Robotic System Research Articles

Intelligent Recommendation Algorithm for Product Information on E-commerce Platforms Based on Robot Customer Service Automatic Q&A

In order to enhance the shopping experience of customers and retain them, thereby increasing sales volume, the author proposes the research topic of an intelligent recommendation system for product information on e-commerce platforms based on robot customer service automatic question answering. Firstly, starting directly from the question itself, the system can provide feedback to customers by simply segmenting the questions submitted by customers and matching them with semantic templates; Secondly, the system automatically builds and updates the user’s personalized knowledge base, using this to predict user purchasing tendencies and achieve the function of recommending products to customers. The implementation of the intelligent shopping robot system has passed 365 question and answer tests on 5G mobile phone sales terms, and is feasible in the professional field. The experimental results indicate that, when the number of training corpora increased to 300, the accuracy of the system was 0.85, 0.90, and 0.98 using 100, 2003, and 300 tests respectively. Such a system is perfect for natural language processing, so we can improve the system by expanding and improving the knowledge base. The intelligent shopping robot recommendation system studied by the author is still in the analysis and demonstration stage, sincerely hope that the processing method used in this project can have reference significance for similar recommendation systems in the near future.

Runtime Verification and Field-Based Testing for ROS-Based Robotic Systems

Runtime Verification and Field-Based Testing for ROS-Based Robotic Systems

AUTONOMOUS MONITORING ROBOT SYSTEM THAT MEASURES AIR POLLUTION

Air pollution poses a significant threat to human health, ecosystems, and climate stability, necessitating effective monitoring and control measures. Traditional air quality monitoring stations, while accurate, are static, expensive, and limited in coverage. The Autonomous Monitoring Robot System (AMRS) provides a dynamic solution, offering real-time air quality monitoring through mobile robotic platforms. Equipped with advanced sensors, these robots can measure various pollutants, such as particulate matter (PM), nitrogen dioxide (NO2), carbon monoxide (CO), and volatile organic compounds (VOCs), across large and complex areas. By employing AI-based navigation and mapping technologies, AMRS can autonomously traverse urban and industrial environments, collecting high-resolution pollution data and creating real-time air quality maps. This approach allows for better spatial coverage, cost-efficiency, and access to hard-to-reach locations compared to traditional methods. The system can be deployed in diverse use cases, including urban air quality monitoring, industrial pollution control, and disaster management. While challenges such as battery life, sensor calibration, and data processing remain, AMRS represents a promising technological advancement in environmental monitoring and pollution control.

Fracture-driven power amplification in a hydrogel launcher.

Robotic tasks that require robust propulsion abilities such as jumping, ejecting or catapulting require power-amplification strategies where kinetic energy is generated from pre-stored energy. Here we report an engineered accumulated strain energy-fracture power-amplification method that is inspired by the pressurized fluidic squirting mechanism of Ecballium elaterium (squirting cucumber plants). We realize a light-driven hydrogel launcher that harnesses fast liquid vapourization triggered by the photothermal response of an embedded graphene suspension. This vapourization leads to appreciable elastic energy storage within the surrounding hydrogel network, followed by rapid elastic energy release within 0.3 ms. These soft hydrogel robots achieve controlled launching at high velocity with a predictable trajectory. The accumulated strain energy-fracture method was used to create an artificial squirting cucumber that disperses artificial seeds over metres, which can further achieve smart seeding through an integrated radio-frequency identification chip. This power-amplification strategy provides a basis for propulsive motion to advance the capabilities of miniaturized soft robotic systems.

Task-Oriented Adaptive Position/Force Control for Robotic Systems Under Hybrid Constraints

Task-Oriented Adaptive Position/Force Control for Robotic Systems Under Hybrid Constraints

Soft Fibrous Syringe Architecture for Electricity-Free and Motorless Control of Flexible Robotic Systems.

Flexible robotic systems (FRSs) and wearable user interfaces (WUIs) have been widely used in medical fields, offering lower infection risk and shorter recovery, and supporting amiable human-machine interactions (HMIs). Recently, soft electric, thermal, magnetic, and fluidic actuators with enhanced safety and compliance have innovatively boosted the use of FRSs and WUIs across many sectors. Among them, soft hydraulic actuators offer great speed, low noise, and high force density. However, they currently require bulky electric motors/pumps, pistons, valves, rigid accessories, and complex controllers, which inherently result in high cost, low adaptation, and complex setups. This paper introduces a novel soft fibrous syringe architecture (SFSA) consisting of two or more hydraulically connected soft artificial muscles that enable electricity-free actuation, motorless control, and built-in sensing ability for use in FRSs and WUIs. Its capabilities are experimentally demonstrated with various robotic applications including teleoperated flexible catheters, cable-driven continuum robotic arms, and WUIs. In addition, its sensing abilities to detect passive and active touch, surface texture, and object stiffness are also proven. These excellent results demonstrate a high feasibility of using a current-free and motor-less control approach for the FRSs and WUIs, enabling new methods of sensing and actuation across the robotic field.

