Robotic Applications Research Articles

Exploring Robotic Nursing: A Comprehensive Systematic Review of Socially Assistive Robots within the Healthcare Professions

ABSTRACT Purpose The objective is to evaluate empirical literature on Socially Assistive Robots (SARs) in nursing, identifying strengths, weaknesses, and avenues for future research and practice. This article explores studies investigating robotic applications in healthcare, specifically nursing. Design The systematic review using PRISMA guidelines includes 19 relevant studies from Medline, PubMed, and Cochrane, presenting insights into the potential of SARs in addressing patients’ mental health and well-being. Methods The eligibility criteria for this review included publications from 2015 to 2024, full-text articles employing either qualitative or quantitative methodologies, articles written in English, and those published in peer-reviewed academic journals. Excluded were single-case studies, unpublished theses or dissertations, and studies not published in peer-reviewed journals. The search employed the terms “robotic nursing” and “future,” utilizing Medical Subject Headings (MeSH) terminology for precise retrieval. Findings The current literature has limitations in generalizability, breadth, and quantification of health-related outcomes. Areas of exploration, including diverse robot types, therapies, and geographical contexts, offer promising directions for future research. Conclusions The article concludes that although SARs show promise in healthcare, particularly in nursing, more comprehensive research is needed to establish their efficacy across a wider range of applications and settings. Clinical Evidence Current studies indicate that SARs may play a valuable role in supporting patients’ mental health and well-being, though further investigation is required to determine their broader impact and effectiveness.

Implementation of an FPGA-Based System to Process Images and Match Keypoints on High-Resolution Pictures

Processing scenery and finding points of interest is crucial for applications in robotics and aerospace missions. Those areas require efficient and reliable visual input processing. Here, field programmable gate arrays (FPGAs) offer essential advantages, like low power consumption compared to CPUs, performing a large number of calculations simultaneously, and having compact hardware. This paper presents an FPGA system that processes incoming camera data, finds points of interest, and matches them across different images on high-resolution images (2048 × 1088). It is a novel approach to implement the complete image processing pipeline on high-resolution images within the FPGA fabric without additional hardware. For keypoint detection and matching, our work uses a modified SIFT algorithm optimized for FPGA implementation processing and a nearest neighbor-based matching method. It was implemented on a Xilinx Kintex-7 FPGA and partially on a NanoXplore NG-Ultra to evaluate a radiation-hardened FPGA for space applications. On the Kintex-7, the keypoint detection achieves a speed of 33 ms per image, and its features are matched on up to 5 images per second. Judging by the resource utilization of one image processing module on the NG-Ultra, porting the entire system on a radiation-hardened FPGA appears feasible.

Future Prospects of Large Language Models: Enabling Natural Language Processing in Educational Robotics

Large language models (LLMs) have recently shown considerable promise in educational robotics by offering generic knowledge necessary in situations when prior programming is not possible. In general, mobile education robots cannot perform tasks like navigation or localization unless they have a working knowledge of maps. In this letter, we tackle the issue of making LLMs more applicable in the field of mobile education robots by helping them to understand Space Graph, a text-based map description. This study, which focuses on LLMs, is divided into several sections. It explores basic natural language processing (NLP) techniques and highlights how they can help create smooth education discussions. Examining the development of LLMs inside NLP systems, the paper explores the benefits and implementation issues of important models utilized in the education sector. Applications useful in educational discussions are described in depth, ranging from patient-focused tools like diagnosis and treatment recommendations to systems that support education providers. We provide thorough instructions and real-world examples for quick engineering, making LLM-based educational robotics solutions more accessible to novices. We demonstrate how LLM-guided upgrades can be easily included in education robotics applications using tutorial-level examples and structured prompt creation. This survey provides a thorough review and helpful advice for leveraging language models in automation development, acting as a road map for researchers navigating the rapidly changing field of LLM-driven educational robotics.

