Robotics

24 pages, 19432 KB

Open AccessArticle

Robot Learning from Teleoperated Demonstrations: A Pilot Study Towards Automating Mastic Deposition in Construction Sites

by Irati Rasines, Erlantz Loizaga, Rebecca Erlebach, Anurag Bansal, Sara Sillaurren, Patricia Rosen, Sascha Wischniewski, Arantxa Renteria and Itziar Cabanes

Robotics 2025, 14(8), 114; https://doi.org/10.3390/robotics14080114 - 19 Aug 2025

Viewed by 477

Abstract

The construction industry faces significant challenges due to the physically demanding and hazardous nature of tasks such as manual filling of expansion joints with mastic. Automating mastic filling presents additional difficulties due to the variability of mastic density with temperature, which creates a [...] Read more.

The construction industry faces significant challenges due to the physically demanding and hazardous nature of tasks such as manual filling of expansion joints with mastic. Automating mastic filling presents additional difficulties due to the variability of mastic density with temperature, which creates a constantly changing environment that requires adaptive control strategies to ensure consistent application quality. This pilot study focuses on testing a new human–robot collaborative approach for automating the mastic application in concrete expansion joints. The system learns the task from demonstrations performed by expert construction operators teleoperating the robot. This study evaluates the usability, efficiency, and adoption of robotic assistance in joint-filling tasks compared to traditional manual methods. The study analyzes execution time and joint quality measurements, psychophysiological signal analysis, and post-task user feedback. This multi-source approach enables a comprehensive assessment of task performance and both objective and subjective evaluations of technology acceptance. The findings underscore the effectiveness of automated systems in improving safety and productivity on construction sites, while also identifying key areas for technological improvement. Full article

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

► Show Figures

Figure 1

23 pages, 21704 KB

Open AccessArticle

Autonomous Grasping of Deformable Objects with Deep Reinforcement Learning: A Study on Spaghetti Manipulation

by Prem Gamolped, Nattapat Koomklang, Abbe Mowshowitz and Eiji Hayashi

Robotics 2025, 14(8), 113; https://doi.org/10.3390/robotics14080113 - 18 Aug 2025

Viewed by 356

Abstract

Packing food into lunch boxes requires the correct portion to be selected. Food items such as fried chicken, eggs, and sausages are straightforward to manipulate when packing. In contrast, deformable objects like spaghetti can give challenges to lunch box packing due to their [...] Read more.

Packing food into lunch boxes requires the correct portion to be selected. Food items such as fried chicken, eggs, and sausages are straightforward to manipulate when packing. In contrast, deformable objects like spaghetti can give challenges to lunch box packing due to their fragility and tendency to break apart, and the fluctuating weight of noodles. Furthermore, achieving the correct amount is crucial for lunch box packing. This research focuses on self-learned grasping by a robotic arm to enable the ability to autonomously predict and grasp deformable objects, specifically spaghetti, to achieve the correct amount within specified ranges. We utilize deep reinforcement learning as the core learning. We developed a custom environment and policy network along a real-world scenario that was simplified as in a food factory, incorporating multi-sensors to observe the environment and pipeline to work with a real robotic arm. Through the study and experiments, our results show that the robot can grasp the spaghetti within the desired ranges, although occasional failures were caused by the nature of the deformable object. Addressing the problem under varying environmental conditions such as data augmentation can partially help model prediction. The study highlights the potential of combining deep learning with robotic manipulation for complex deformable object tasks, offering insight for applications in automated food handling and other industries. Full article

(This article belongs to the Section Humanoid and Human Robotics)

► Show Figures

Figure 1

15 pages, 252 KB

Open AccessArticle

Mortal vs. Machine: A Compact Two-Factor Model for Comparing Trust in Humans and Robots

by Andrew Prahl

Robotics 2025, 14(8), 112; https://doi.org/10.3390/robotics14080112 - 16 Aug 2025

Viewed by 381

Abstract

Trust in robots is often analyzed with scales built for either humans or automation, making cross-species comparisons imprecise. Addressing that gap, this paper distils decades of trust scholarship, from clinical vs. actuarial judgement to modern human–robot teaming, into a lean two-factor framework: Mortal [...] Read more.