Development and validation of a robotic system for milling individualized jawbone cavities in oral and maxillofacial surgery

ObjectivesThis study aimed to develop and validate a robotic system capable of performing accurate and minimally invasive jawbone milling procedures in oral and maxillofacial surgery. MethodsThe robotic hardware system mainly includes a UR5E arm (Universal Robots, Denmark) and the binocular positioning system (FusionTrack 250, Atracsys LLC, Switzerland). The robotic software (Dental Navi 3.0.0, Yakebot Technology Ltd., China) is capable of generating cutting tool paths based on three-dimensional shape description files, typically in the stereolithography format, and selected cutting tool parameters, as well as designing surgical accessories. Fully impacted supernumerary tooth models in the maxilla were fabricated using software and three-dimensional printing. Following the planning of a customized cavity to fully expose the tooth, maxillary bone milling was performed on both the robot and static guide groups (n = 8). After milling, all models underwent scanning for assessment. ResultsIn the experiment with fully buried supernumerary tooth models in the maxilla, the root mean square, translation error, over-removal rate, and maximum distance were significantly smaller in the robot group compared to the static guide group. Moreover, the overlap ratio and Dice coefficient were significantly greater in the robot group. No statistically significant differences were observed between the two groups in terms of the rotation error (P = 0.80) or under-removal rate (P = 0.92). ConclusionsThis study has developed a robotic system for milling individualized jawbone cavities in oral and maxillofacial surgery, and its accuracy has been preliminarily verified to meet clinical requirements. Clinical significanceThe robotic system can achieve precise, minimally invasive, individualized jawbone milling in a variety of oral and maxillofacial surgeries, including tooth autotransplantation, surgical reshaping for zygomatic fibrous dysplasia, removal of fully impacted supernumerary or impacted teeth, and endodontic microsurgery, among other relevant clinical applications.

Overcoming the Learning Curve in Robot-Assisted Spinal Surgery—How Does It Compare to O-Arm Navigation?

Background: Robotic systems have the potential to significantly enhance the accuracy and outcomes of spinal surgery. Adopting this new technology requires an examination of its learning curve and influencing factors. This study analyzes the learning curve associated with using the Mazor X Stealth Edition system for pedicle screw placement and performs a matched-pair analysis to compare operative durations between robot-assisted and navigation-based surgeries, evaluating the efficiency of the robotic system. Methods: We collected retrospective operative data from patients who underwent robot-assisted pedicle screw placements between December 2020 and June 2024 and conducted a cumulative sum (CuSUM) analysis to assess the learning curve, focusing on the robotic system’s setup duration. Additionally, we compared a group of patients who underwent robot-assisted pedicle screw placements with a pair-matched group who underwent O-arm-based navigation-assisted pedicle screw placements. Results: There was a notable decrease in the robotic setup duration, with a significant shift in trend observed after the first 20 cases. While the initial setup time was 24 minutes, it reduced to 17 minutes in later cases, reflecting a marked improvement in efficiency as the surgeon gained more experience with the robot. Conclusion: Our findings indicate there were no added difficulties using the robotic system compared to the navigation system. Moreover, the learning curve for the robotic system can be quickly surmounted, and it offers clear advantages over previous systems, making it a valuable tool for pedicle screw application.

Implementing a Vision-Based ROS Package for Reliable Part Localization and Displacement from Conveyor Belts

The use of computer vision in the industry has become fundamental, playing an essential role in areas such as quality control and inspection, object recognition/tracking, and automation. Despite this constant growth, robotic cell systems employing computer vision encounter significant challenges, such as a lack of flexibility to adapt to different tasks or types of objects, necessitating extensive adjustments each time a change is required. This highlights the importance of developing a system that can be easily reused and reconfigured to address these challenges. This paper introduces a versatile and adaptable framework that exploits Computer Vision and the Robot Operating System (ROS) to facilitate pick-and-place operations within robotic cells, offering a comprehensive solution for handling and sorting random-flow objects on conveyor belts. Designed to be easily configured and reconfigured, it accommodates ROS-compatible robotic arms and 3D vision systems, ensuring adaptability to different technological requirements and reducing deployment costs. Experimental results demonstrate the framework’s high precision and accuracy in manipulating and sorting tested objects. Thus, this framework enhances the efficiency and flexibility of industrial robotic systems, making object manipulation more adaptable for unpredictable manufacturing environments.