Cooperative dual-actor proximal policy optimization algorithm for multi-robot complex control task

This paper introduces a novel multi-agent Deep Reinforcement Learning (DRL) framework named the Cooperative Dual-Actor Proximal Policy Optimization (CDA-PPO) algorithm, designed to address complex humanoid robot cooperative learning control tasks. Effective cooperation among multiple humanoid robots, particularly in scenarios involving complex walking gait control and external disturbances in dynamic environments, is a critical challenge. This is especially pertinent for tasks requiring precise coordination and control, such as joint object transportation. In various real-life scenarios, humanoid robots might need to cooperate to carry large objects in many scenarios. This capability is crucial for logistics, manufacturing, intelligent transportation, and search-and-rescue missions applications. Humanoid robots have gained significant popularity, and their use in these cooperative tasks is becoming more common. To address this challenge, we propose CDA-PPO, which introduces a learning-based communication platform between agents and employs two distinct policy networks for each agent. This dual-policy approach enhances the robots’ ability to adapt to complex interactions and maintain stability while performing intricate tasks. We demonstrate the efficacy of CDA-PPO in a cooperative object-transportation scenario, where two humanoid robots collaborate to carry a table. The experimental results show that CDA-PPO significantly outperforms traditional methods, such as Independent PPO (IPPO), Multi-Agent PPO (MAPPO), and Multi-Agent Twin Delayed Deep Deterministic Policy Gradient (MATD3), in terms of training efficiency, stability, reward acquisition, and humanoid robot cooperative balance control with effective coordination between robots. The findings underscore the potential of CDA-PPO to advance the field of cooperative multi-agent control problems, proposing the way for future research in complex robotics applications.

Editorial: Artificial intelligence and robotic applications for smart monitoring and assistance in healthcare services

Editorial: Artificial intelligence and robotic applications for smart monitoring and assistance in healthcare services

Relative-kinematic formulation of geometrically exact beam dynamics based on Lie group variational integrators

Geometrically exact beam models can accurately describe the statics and dynamics of elastic, slender beams undergoing large deformations. This work introduces a variational integrator for such models based on a relative-kinematic formulation, in which positions and velocities of nodes in the discretized beam are expressed relative to the respective preceding nodes in the kinematic chain. The resulting model is especially suited for applications in robotics and control, since it has a minimum number of states and possesses the same structure as rigid mechanical systems, simplifying the combined modeling of rigid–flexible systems. Moreover, this approach allows to specifically select the modeled deformation modes, avoiding numerical issues associated with stiff, high-frequency modes and greatly increasing numerical efficiency. The proposed model is derived fully variationally in the discrete mechanics framework and under consistent consideration of the underlying Lie group structure, which translates into beneficial numerical properties. We provide a detailed treatment of the inclusion of dissipation and propose two solver strategies for time integration, including a linear-time solver based on recursive rigid-body dynamics algorithms. The model is validated and analyzed in detailed simulation studies underlining its efficiency for the simulation of stiff and slender beams, where the straightforward, but exact reduction to a Kirchhoff beam in the presented frame leads to a substantial speed-up of the simulations.

A Skin-Like Self-Powered Flexible Sensor for Wearable Monitoring and Robotic Tactile Application

A Skin-Like Self-Powered Flexible Sensor for Wearable Monitoring and Robotic Tactile Application