Trust in robots is often analyzed with scales built for either humans or automation, making cross-species comparisons imprecise. Addressing that gap, this paper distils decades of trust scholarship, from clinical vs. actuarial judgement to modern human–robot teaming, into a lean two-factor framework: Mortal vs. Machine (MvM). We first surveyed classic technology-acceptance and automation-reliance research and then integrated empirical findings in human–robot interaction to identify diagnostic cues that can be instantiated by both human and machine agents. The model includes (i) ability—perceived task competence and reliability—and (ii) value congruence—alignment of decision weights and trade-off priorities. Benevolence, oft-included in trust studies, was excluded because current robots cannot manifest genuine goodwill and existing items elicit high dropout. The resulting scale travels across contexts, allowing for researchers to benchmark a robot against a human co-worker on identical terms and enabling practitioners to pinpoint whether performance deficits or priority clashes drive acceptance. By reconciling anthropocentric and technocentric trust literature in a deployable diagnostic, MvM offers a field-ready tool and a conceptual bridge for future studies of AI-empowered robotics. Full article

(This article belongs to the Section Humanoid and Human Robotics)

13 pages, 854 KB

Open AccessArticle

Physical Reinforcement Learning with Integral Temporal Difference Error for Constrained Robots

by Luis Pantoja-Garcia, Vicente Parra-Vega and Rodolfo Garcia-Rodriguez

Robotics 2025, 14(8), 111; https://doi.org/10.3390/robotics14080111 - 14 Aug 2025

Viewed by 687

Abstract

The paradigm of reinforcement learning (RL) refers to agents that learn iteratively through continuous interactions with their environment. However, when the value function is unknown, a neural network is used, which is typically encoded into an unknown temporal difference equation. When RL is [...] Read more.

The paradigm of reinforcement learning (RL) refers to agents that learn iteratively through continuous interactions with their environment. However, when the value function is unknown, a neural network is used, which is typically encoded into an unknown temporal difference equation. When RL is implemented in physical systems, explicit convergence and stability analyses are required to guarantee the worst-case operations for any trial, even when the initial conditions are set to zero. In this paper, physical RL (p-RL) refers to the application of RL in dynamical systems that interact with their environments, such as robot manipulators in contact tasks and humanoid robots in cooperation or interaction tasks. Unfortunately, most p-RL schemes lack stability properties, which can even be dangerous for specific robot applications, such as those involving contact (constrained) tasks or interaction tasks. Considering an unknown and disturbed DAE2 robot, in this paper a p-RL approach is developed to guaranteeing robust stability throughout a continuous-time-adaptive actor–critic, with local exponential convergence of force–position tracking error. The novel adaptive mechanisms lead to robustness, while an integral sliding mode enforces tracking. Simulations are presented and discussed to show our proposal’s effectiveness, and some final remarks are addressed concerning the structural aspects. Full article

(This article belongs to the Section AI in Robotics)

► Show Figures

Figure 1

31 pages, 6032 KB

Open AccessArticle

Event-Based Closed-Loop Control for Path Following of a Purcell’s Three-Link Swimmer

by Cristina Nuevo-Gallardo, Luis Mérida-Calvo, Inés Tejado, Blas M. Vinagre and Vicente Feliu-Batlle

Robotics 2025, 14(8), 110; https://doi.org/10.3390/robotics14080110 - 14 Aug 2025

Viewed by 194

Abstract

Purcell’s three-link swimmers, characterised by segments connected through one-degree-of-freedom joints, exhibit a difficulty in following precise paths. This is attributed to their motion primitives, which do not inherently generate displacement in a singular, predictable direction. To overcome this limitation, this paper proposes a [...] Read more.