A Simulation-Based Approach for Evaluating the Effectiveness of Robotic Automation Systems in HMR Product Loading.

The food industry has tried to enhance production processes in response to the increasing demand for safe, high-quality Home Meal Replacement (HMR) products. While robotic automation systems are recognized for their potential to improve efficiency, their high costs and risks make them less accessible to small and medium-sized enterprises (SMEs). This study presents a simulation-based approach to evaluating the feasibility and impact of robotic automation on HMR production, focusing on two distinct production cases. By modeling large-scale and order-based production cases using simulation software, the study identified key bottlenecks, worker utilization, and throughput improvements. It demonstrated that robotic automation increased throughput by 31.2% in large-scale production (Case A) and 12.0% in order-based production (Case B). The actual implementation showed results that closely matched the simulation, validating the approach. Moreover, the study confirmed that a single worker could operate the robotic system effectively, highlighting the practicality of robotics for SMEs. This research provides critical insights into integrating robotics to enhance productivity, reduce labor dependency, and facilitate digital transformation in food manufacturing.

Development of a robotic wheel door opener system assistive device

Physical disabilities significantly impact individuals' ability to perform activities of daily living (ADL), leading to reduced autonomy and difficulty to accomplish daily living tasks. One such barrier is the difficulty or inability to open doors, preventing access to different rooms in their residence (bathroom, bedroom, etc.), rooms at work, or shopping areas. Existing solutions, such as robotic arms on wheelchairs and door openers mounted at the top of doors, remain expensive, complex to install, and relatively difficult for the target population to use. Addressing this challenge, this study introduces a Robotic Wheel Door Opener System (RWDOS) designed to facilitate the opening and closing of the door. The RWDOS is installed at the bottom of a door and is controlled remotely through a smartphone application. The paper presents the mechanical design and control system along with a cost analysis. It concludes with initial results and outlines the future directions for the project.

Mixed H2/H-infinity Controller Design for Triple Inverted Pendulum System

The steady increase in reliance on robotic systems in industrial applications arises the need to ensure their reliability despite the presence of external disturbances in the environment they work in and their parameters variations due to several factors like: change of temperature, wear and tear effect, and payload variation. Traditional controllers usually fail to maintain the system's stability and performance in the presence of uncertainty, while robust controllers aim to guarantee stability and desired performance across a range of possible uncertainties in the system through incorporating these uncertainties into their design process. This paper investigates the robustness of three controllers namely, H2 controller, H-infinity controller, and mixed H2/H-infinity controller, applied to the triple inverted pendulum system which translates to robustly control legged robots and robotic arms. The results show that among the three controllers, only the mixed H2/H-infinity control system is robustly stable and maintains its performance with stability margin 1.1864 and performance margin 1.1662. Index Terms— H2, H-infinity, Mixed H2/H-infinity, Robust Control, triple inverted pendulum.

Reinforcement learning in autonomous defense systems: Strategic applications and challenges

Reinforcement learning (RL) is one of the most progressive ways to improve the efficiency of drones and robotic systems in the context of the defense and security industries. In Anomaly Detection (AD) systems, this paper discusses the potential of RL as a Model Selection Criteria (MSC) method and its associated issues. RL algorithms enable such systems to adapt to and learn from interactions with their environment, optimizing their response to complex and dynamic threats. This way, new states may be introduced with better decision-making processes, improving the effectiveness of the operations and enabling Reinforcement learning -powered systems to learn new scenarios as well as perform detailed defensive actions in a real-time context. The importance of RL in national defense can therefore be said to lie in its capacities for changing how threats are identified, how threats are responded to, and even what strategies of defense are thought of. Self-governing systems that incorporate Reinforcement learning are capable of functioning in an unpredictable environment, evaluating threats correctly, and carrying out defensive measures with the help of people practically at all. This versatility is critical in modern warfare because a preferred option is the right response to threats that were unknown a few years ago. However, incorporating RL into autonomous defense systems is not without big challenges. Some important problem areas are improved stability and accuracy of RL algorithms in various and critical situations, the legal and practical consequences of autonomous decision-making and possible threats that can arise due to adversarial manipulation of learning algorithms. In addition, such systems have to be developed and put into practice under national and international standards to meet certain requirements and build confidence in such applications. This paper explores these strategic uses and issues and presents a detailed overview of how RL can improve independent defense functionalities, as well as the significant problems relating to this approach. Thus, by providing case studies and theoretical analysis, it aims to demonstrate that RL has the potential to define the technological development of defense and benefit national security systems in the context of a growing threat.