Ground Robots Bring Potential for Efficiency, Safety in FPSO Operations

_ This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper OTC 32872, “Evaluation of the Potential Impact of Ground Robots on FPSO Operations,” by Gustavo L.L. da Silva, Maurício M. Cordeiro Jr., and Maurício Galassi, Petrobras, et al. The paper has not been peer reviewed. Copyright 2024 Offshore Technology Conference. _ The objective of this paper is to present the operator’s learnings in evaluating the processes by which the asset crew of a floating production, storage, and offloading (FPSO) vessel identifies scenarios for the application of robotics in day-to-day offshore activities. The studies reveal a glimpse of the addressable market size of ground robots for routine offshore verification tasks. An initial analysis suggests that 30–50% of the theoretical equivalent of hours per year could be freed. Introduction In the complete paper, the hypothetical use of ground mobile robots to carry out operational activities is considered. For that goal, the capability of robotic platforms to move along an offshore facility (an FPSO, for the purposes of this paper) has been explored. This includes the ability to overcome obstacles, move up and down stairs or ramps, and walk on uneven floors or gratings while being piloted remotely or even doing so autonomously. Some of the considered equipment may have coupled robotic manipulators that also enable them to interact with the environment, allowing them to open or close doors, turn handles, and activate commands. These robotic platforms, in general, include actuator mechanisms and sensors that enable visual inspections, thermography, dimensional analysis, area mapping, gas measurements, noise and vibration analysis, and other operations requiring specific sensing. Operational Requirements A paramount requirement for a robot to be widely used in an FPSO is its ability to operate in hazardous areas. Robotic platforms for hazardous zones are not widely available. However, some companies are quickly advancing in the development and commercialization of these platforms. A Swiss company has already made available a quadruped robot with high mobilization capacity, including the ability to navigate stairs and carry out autonomous missions that have been preprogrammed. An Austrian company has marketed a caterpillar robot that can carry out inspections autonomously in classified areas. Every such activity will demand thorough analysis to properly define technical and process requirements. On FPSO platforms, the procedure for planning any service takes place at least a few days before its execution, a task already demanding many hours. Subsequently, a permit to work (PTW) is issued to perform the service. Sensors and Actuators for a Robotic System Some of the main data-acquisition or processing sensors used in robotic systems are detailed in the complete paper. In this context, “data” means everything that can be processed online or is capable of producing useful information in the future. Cameras for Acquisition of Images and Videos. These can be very useful in the visual inspection of systems or equipment, the visualization of the workspace, or the generation of input for image processing with the purpose of identifying patterns of interest, segmentation, classification, or other aspects related to computer vision.

A first principles study of BiSb monolayer: A novel gas sensor for robotic applications

This study, based on density functional theory (DFT) and non-equilibrium Green's functions, systematically analyzes the structural stability and adsorption behavior of gases (CO, CO2, NH3, Cl2, and CH4) on BiSb monolayers, aiming to provide a theoretical foundation for environmental sensors in post-earthquake disaster relief robots. The optimal structures, electron density difference (EDD), electron localization function (ELF), density of states (DOS), band gap, and other adsorption properties of the adsorption systems were examined to elucidate the interactions between gas molecules and the BiSb monolayer. Theoretical results indicate that the adsorption process is exothermic, characterized by negative adsorption energy. Furthermore, the analysis shows that BiSb monolayers exhibit high selectivity for gas adsorption, the adsorption strength follows the order: Cl2 > CO > NH3 > CO2 > CH4. Theoretically, BiSb monolayers hold promise for developing novel gas sensors and adsorbents, applicable to real-time monitoring, search, and rescue operations in post-earthquake scenarios for robotic applications.

Controlling the Deformation of the Antagonistic Shape Memory Alloy System by LSTM Deep Learning

The antagonistic system of two shape memory alloy wires is a great inspiration for the robotics field where it is applied as a linear actuator due to its shape memory effect. However, its control is still a challenge due to its hysteresis behavior. For that reason, a new controller is proposed in this paper for the displacement of the system’s effector. It is based on a Long Short-Term Memory neural network model. The aim is achieved by combining temperature-deformation data from an analytical model with voltage-temperature-deformation data from real experiments. Hence, these datasets are studied to overcome the nonlinearity obstacle of this system in order to be able to integrate it into robotic applications.