Purcell’s three-link swimmers, characterised by segments connected through one-degree-of-freedom joints, exhibit a difficulty in following precise paths. This is attributed to their motion primitives, which do not inherently generate displacement in a singular, predictable direction. To overcome this limitation, this paper proposes a closed-loop control strategy on the basis of event-based control. This control approach enables the robot to perform a specific motion primitive when the deviation from the desired trajectory exceeds a predefined threshold. In other words, an asynchronous strategy is used to adjust the motion of the swimmer, thereby ensuring tracking of the desired path with a limited error. The effectiveness of this closed-loop control strategy is demonstrated through experiments with a motor-driven 30 cm-length prototype. These tests show that this event-based control strategy allows the swimmer to follow specific paths with a tracking error of less than 30% of its length. Full article

(This article belongs to the Special Issue Adaptive and Nonlinear Control of Robotics)

► Show Figures

Figure 1

49 pages, 15124 KB

Open AccessArticle

Flexible Constraint-Based Controller Framework for Ros_Control

by Miguel Prada, Asier Fernandez, Anthony Remazeilles and Joseph McIntyre

Robotics 2025, 14(8), 109; https://doi.org/10.3390/robotics14080109 - 11 Aug 2025

Viewed by 340

Abstract

Generating robot behaviors in dynamic real-world situations generally requires the programming of multiple, often redundant degrees of freedom to meet multiple goals governing the desired motions. In this work, we propose a constraint-based controller specification methodology. A novel declarative language is used to [...] Read more.

Generating robot behaviors in dynamic real-world situations generally requires the programming of multiple, often redundant degrees of freedom to meet multiple goals governing the desired motions. In this work, we propose a constraint-based controller specification methodology. A novel declarative language is used to combine semantically specialized building blocks into composite controllers. This description is automatically transformed at runtime into an executable form, which can automatically leverage multiple threads to parallelize computations whenever possible. Enabling runtime definition of controller topologies out of declarative descriptions not only reduces the work required to develop such controllers, but it also allows one to dynamically synthesize new controllers based on higher-level task planners or by user interaction through Graphical User Interfaces (GUIs). Our solution adds new functionality to the Robot Operating System (ROS)/ros_control ecosystem, where robot behaviors are typically achieved by deploying single-objective, off-the-shelf controllers for tasks like following joint trajectories, executing interpolated point-to-point motions in Cartesian space, or for basic compliant behaviors. Our proposed constraint-based framework enhances ros_control by providing the means to easily construct composite controllers from existing primary elements using our design language. Building on top of the ros_control infrastructure facilitates the usage of our controller with a wide range of supported robots and enables quick integration with the existing ROS ecosystem. Full article

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

► Show Figures

Figure 1

14 pages, 18726 KB

Open AccessArticle

Safe Autonomous UAV Target-Tracking Under External Disturbance, Through Learned Control Barrier Functions

by Promit Panja, Madan Mohan Rayguru and Sabur Baidya

Robotics 2025, 14(8), 108; https://doi.org/10.3390/robotics14080108 - 3 Aug 2025

Viewed by 564

Abstract

Ensuring the safe operation of Unmanned Aerial Vehicles (UAVs) is crucial for both mission-critical and safety-critical tasks. In scenarios where UAVs must track airborne targets, they need to follow the target’s path while maintaining a safe distance, even in the presence of unmodeled [...] Read more.