Development of an imitation learning method for a neural network system of mobile robot’s movement on example of the maze solving

Objectives. To develop a new method for training a mobile robot control system to use a maze solver algorithm based on reinforcement learning and the right-hand algorithm.Methods. The work uses the method of computer modeling in the MATLAB/Simulink environment.Results. A new method for training a mobile robot control system capable of implementing the right-hand algorithm for finding an exit from a maze is proposed. The proposed method is based on the work of two agents interacting with each other: the first directly implements the search algorithm and searches for an exit from the maze, and the second, following it, tries to learn using the imitation learning method. The expert agent, implementing a discrete algorithm for moving through the maze, makes precise discrete steps and moves almost independently of the second agent. The only limitation is its speed, which is directly proportional to the distance between the agents. The second agent, the student agent, tries to reduce the distance to the first agent by trial and error. The learning process was implemented using the reinforcement learning method, which was used in the imitation mode and for which a corresponding reward function was developed, allowing the robot's center of mass to be kept in the center of the corridor and, if necessary, to turn, following the expert agent. The agents move along a virtual polygon consisting of branched corridors wide enough to implement various movement maneuvers.Conclusion. It was proven that, thanks to the proposed method of imitative learning, the student agent is able not only to adopt the required behavior patterns from the expert agent – to search for an exit in a previously unknown labyrinth using the right-hand algorithm, but also to independently acquire new ones (changing speed on a turn, bypassing small dead-end corridors), which positively influence the performance of the assigned task.

A Self-Driven Ga2O3 Memristor Synapse for Humanoid Robot Learning.

In recent years, the rapid development of brain-inspired neuromorphic systems has created an imperative demand for artificial photonic synapses that operate with low power consumption. In this study, a self-driven memristor synapse based on gallium oxide (Ga2O3) nanowires is proposed and demonstrated successfully. This memristor synapse is capable of emulating a range of functionalities of biological synapses when exposed to 255nm light stimulation. These functionalities encompass peak time-dependent plasticity, pulse facilitation, and memory learning capabilities. It exhibits an ultrahigh paired-pulse facilitation index of 158, indicating exceptional learning performance. The transition from short-term memory to long-term memory can be attributed to the remarkable relearning capabilities. Furthermore, the potential applications of the memristor synapse is showcased through the successful manipulation of a humanoid intelligent robot. Upon establishing artificial intelligence (AI) systems, the control commands originating from the synaptic device can drive the humanoid robot to perform various actions. Based on the memristor synapses, the autonomous feedback system of the humanoid robot facilitates a good collaboration between robotic actions and bio-inspired light perception. Therefore, this research opens up an effective way to advance the development of neuromorphic computing technologies, AI systems, and intelligent robots that demand ultra-low energy consumption.

Mobile robots control with neuromorphic classifires of environment states

The article proposes to implement mobile robots control systems using neuromorphic classifiers, in which biosimi-lar neurons are built on an original neuro-fuzzy model, trained to display the function of the Izhikevich neuron. Us-ing this approach, neuromorphic classifiers of spatial and spatiotemporal patterns were developed. Such a classi-fiers were used in non-contact supervisory control system for mobile robot based on static and dynamic states of the environment. The experiments performed demonstrated the effectiveness of using the neuromorphic classifi-ers, both in a neural interface when recognizing imaginary supervisory commands of the user, and when solving problems of robot navigation in environments with static and dynamic obstacles. At comparative analysis of navi-gation systems implemented using the neuromorphic classifiers, modular fuzzy logic and the adaptive neuro-fuzzy system ANFIS it was shown that the system with the neuromorphic classifiers give the highest average speed of the robot, as well as the shortest travel time. An experiment with the use of the neuromorphic classifiers in the con-trol system based on dynamic states of the environment showed that robot successfully avoids collisions with per-son.

Bridging vision and touch: advancing robotic interaction prediction with self-supervised multimodal learning.

Predicting the consequences of the agent's actions on its environment is a pivotal challenge in robotic learning, which plays a key role in developing higher cognitive skills for intelligent robots. While current methods have predominantly relied on vision and motion data to generate the predicted videos, more comprehensive sensory perception is required for complex physical interactions such as contact-rich manipulation or highly dynamic tasks. In this work, we investigate the interdependence between vision and tactile sensation in the scenario of dynamic robotic interaction. A multi-modal fusion mechanism is introduced to the action-conditioned video prediction model to forecast future scenes, which enriches the single-modality prototype with a compressed latent representation of multiple sensory inputs. Additionally, to accomplish the interactive setting, we built a robotic interaction system that is equipped with both web cameras and vision-based tactile sensors to collect the dataset of vision-tactile sequences and the corresponding robot action data. Finally, through a series of qualitative and quantitative comparative study of different prediction architecture and tasks, we present insightful analysis of the cross-modality influence between vision, tactile and action, revealing the asymmetrical impact that exists between the sensations when contributing to interpreting the environment information. This opens possibilities for more adaptive and efficient robotic control in complex environments, with implications for dexterous manipulation and human-robot interaction.

Internal validation of the Tampa Robotic Difficulty Scoring System: real-time assessment of the novel robotic scoring system in predicting clinical outcomes after hepatectomy.

As the robotic approach in hepatectomy gains prominence, the need to establish a robotic-specific difficulty scoring system (DSS) is evident. The Tampa Difficulty Score was conceived to bridge this gap, offering a novel and dedicated robotic DSS aimed at improving preoperative surgical planning and predicting potential clinical challenges in robotic hepatectomies. In this study, we internally validated the recently published Tampa DSS by applying the scoring system to our most recent cohort of patients. The Tampa Difficulty Score was applied to 170 recent patients who underwent robotic hepatectomy in our center. Patients were classified into: Group 1 (score 1-8, n = 23), Group 2 (score 9-24, n = 120), Group 3 (score 25-32, n = 20), and Group 4 (score 33-49, n = 7). Key variables for each of the groups were analyzed and compared. Statistical significance was accepted at p ≤ 0.05. Notable correlations were found between the Tampa Difficulty Score and key clinical parameters such as operative duration (p < 0.0001), estimated blood loss (p < 0.0001), and percentage of major resection (p = 0.00007), affirming the score's predictive capacity for operative technical complexity. The Tampa Difficulty Score also correlated with major complications (Clavien-Dindo ≥ III) (p < 0.0001), length of stay (p = 0.011), and 30-day readmission (p = 0.046) after robotic hepatectomy. The Tampa Difficulty Score, through the internal validation process, has confirmed its effectiveness in predicting intra- and postoperative outcomes in patients undergoing robotic hepatectomy. The predictive capacity of this system is useful in preoperative surgical planning and risk categorization. External validation is necessary to further explore the accuracy of this robotic DSS.

Design of an Optimal Multivariable PID Controller for a Two-Link Robot Arm

Incorporating manipulator robots into various industries has revolutionized automation and manufacturing processes. Manipulator robots are versatile machines equipped with robotic arms and end-effectors, enabling them to handle complex tasks with precision and efficiency. This research aims to design an optimal Mutivariable PID (MPID) controller that ensures precise and accurate movements of two-link robot arm. Theoretical foundations of the MPID controller are discussed together with its relevance to robotic arm systems, and the challenges associated with its implementation. The research methodology involves mathematical modelling of the two-link robot arm dynamics, and the use of an optimization algorithm to determine the optimal MPID controller coefficients. Simulation results demonstrate performance enhancement and productivity of the two-link robot arm through the improved MPID controller.

Voice Control System for Robotics in a Noisy Environment

This paper analyzes the effectiveness of the developed voice control system for robotics based on MFCC and GMM-SVM under the influence of interference in the communication channel. The system allows characterizing individual features of speech signals with their subsequent classification and making a reliable decision on the interpretation and execution of voice commands by robotic equipment. The proposed voice control system for robotics based on MFCC and GMM-SVM is implemented using the following technologies: 1) selection of active speech areas by calculating the short-term energy and the number of zero crossings between adjacent frames of the speech signal; 2) adaptive wavelet filtering of the speech signal, where it is necessary to generate threshold values, which will reduce the impact of additive noise; 3) selection of recognition features, which are used as mel-frequency cepstral coefficients; 4) classification of recognition features based on mixtures of Gaussian distributions and the support vector method using the linear Campbell kernel and the principal component method with a projection on latent structures, which will reduce errors of the 1st and 2nd kind.