Activities of Daily Living Object Dataset: Advancing Assistive Robotic Manipulation with a Tailored Dataset

The increasing number of individuals with disabilities—over 61 million adults in the United States alone—underscores the urgent need for technologies that enhance autonomy and independence. Among these individuals, millions rely on wheelchairs and often require assistance from another person with activities of daily living (ADLs), such as eating, grooming, and dressing. Wheelchair-mounted assistive robotic arms offer a promising solution to enhance independence, but their complex control interfaces can be challenging for users. Automating control through deep learning-based object detection models presents a viable pathway to simplify operation, yet progress is impeded by the absence of specialized datasets tailored for ADL objects suitable for robotic manipulation in home environments. To bridge this gap, we present a novel ADL object dataset explicitly designed for training deep learning models in assistive robotic applications. We curated over 112,000 high-quality images from four major open-source datasets—COCO, Open Images, LVIS, and Roboflow Universe—focusing on objects pertinent to daily living tasks. Annotations were standardized to the YOLO Darknet format, and data quality was enhanced through a rigorous filtering process involving a pre-trained YOLOv5x model and manual validation. Our dataset provides a valuable resource that facilitates the development of more effective and user-friendly semi-autonomous control systems for assistive robots. By offering a focused collection of ADL-related objects, we aim to advance assistive technologies that empower individuals with mobility impairments, addressing a pressing societal need and laying the foundation for future innovations in human–robot interaction within home settings.

C2Fi-NeRF: Coarse to fine inversion NeRF for 6D pose estimation

Estimating the 6DoF pose of objects in complex scenarios is one of the core challenges in environmental perception for unmanned systems. Recently, mesh-free pose estimation methods based on “inverse” NeRF have achieved state-of-the-art (SOTA) accuracy under ideal data conditions compared to traditional methods. However, the overall performance of this strategy is suboptimal due to some overlooked details, such as NeRF’s sampling of pixel backpropagation, which can lead to local minima in high-resolution images. Random initialization of poses increases the difficulty of network convergence and estimation bias. Pose estimation neglects geometric consistency constraints, resulting in low robustness to occluded environments. To address these issues, this paper proposes a “coarse-to-fine” NeRF pose prediction framework (C2Fi-NeRF). During the training phase, an affinity-based full-pixel backpropagation strategy is proposed, abandoning the sparse sampling of traditional NeRF training. The complete gradient map is divided into affinity blocks, which are rendered and backpropagated in sequence. This not only achieves efficient full-pixel training for high-resolution images but also significantly improves the quality and consistency of rendered images, reducing noise and artifacts. The prediction phase is divided into two parts: the coarse phase optimizes reprojection errors through feature point matching to introduce precise initialization data, accelerating NeRF convergence and reducing bias potential. The fine estimation phase integrates multi-view geometry and color consistency constraints in the inverse NeRF iteration, enhancing pixel rendering robustness in complex occluded scenarios while also refining pose prediction. Experiments demonstrate that compared to existing NeRF-based and mainstream deep learning methods, C2Fi-NeRF is competitive in accuracy and efficiency on relevant datasets (NeRF-Synthetic, LLFF, Replica, YCB) and is more suitable for practical robotic applications.

Handwritten Data Extraction Using OpenAI ChatGPT4o and Robotic Process Automation.

This paper proposes to create an Robotic Process Automation style application that can digitalize and extract data from handwritten medical forms. The RPA robot uses OpenAI ChatGPT4o model to extract handwritten medical data and transform it into typed data. The handwritten data is transcribed correctly at a rate of 100%. The data interpretation is accomplished by the UiPath machine learning API. By creating new nonstandard form templates and associated taxonomies the system can be scaled as desired. After the data extraction process the saved data can be sent to a database, spreadsheet. The access to this medical data is restricted to the physicians and medical nurses employed at the medical facility.

4D Printing of Liquid Crystal Emulsions for Smart Structures with Multiple Functionalities.

3D printing, and more recently 4D printing, has emerged as a transformative technology for fabricating structures with complex geometries and responsive properties. However, employing functional colloidal solutions as inks for printing remains unexplored. In this work, we present a novel and versatile 4D printing approach for fabricating functional and complex-shaped objects using polymerizable liquid crystal (LC) emulsion droplets. Leveraging a digital light processing (DLP) 3D printing technique, we achieve rapid production of intricate 3D geometries with high resolution. The printed structures retain the LC ordering from the precursor droplets, imparting the final objects with shape memory properties, including shape fixation and recovery upon heating or light exposure. Light-responsive behavior is introduced post-printing by embedding an azo dye into the 3D structures. Additionally, we explore the potential to create intrinsically porous 3D structures by selectively removing non-reactive components from the printed geometries, adding an extra level of functionality to the printed objects. Furthermore, we incorporate chiral nematic LCs into the emulsion droplets, producing 3D objects with tunable reflective properties. To our knowledge, this is the first example of DLP 3D printing with emulsions, offering an effective and versatile pathway for developing 4D-printed materials with potential applications in optics, robotics, and biomedicine.

Optimising aerodynamic drag for enhanced robotic balancing

This paper introduces an innovative optimisation study for the Drag-Inducing Device (DI) on the AeroTail, a novel robotic tail designed to achieve balancing purely through aerodynamic drag. Jumping robots traditionally rely on reaction wheels for flight-phase orientation control, but inspired by nature, we propose a mass-less, aerodynamic tail device to overcome the added weight issue, leading to the conceptualisation of the AeroTail. The study ambitiously aims to engineer a DI that maximises drag generation while maintaining minimal weight, a crucial factor in robotic balancing efficiency. Addressing the gap in available analytic and wind tunnel performance data for optimal DI shapes, this research employs Computational Fluid Dynamics (CFD) simulations to scrutinise various shapes and discern how specific features influence drag production. An optimisation problem is subsequently formulated, leading to the development of an ideal DI frame design characterised by innovative ‘T’ shaped sections. Rigorous experimental validation confirms the superiority of a semi-cylindrical shaped DI, which emerges as the top performer among all contenders. Notably, the study reveals that the orientation of DI installation on the tail significantly impacts torque generation, with some configurations achieving an impressive 20.8 % enhancement in performance. This research not only provides valuable insights into aerodynamic drag optimisation for robotic applications but also sets a new benchmark in the design and functionality of robotic balancing devices.

Context-Specific Navigation for ‘Gentle’ Approach Towards Objects Based on LiDAR and URF Sensors

Navigation skills are essential for most social and service robotics applications. The robots that are currently in practical use in various complex human environments are generally very limited in their autonomous navigational abilities; while they can reach the proximity of objects, they are not efficient in approaching them closely. The new solution described in this paper presents a system to solve this context-specific navigation problem. The system handles locations with differing contexts based on the use of LiDAR and URF sensors, allowing for the avoidance of people and obstacles with a wide margin, as well as for approaching target objects closely. To quantify the efficiency of our solution we compared it with the ROS contextless standard navigation (move_base) in two different robot platforms and environments, both with real-world tests and simulations. The metrics selected were (1) the time the robot needs to reach an object, (2) the Euclidean distance, and (3) the orientation between the final position of the robot and the defined goal position. We show that our context-specific solution is superior to the standard navigation both in time and Euclidean distance.

A Fault Detection Robotic Cell Application Based on Deep Learning and Image Processing Hybrid Approach for Quality Control of Automotive Parts

A Fault Detection Robotic Cell Application Based on Deep Learning and Image Processing Hybrid Approach for Quality Control of Automotive Parts

A Self-Oscillator Based on Liquid Crystal Elastomer Fiber Under Constant Voltage.

Self-oscillation is the phenomenon in which a system generates spontaneous, consistent periodic motion in response to a steady external stimulus, making it highly suitable for applications in soft robotics, motors, and mechatronic devices. In this paper, we present a self-oscillator based on liquid crystal elastomer (LCE) fiber under constant voltage. The system primarily consists of an LCE-liquid metal (LCE-LM) composite fiber, a metal mass sphere, and a straight rod featuring both conductive and insulating segments. Building upon an established dynamic LCE model, we derive the governing dynamic equations. Numerical calculations reveal two distinct motion regimes: a static regime and a self-oscillation regime. Furthermore, we provide the temporal behavior curves of electrothermal-induced contraction and tensile force, the phase trajectories variation curves of the equivalent driving force and damping force. These detailed studies elucidate that self-oscillation results from the contraction of the electrothermal-responsive LCE-LM fiber when the circuit is activated, with continuous periodic motion being sustained through the interplay between the metal mass sphere and a self-controlled dynamic circuit. We also investigate the threshold conditions necessary for initiating self-oscillation, as well as the key system parameters that influence its frequency and amplitude. Our self-oscillator demonstrates improved stability by reducing the effects of gravity and other disturbances. Additionally, the curved trajectory of the mass sphere can be achieved by replacing the straight rod with a curved one, resulting in a more flexible and easily controllable structure. Given these characteristics, a self-oscillator system based on LCE-LM fiber may be ideal for creating monitoring and warning devices, dynamic circuit systems, and for integrating actuators and controllers.

Promoting Piezoelectricity in Amino Acids by Fluorination

AbstractBioinspired piezoelectric amino acids and peptides are attracting attention due to their designable sequences, versatile structures, low cost, and biodegradability. However, it remains a challenge to design amino acids and peptides with high piezoelectricity. Herein, a high piezoelectric amino acid by simple fluorination in its side chain is presented. The three phenylalanine derivatives are designed: Cbz‐Phe, Cbz‐Phe(4F), and Cbz‐pentafluoro‐Phe. The effect of fluorination on self‐assembly and piezoelectricity is investigated. Cbz‐Phe(4F) can self‐assemble into crystals with a C2 space group, while Cbz‐Phe and Cbz‐pentafluoro‐Phe form aggregated self‐assemblies. Moreover, Cbz‐Phe(4F) crystals exhibit a remarkably higher piezoelectric coefficient () of ≈17.9 pm V−1 than Cbz‐Phe and Cbz‐pentafluoro‐Phe. When fabricated as a piezoelectric nanogenerator, it generates an open‐circuit voltage of ≈2.4 V. Importantly, Cbz‐Phe(4F) crystals as a flexible piezoelectric sensor for the classification of various nuts and their quality sorting, which includes those as small as individual pumpkin seeds with high sensitivity and accuracy of sorting and quality checks. When mounted onto soft grippers, the sensor performs the tactile self‐sensing functions. This work provides a promising approach to designing high piezoelectric amino acids by simple fluorination, offering exciting prospects for advancements in bioinspired piezoelectric materials in the application of smart agriculture and soft robotics.

Multi‐Material Gradient Printing Using Meniscus‐enabled Projection Stereolithography (MAPS)

AbstractLight‐based additive manufacturing methods are widely used to print high‐resolution 3D structures for applications in tissue engineering, soft robotics, photonics, and microfluidics, among others. Despite this progress, multi‐material printing with these methods remains challenging due to constraints associated with hardware modifications, control systems, cross‐contamination, waste, and resin properties. Here, a new printing platform coined Meniscus‐enabled Projection Stereolithography (MAPS) is reported, a vat‐free method that relies on generating and maintaining a resin meniscus between a crosslinked structure and bottom window to print lateral, vertical, discrete, or gradient multi‐material 3D structures with no waste and user‐defined mixing between layers. MAPS is compatible with a wide range of resins shown and can print complex multi‐material 3D structures without requiring specialized hardware, software, or complex washing protocols. MAPS's ability to print structures with microscale variations in mechanical stiffness, opacity, surface energy, cell densities, and magnetic properties provides a generic method to make advanced materials for a broad range of applications.