Ensuring the safe operation of Unmanned Aerial Vehicles (UAVs) is crucial for both mission-critical and safety-critical tasks. In scenarios where UAVs must track airborne targets, they need to follow the target’s path while maintaining a safe distance, even in the presence of unmodeled dynamics and environmental disturbances. This paper presents a novel collision avoidance strategy for dynamic quadrotor UAVs during target-tracking missions. We propose a safety controller that combines a learning-based Control Barrier Function (CBF) with standard sliding mode feedback. Our approach employs a neural network that learns the true CBF constraint, accounting for wind disturbances, while the sliding mode controller addresses unmodeled dynamics. This unified control law ensures safe leader-following behavior and precise trajectory tracking. By leveraging a learned CBF, the controller offers improved adaptability to complex and unpredictable environments, enhancing both the safety and robustness of the system. The effectiveness of our proposed method is demonstrated through the AirSim platform using the PX4 flight controller. Full article

(This article belongs to the Special Issue Applications of Neural Networks in Robot Control)

► Show Figures

Figure 1

16 pages, 2448 KB

Open AccessArticle

A Body-Powered Underactuated Prosthetic Finger Driven by MCP Joint Motion

by Worathris Chungsangsatiporn, Chaiwuth Sithiwichankit, Ratchatin Chancharoen, Ronnapee Chaichaowarat, Nopdanai Ajavakom and Gridsada Phanomchoeng

Robotics 2025, 14(8), 107; https://doi.org/10.3390/robotics14080107 - 31 Jul 2025

Viewed by 505

Abstract

This study presents the design, fabrication, and clinical validation of a lightweight, body-powered prosthetic index finger actuated via metacarpophalangeal (MCP) joint motion. The proposed system incorporates an underactuated, cable-driven mechanism combining rigid and compliant elements to achieve passive adaptability and embodied intelligence, supporting [...] Read more.

This study presents the design, fabrication, and clinical validation of a lightweight, body-powered prosthetic index finger actuated via metacarpophalangeal (MCP) joint motion. The proposed system incorporates an underactuated, cable-driven mechanism combining rigid and compliant elements to achieve passive adaptability and embodied intelligence, supporting intuitive user interaction. Results indicate that the prosthesis successfully mimics natural finger flexion and adapts effectively to a variety of grasping tasks with minimal effort. This study was conducted in accordance with ethical standards and approved by the Institutional Review Board (IRB), Project No. 670161, titled “Biologically-Inspired Synthetic Finger: Design, Fabrication, and Application.” The findings suggest that the device offers a viable and practical solution for individuals with partial hand loss, particularly in settings where electrically powered systems are unsuitable or inaccessible. Full article

(This article belongs to the Section Neurorobotics)

► Show Figures

Figure 1

26 pages, 6831 KB

Open AccessArticle

Human–Robot Interaction and Tracking System Based on Mixed Reality Disassembly Tasks

by Raúl Calderón-Sesmero, Adrián Lozano-Hernández, Fernando Frontela-Encinas, Guillermo Cabezas-López and Mireya De-Diego-Moro

Robotics 2025, 14(8), 106; https://doi.org/10.3390/robotics14080106 - 30 Jul 2025

Viewed by 592

Abstract

Disassembly is a crucial process in industrial operations, especially in tasks requiring high precision and strict safety standards when handling components with collaborative robots. However, traditional methods often rely on rigid and sequential task planning, which makes it difficult to adapt to unforeseen [...] Read more.

Disassembly is a crucial process in industrial operations, especially in tasks requiring high precision and strict safety standards when handling components with collaborative robots. However, traditional methods often rely on rigid and sequential task planning, which makes it difficult to adapt to unforeseen changes or dynamic environments. This rigidity not only limits flexibility but also leads to prolonged execution times, as operators must follow predefined steps that do not allow for real-time adjustments. Although techniques like teleoperation have attempted to address these limitations, they often hinder direct human–robot collaboration within the same workspace, reducing effectiveness in dynamic environments. In response to these challenges, this research introduces an advanced human–robot interaction (HRI) system leveraging a mixed-reality (MR) interface embedded in a head-mounted device (HMD). The system enables operators to issue real-time control commands using multimodal inputs, including voice, gestures, and gaze tracking. These inputs are synchronized and processed via the Robot Operating System (ROS2), enabling dynamic and flexible task execution. Additionally, the integration of deep learning algorithms ensures precise detection and validation of disassembly components, enhancing accuracy. Experimental evaluations demonstrate significant improvements, including reduced task completion times, enhanced operator experience, and compliance with strict adherence to safety standards. This scalable solution offers broad applicability for general-purpose disassembly tasks, making it well-suited for complex industrial scenarios. Full article

(This article belongs to the Special Issue Robot Teleoperation Integrating with Augmented Reality)

► Show Figures

Figure 1

18 pages, 16316 KB

Open AccessArticle

AntGrip—Boosting Parallel Plate Gripper Performance Inspired by the Internal Hairs of Ant Mandibles

by Mohamed Sorour and Barbara Webb

Robotics 2025, 14(8), 105; https://doi.org/10.3390/robotics14080105 - 30 Jul 2025

Viewed by 498

Abstract

Ants use their mandibles—effectively a two-finger gripper—for a wide range of grasping activities. Here, we investigate whether mimicking the internal hairs found on ant mandibles can improve performance of a two-finger parallel plate robot gripper. With bin-picking applications in mind, the gripper fingers [...] Read more.

Ants use their mandibles—effectively a two-finger gripper—for a wide range of grasping activities. Here, we investigate whether mimicking the internal hairs found on ant mandibles can improve performance of a two-finger parallel plate robot gripper. With bin-picking applications in mind, the gripper fingers are long and slim, with interchangeable soft gripping pads that can be hairy or hairless. A total of 2400 video-documented experiments have been conducted, comparing hairless to hairy pads with different hair patterns. Simply by adding hairs, the grasp success rate was increased by at least

29 %

, and the number of objects that remain securely gripped during manipulation more than doubled. This result not only advances the state of the art in grasping technology, but also provides novel insight into the mechanical role of mandible hairs in ant biology. Full article

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

► Show Figures

Figure 1

20 pages, 2108 KB

Open AccessReview

Underwater Polarized Light Navigation: Current Progress, Key Challenges, and Future Perspectives

by Mingzhi Chen, Yuan Liu, Daqi Zhu, Wen Pang and Jianmin Zhu

Robotics 2025, 14(8), 104; https://doi.org/10.3390/robotics14080104 - 29 Jul 2025

Viewed by 714

Abstract

Underwater navigation remains constrained by technological limitations, driving the exploration of alternative approaches such as polarized light-based systems. This review systematically examines advances in polarized navigation from three perspectives. First, the principles of atmospheric polarization navigation are analyzed, with their operational mechanisms, advantages, [...] Read more.

Underwater navigation remains constrained by technological limitations, driving the exploration of alternative approaches such as polarized light-based systems. This review systematically examines advances in polarized navigation from three perspectives. First, the principles of atmospheric polarization navigation are analyzed, with their operational mechanisms, advantages, and inherent constraints dissected. Second, innovations in bionic polarization multi-sensor fusion positioning are consolidated, highlighting progress beyond conventional heading-direction extraction. Third, emerging underwater polarization navigation techniques are critically evaluated, revealing that current methods predominantly adapt atmospheric frameworks enhanced by advanced filtering to mitigate underwater interference. A comprehensive synthesis of underwater polarization modeling methodologies is provided, categorizing physical, data-driven, and hybrid approaches. Through rigorous analysis of studies, three persistent barriers are identified: (1) inadequate polarization pattern modeling under dynamic cross-media conditions; (2) insufficient robustness against turbidity-induced noise; (3) immature integration of polarization vision with sonar/IMU (Inertial Measurement Unit) sensing. Targeted research directions are proposed, including adaptive deep learning models, multi-spectral polarization sensing, and bio-inspired sensor fusion architectures. These insights establish a roadmap for developing reliable underwater navigation systems that transcend current technological boundaries. Full article

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

► Show Figures

Figure 1

21 pages, 6018 KB

Open AccessArticle

Model-Based Design of the 5-DoF Light Industrial Robot

by Yongping Shi, Tianbing Ma, Hao Wang, Tao Zhang, Xin Zhang, Huapeng Wu and Ming Li

Robotics 2025, 14(8), 103; https://doi.org/10.3390/robotics14080103 - 29 Jul 2025

Viewed by 344

Abstract

With the application and rapid development of light industrial robots, it is vital to accelerate the prototype design to fulfill the demands of shortening the robot’s production cycle, owing to rapid update iterations. Since the traditional design method cannot intuitively and efficiently check [...] Read more.

With the application and rapid development of light industrial robots, it is vital to accelerate the prototype design to fulfill the demands of shortening the robot’s production cycle, owing to rapid update iterations. Since the traditional design method cannot intuitively and efficiently check the deficiencies in the design preparation, the secondary design iterations will result in higher equipment costs, longer design cycles, and lower development efficiency. The MBD (model-based design), a full 3D (three-dimensional) design and manufacturing method, is proposed to swiftly finish the prototype design for solving the above problems. Firstly, the robot design preparation is completed with the design requirements to generate a robot 3D model. Secondly, several design methods are used: (i) the rapid prototyping, which includes the joint component verification and selection to further optimize the 3D model; (ii) the robot kinematics algorithm, which provides a theoretical foundation for the 3D model design; (iii) the robot kinematics simulation, which verifies the correctness of the kinematics algorithm. Finally, the feasibility of the MBD is verified by the robot prototype and the motion control system test. Taking the MBD to design a 5-DoF (five-degrees-of-freedom) robot as an example, the joint verification and selection are finished quickly and accurately to build the robot prototype without the need for secondary design processing, and the kinematic algorithm verified by the co-simulation platform can be used directly in the actual motion control of the robot prototype, which accelerates the development of the robot motion control system. Full article

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

► Show Figures

Figure 1

18 pages, 2335 KB

Open AccessArticle

MLLM-Search: A Zero-Shot Approach to Finding People Using Multimodal Large Language Models

by Angus Fung, Aaron Hao Tan, Haitong Wang, Bensiyon Benhabib and Goldie Nejat

Robotics 2025, 14(8), 102; https://doi.org/10.3390/robotics14080102 - 28 Jul 2025

Viewed by 674

Abstract

Robotic search of people in human-centered environments, including healthcare settings, is challenging, as autonomous robots need to locate people without complete or any prior knowledge of their schedules, plans, or locations. Furthermore, robots need to be able to adapt to real-time events that [...] Read more.

Robotic search of people in human-centered environments, including healthcare settings, is challenging, as autonomous robots need to locate people without complete or any prior knowledge of their schedules, plans, or locations. Furthermore, robots need to be able to adapt to real-time events that can influence a person’s plan in an environment. In this paper, we present MLLM-Search, a novel zero-shot person search architecture that leverages multimodal large language models (MLLM) to address the mobile robot problem of searching for a person under event-driven scenarios with varying user schedules. Our approach introduces a novel visual prompting method to provide robots with spatial understanding of the environment by generating a spatially grounded waypoint map, representing navigable waypoints using a topological graph and regions by semantic labels. This is incorporated into an MLLM with a region planner that selects the next search region based on the semantic relevance to the search scenario and a waypoint planner that generates a search path by considering the semantically relevant objects and the local spatial context through our unique spatial chain-of-thought prompting approach. Extensive 3D photorealistic experiments were conducted to validate the performance of MLLM-Search in searching for a person with a changing schedule in different environments. An ablation study was also conducted to validate the main design choices of MLLM-Search. Furthermore, a comparison study with state-of-the-art search methods demonstrated that MLLM-Search outperforms existing methods with respect to search efficiency. Real-world experiments with a mobile robot in a multi-room floor of a building showed that MLLM-Search was able to generalize to new and unseen environments. Full article

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

► Show Figures

Figure 1

32 pages, 5721 KB

Open AccessReview

Control Strategies for Two-Wheeled Self-Balancing Robotic Systems: A Comprehensive Review

by Huaqiang Zhang and Norzalilah Mohamad Nor

Robotics 2025, 14(8), 101; https://doi.org/10.3390/robotics14080101 - 26 Jul 2025

Viewed by 888

Abstract

Two-wheeled self-balancing robots (TWSBRs) are underactuated, inherently nonlinear systems that exhibit unstable dynamics. Due to their structural simplicity and rich control challenges, TWSBRs have become a standard platform for validating and benchmarking various control algorithms. This paper presents a comprehensive and structured review [...] Read more.

Two-wheeled self-balancing robots (TWSBRs) are underactuated, inherently nonlinear systems that exhibit unstable dynamics. Due to their structural simplicity and rich control challenges, TWSBRs have become a standard platform for validating and benchmarking various control algorithms. This paper presents a comprehensive and structured review of control strategies applied to TWSBRs, encompassing classical linear approaches such as PID and LQR, modern nonlinear methods including sliding mode control (SMC), model predictive control (MPC), and intelligent techniques such as fuzzy logic, neural networks, and reinforcement learning. Additionally, supporting techniques such as state estimation, observer design, and filtering are discussed in the context of their importance to control implementation. The evolution of control theory is analyzed, and a detailed taxonomy is proposed to classify existing works. Notably, a comparative analysis section is included, offering practical guidelines for selecting suitable control strategies based on system complexity, computational resources, and robustness requirements. This review aims to support both academic research and real-world applications by summarizing key methodologies, identifying open challenges, and highlighting promising directions for future development. Full article

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

► Show Figures

Figure 1

16 pages, 10372 KB

Open AccessArticle

PRONOBIS: A Robotic System for Automated Ultrasound-Based Prostate Reconstruction and Biopsy Planning

by Matija Markulin, Luka Matijević, Janko Jurdana, Luka Šiktar, Branimir Ćaran, Toni Zekulić, Filip Šuligoj, Bojan Šekoranja, Tvrtko Hudolin, Tomislav Kuliš, Bojan Jerbić and Marko Švaco

Robotics 2025, 14(8), 100; https://doi.org/10.3390/robotics14080100 - 22 Jul 2025

Viewed by 516

Abstract

This paper presents the PRONOBIS project, an ultrasound-only, robotically assisted, deep learning-based system for prostate scanning and biopsy treatment planning. The proposed system addresses the challenges of precise prostate segmentation, reconstruction and inter-operator variability by performing fully automated prostate scanning, real-time CNN-transformer-based image [...] Read more.

This paper presents the PRONOBIS project, an ultrasound-only, robotically assisted, deep learning-based system for prostate scanning and biopsy treatment planning. The proposed system addresses the challenges of precise prostate segmentation, reconstruction and inter-operator variability by performing fully automated prostate scanning, real-time CNN-transformer-based image processing, 3D prostate reconstruction, and biopsy needle position planning. Fully automated prostate scanning is achieved by using a robotic arm equipped with an ultrasound system. Real-time ultrasound image processing utilizes state-of-the-art deep learning algorithms with intelligent post-processing techniques for precise prostate segmentation. To create a high-quality prostate segmentation dataset, this paper proposes a deep learning-based medical annotation platform, MedAP. For precise segmentation of the entire prostate sweep, DAF3D and MicroSegNet models are evaluated, and additional image post-processing methods are proposed. Three-dimensional visualization and prostate reconstruction are performed by utilizing the segmentation results and robotic positional data, enabling robust, user-friendly biopsy treatment planning. The real-time sweep scanning and segmentation operate at 30 Hz, which enable complete scan in 15 to 20 s, depending on the size of the prostate. The system is evaluated on prostate phantoms by reconstructing the sweep and by performing dimensional analysis, which indicates 92% and 98% volumetric accuracy on the tested phantoms. Three-dimansional prostate reconstruction takes approximately 3 s and enables fast and detailed insight for precise biopsy needle position planning. Full article

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

► Show Figures

Figure 1

Journal Menu

Journal Browser

Robotics, Volume 14, Issue 8 (August 2025) – 15 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI