial scenario, obtaining promising metrics and results. Full article

(This article belongs to the Special Issue Integrating Robotics into High-Accuracy Industrial Operations)

► Show Figures

Graphical abstract

23 pages, 2040 KiB

Open AccessReview

Trajectory Planning for Robotic Manipulators in Automated Palletizing: A Comprehensive Review

by Samuel Romero, Jorge Valero, Andrea Valentina García, Carlos F. Rodríguez, Ana Maria Montes, Cesar Marín, Ruben Bolaños and David Álvarez-Martínez

Robotics 2025, 14(5), 55; https://doi.org/10.3390/robotics14050055 - 26 Apr 2025

Viewed by 392

Abstract

Recent industrial production paradigms have seen the promotion of the outsourcing of low-value-added operations to robotic cells as a service, particularly end-of-line packaging. As a result, various types of research have emerged, offering different approaches to the trajectory design optimization of robotic manipulators [...] Read more.

Recent industrial production paradigms have seen the promotion of the outsourcing of low-value-added operations to robotic cells as a service, particularly end-of-line packaging. As a result, various types of research have emerged, offering different approaches to the trajectory design optimization of robotic manipulators and their applications. Over time, numerous improvements and updates have been made to the proposed methodologies, addressing the limitations and restrictions of earlier work. This survey-type article compiles research articles published in recent years that focus on the main algorithms proposed for addressing placement and minimum-time path planning for a manipulator responsible for performing pick-and-place tasks. Specifically, the research examines the construction of an automated robotic cell for the palletizing of regular heterogeneous boxes on a collision-free mixed pallet. By reviewing and synthesizing the most recent research, this article sheds light on the state-of-the-art manipulator planning algorithms for pick-and-place tasks in palletizing applications. Full article

(This article belongs to the Section Industrial Robots and Automation)

► Show Figures

Figure 1

16 pages, 1696 KiB

Open AccessArticle

A Motion Propagation Force Analysis of Multi-DoF Systems Using the Partial Lagrangian Method

by Hironori Gunji, Takashi Kusaka and Takayuki Tanaka

Robotics 2025, 14(5), 54; https://doi.org/10.3390/robotics14050054 - 24 Apr 2025

Viewed by 251

Abstract

A partial Lagrangian method is proposed as an inverse dynamics analysis method for multi-link systems. This method, combined with automatic differentiation, allows for the derivation of equations of motion and analytical extraction of motion-induced torque components. We introduce the concept of motion propagation [...] Read more.

A partial Lagrangian method is proposed as an inverse dynamics analysis method for multi-link systems. This method, combined with automatic differentiation, allows for the derivation of equations of motion and analytical extraction of motion-induced torque components. We introduce the concept of motion propagation force to describe joint torque components generated by the motion of other joints. This concept aligns with existing notions such as interaction torque, while providing a novel analytical perspective. The effectiveness of the proposed method is confirmed through simulations using a three-DoF arm model, where motion propagation torques are visualized and validated. This method is useful for motion analysis and impedance control in complex robotic systems. Full article

(This article belongs to the Section Intelligent Robots and Mechatronics)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Robotics, Volume 14, Issue 5 (May 2025) – 14 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI