Robotic Applications Research Articles

Experimental study of ARtag-based indoor localization techniques

Abstract To address the limitations of traditional indoor localization techniques in indoor environments, the ARtag indoor localization technique is proposed to determine the optimal recognition distance to optimize the robot’s localization performance in indoor environments. The performance of the robot at different distances is evaluated by setting up an ARtag at different distances in an indoor environment, testing and comparing the robot’s recognition accuracy and response time at these distances. The experimental results show that at a distance of 25 cm, the robot has the fastest response speed and the highest stability, with a recognition accuracy of 100% and a response time of only 0.39 ms. The ARtag indoor localization technique can significantly improve the robot’s localization performance at specific distances, which can provide a basis for optimizing the performance of indoor robotic applications.

Leveraging Environmental Contact and Sensor Feedback for Precision in Robotic Manipulation.

This paper investigates methods that leverage physical contact between a robot's structure and its environment to enhance task performance, with a primary emphasis on improving precision. Two main approaches are examined: solving the inverse kinematics problem and employing quadratic programming, which offers computational efficiency by utilizing forward kinematics. Additionally, geometrical methods are explored to simplify robot assembly and reduce the complexity of control calculations. These approaches are implemented on a physical robotic platform and evaluated in real-time applications to assess their effectiveness. Through experimental evaluation, this study aims to understand how environmental contact can be utilized to enhance performance across various conditions, offering valuable insights for practical applications in robotics.

Polyacrylamide/starch hydrogels doped with layered double hydroxides towards strain sensing applications

Electrically conductive hydrogels have attracted enormous attention due to the rapid development of flexible electronics. In this paper, the application of layered double hydroxides (LDHs) in the field of conductive hydrogel for strain sensing is firstly explored. LDHs are introduced to the polyacrylamide (PAM)/starch (St) semi-interpenetrating network (SIPN) to fabricate conductive PAM/St/LDHs (PSL) hydrogels for strain sensing applications. The results show that LDHs incorporated into PAM/St SIPN as inorganic nano fillers not only improve the mechanical strength, but also innovatively endow the hydrogel with electrical conductivity properties. The PSL hydrogels exhibit excellent mechanical properties (with an elongation strain of 1750 % and a fracture strength of 0.22 MPa) and decent sensing properties (with a gauge factor of 2.73). As a proof of concept, an 8*8 sensing array based on PSL hydrogels is designed to realize the visualization of pressure sensing, demonstrating the broad prospect of PSL hydrogels in applications of human-computer interaction, flexible wearable and soft robotics.

Is minimally invasive surgery a game changer in spinal surgery?

Minimally invasive spine surgery (MISS) has revolutionized the treatment of spinal disorders over the past few decades. This review provides an in-depth analysis of MISS techniques, technologies, outcomes, and future directions. The evolution of MISS techniques-including tubular retractor systems, percutaneous pedicle screw fixation, minimally invasive transforaminal lumbar interbody fusion, lateral lumbar interbody fusion, and endoscopic spine surgery-has expanded the scope of treatable spinal pathologies while minimizing tissue trauma. Technological advancements such as intraoperative navigation, robotics, and augmented reality applications have enhanced precision and capabilities. Clinical evidence supports the efficacy and safety of MISS techniques for various spinal pathologies, demonstrating comparable or superior outcomes to traditional open approaches with reduced tissue trauma, blood loss, and hospital stays. Cost-effectiveness analyses also favor MISS over open techniques. Future directions in MISS include expanding indications, integrating artificial intelligence and machine learning, advancing tissue engineering and biologics, and refining robotic and augmented reality applications. As MISS continues to evolve, it is poised to play an increasingly important role in the treatment of spinal disorders, offering improved patient outcomes with reduced morbidity. However, ongoing rigorous evaluation of new techniques and technologies is crucial to balance potential benefits with associated risks and costs.

Research on Bionic Robot Motion Control Based on Reinforcement Learning

This research explores the application of reinforcement learning (RL) to enhance the motion control of bio-inspired robots across various environments. Focusing on underwater, terrestrial, and aerial robotic models, the study integrates model-free Q-learning, Deep Q Network (DQN), State-Action-Reward-State-Action (SARSA), and Double Deep Q Network (DDQN) algorithms. These methods are employed to achieve adaptive and efficient movement strategies without relying on pre-defined environmental models. The methodologies range from real-time data capture using live camera feeds for terrestrial robots to simulating aquatic and flight dynamics in controlled environments. Experimental results confirm the efficacy of these RL methods, demonstrating significant improvements in the robots' ability to adapt to dynamic and unknown environments, optimize movement efficiency, and navigate complex scenarios. The findings suggest a promising direction for future robotic applications, emphasizing the need for further research on optimizing these algorithms and expanding their real-world applicability. This study highlights the potential of RL to revolutionize robotic motion control, making robots more versatile and capable in varied and unpredictable settings.

Comparative Analysis of Value Iteration and Policy Iteration in Robotic Decision-Making

This study focuses on Markov Decision Processes (MDPs) as a framework for decision-making in robotics. MDPs are crucial for enabling autonomous systems to operate in dynamic environments. MDPs enable the development of optimal strategies that balance immediate and future rewards, making them essential for intelligent robotic behavior. The purpose of this study is to evaluate the performance differences of value iteration and strategy iteration algorithms in different robot tasks. The study highlights the strengths and weaknesses of each algorithm. This comparative analysis uniquely addresses a gap in existing research by evaluating both Value Iteration and Policy Iteration side by side, offering critical insights into their respective performances across diverse robotic tasks. Results indicate that Policy Iteration converges faster and adapts better in complex environments, making it ideal for real-time applications, while Value Iteration is more efficient in smaller state spaces.These findings provide critical insights for selecting algorithms tailored to specific robotic applications, highlighting their role in advancing intelligent robotic systems.

Design and Applications of High Force Generation in 3D-Printed Pneumatic Artificial Muscles

Increasing the force generation and scalability of soft pneumatic actuators poses significant challenges in robotics applications, especially where high load capacities and precise control are required. This paper presents UniBPAM, a novel, scalable soft pneumatic actuator optimized through 3D printing to enhance force generation. By analyzing design parameters, such as the number of sides, height, and origami factor, UniBPAM achieved a 21.48% increase in force generation. Scalable across diameters from 36 to 144 mm, the actuator demonstrated the ability to lift up to 57 kg with 84.9% strain at larger scales. Additionally, the BiBPAM variant enables bidirectional actuation in robotic joints via motion control, which is realized through PID systems, making it suitable for various robotic applications.

Control of Multi-Robot Arms in Object Retrieval Based on Human-Machine Interface

Multi-robot arm control is the result of the development of advanced robotics technology. With the advancement in the field of human-machine interface, controlling robot arms has become more efficient and can be done intuitively by humans. In this study, we designed three robot arms of 4-DoF, each of which is controlled by a computer in a visual program interface. This research aims to develop a human-machine interface-based multi-robot arm control system that allows humans to interact with the robots directly. The movement method of each robot uses Trajectory Planning, which works when the operator gives motion commands through the interface display. Multi-robot communication with a computer using USB hub serial format. The computer is the master, and each Arduino on the robot is the enslaved. Three robot arms have been tested and controlled by the HMI computer, and all of them move according to the commands of the operator. The time required by each robot to complete its mission is ± 10 seconds. The results of this study are expected to open new opportunities in the application of robotics in various fields, such as the manufacturing industry, health services, and transportation.

Oriblock: The origami-blocks based on hinged dissection

Traditional origami, a well-known art of paper-folding, does not account for material thickness. Subsequently, several thickness-accommodation techniques have been developed, considering the non-negligible thickness of materials, which enables the application of origami to a wide range of mechanisms. Although these techniques prevent self-intersections and preserve kinematics after accommodating panel thickness, they are limited by their reliance on initial zero-thickness origami patterns in two dimensions. To address this issue, this study proposes a novel technique, the volume-accommodation technique in three-dimensional space, which allocates non-coplanar origami creases based on solid geometry to allow a greater variety of shape-changing motions. Typical solid geometries, such as a pyramid and a prism, are selected as examples to demonstrate the design procedures. Closure equations of the obtained oriblock are used to analyze the kinematic properties. Additionally, Bennett and Myard Linkages are derived from oriblocks based on their kinematic equivalence to strengthen their connections. As a result, this new type of origami can offer a variety of mechanisms for designers and facilitate potential applications in origami-inspired metamaterials and robotics.

A scoping review of robotic technology in hospitality and tourism

Purpose With the disruptive evolution of artificial intelligence (AI), the roles of robotics in hospitality and tourism are shifting rapidly from automatic to emotional works. Although academics have focused on examining robotic applications in hospitality and tourism, concrete images of the different roles of robots are unclear. Thus, this study aims to systematically aggregate and evaluate existing robotic technology-related studies published in Social Science Citation Index-listed hospitality and tourism journals to link the fragmented knowledge and provide an up-to-date overview of robotic technology in hospitality and tourism. Design/methodology/approach This study retrieved 134 robotic technology-related articles and used descriptive and content analyses to analyze the retrieved papers thoroughly. Findings The top keyword identified was service robot. Robotic technologies are categorized into AI-supplemented, AI-generated, robotic technology anthropomorphism (RTA)-facilitated and RTA-mediated. Research limitations/implications Future studies can consider exploring service robots further from the perspectives of suppliers in tourism. A more comprehensive categorization of robotic technologies is also recommended. Originality/value This study contributes to the robotic research realm by providing a holistic view of robotic applications in hospitality and tourism research. This study also attempts to pin down the potential research directions to guide researchers in expanding future studies.

3D printed conductive hydrogel based on silk fibroin and tetramer-grafted-polyethylenimine micelle for body-motion monitoring

Conductive hydrogels hold significant promise for applications in flexible wearable, soft robotics, implantable devices, and other fields, which offer distinct advantages due to their biomimetic structures, intrinsic properties, and biocompatibility. This study builds upon our previous research by fabricating a conductive hydrogel through the combination of 30 % Pluronic F127 and aniline tetramer-grafted-polyethyleneimine (AT-PEI) copolymers. To enhance the properties of hydrogels, we successfully engineered silk fibroin-based conductive hydrogels (SF-AD) by inducing the transition of silk fibroin from a random coil to a β-sheet structure using the F127 and AT-PEI/DNA complex (AD), endowing the hydrogels with dual ionic and electronic conductivity. The conductivity of all hydrogel exceeds 10−4 S/cm. Additionally, SEM was employed to characterize the pore size of the hydrogels, revealing a decrease with higher AD content. The swelling ratio ranged between 4.89 and 6.50, indicating the tunable nature of the hydrogels' structure. Utilizing 3D printing, we produced a 2 × 2 cm2 mesh active conductive layer that ensures a more uniform stress distribution—maximum sensitivity with a grid width of 4 mm. Our assembled hydrogel sensor demonstrated long-term stability in cycling tests over 1000 cycles and proved capable of recognizing various human movements. The SF-AD hydrogel, characterized by its unique combination of properties and potential for customization, presents broad prospects for future applications in flexible electronics.

Modeling Backlash-like Hysteresis and Feedforward Control of Tendon-Sheath Mechanism Pair with Arbitrary Shape: Excluding Distal Sensory Input

Abstract The tendon-sheath mechanism (TSM) has garnered attention for its versatile applications in soft robotics, robotic hands, and surgical robots due to its adeptness in transmitting force through tortuous and narrow channels. However, precise control of the TSM is challenging due to its shape-dependent deformation and force generation, highlighting the need to address shape variations in dynamic environments where direct measurement is impractical. This paper introduces a novel methodology leveraging the concept of the equivalent circle in TSM to model its shape under varying conditions. The equivalent circle substitutes an arbitrarily shaped TSM with a circle, whose radius is derived from TSM's deformation and forces measured at the proximal end during calibration. This approach provides a concise and effective framework for understanding and analyzing the distinct characteristics of TSM. Additionally, a control strategy is proposed, utilizing the estimated equivalent circle to adapt to dynamic environments. Experimental results demonstrate promising performance without distal end sensory feedback, with mean percentage errors (MPE) of 0.78% and 2.33% for predicting cumulated curve angle and equivalent circle radius, respectively. Moreover, by utilizing the equivalent circle to calculate and feedforward deadband, effective control is achieved. The root mean square error (RMSE) reduced from 1.31 mm to an average of 0.19 mm in two feedforward experiments, representing an average reduction of 85.5%. These findings shed light on effective control strategies for TSM, offering valuable insights for robotics and surgical applications where TSM shape configurations are uncertain and subject to dynamic change.

Behavioral Cloning Strategies in Steering Angle Prediction: Applications in Mobile Robotics and Autonomous Driving

Artificial neural networks (ANNs) are artificial intelligence techniques that have made autonomous driving more efficient and accurate; however, autonomous driving faces ongoing challenges in the accuracy of decision making based on the analysis of the vehicle environment. A critical task of ANNs is steering angle prediction, which is essential for safe and effective navigation of mobile robots and autonomous vehicles. In this study, to optimize steering angle prediction, NVIDIA’s architecture was adapted and modified along with the implementation of the Swish activation function to train convolutional neural networks (CNNs) by behavioral cloning. The CNN used human driving data obtained from the UDACITY beta simulator and tests in real scenarios, achieving a significant improvement in the loss function during training, indicating a higher efficiency in replicating human driving behavior. The proposed neural network was validated through implementation on a differential drive mobile robot prototype, by means of a comparative analysis of trajectories in autonomous and manual driving modes. This work not only advances the accuracy of steering angle predictions but also provides valuable information for future research and applications in mobile robotics and autonomous driving. The performance results of the model trained with the proposed CNN show improved accuracy in various operational contexts.

Hyper CLS-Data-Based Robotic Interface and Its Application to Intelligent Peg-in-Hole Task Robot Incorporating a CNN Model for Defect Detection

Various types of numerical control (NC) machine tools can be standardly operated and controlled based on NC data that can be easily generated using widespread CAD/CAM systems. On the other hand, the operation environments of industrial robots still depend on conventional teaching and playback systems provided by the makers, so it seems that they have not been standardized and unified like NC machine tools yet. Additionally, robotic functional extensions, e.g., the easy implementation of a machine learning model, such as a convolutional neural network (CNN), a visual feedback controller, cooperative control for multiple robots, and so on, has not been sufficiently realized yet. In this paper, a hyper cutter location source (HCLS)-data-based robotic interface is proposed to cope with the issues. Due to the HCLS-data-based robot interface, the robotic control sequence can be visually and unifiedly described as NC codes. In addition, a VGG19-based CNN model for defect detection, whose classification accuracy is over 99% and average time for forward calculation is 70 ms, can be systematically incorporated into a robotic control application that handles multiple robots. The effectiveness and validity of the proposed system are demonstrated through a cooperative pick and place task using three small-sized industrial robot MG400s and a peg-in-hole task while checking undesirable defects in workpieces with a CNN model without using any programmable logic controller (PLC). The specifications of the PC used for the experiments are CPU: Intel(R) Core(TM) i9-10850K CPU 3.60 GHz, GPU: NVIDIA GeForce RTX 3090, Main memory: 64 GB.

GRID-FAST: A Grid-based Intersection Detection for Fast Semantic Topometric Mapping

This article introduces a novel approach to constructing a topometric map that allows for efficient navigation and decision-making in mobile robotics applications. The method generates the topometric map from a 2D grid-based map. The topometric map segments areas of the input map into different structural-semantic classes: intersections, pathways, dead ends, and pathways leading to unexplored areas. This method is grounded in a new technique for intersection detection that identifies the area and the openings of intersections in a semantically meaningful way. The framework introduces two levels of pre-filtering with minimal computational cost to eliminate small openings and objects from the map which are unimportant in the context of high-level map segmentation and decision making. The topological map generated by GRID-FAST enables fast navigation in large-scale environments, and the structural semantics can aid in mission planning, autonomous exploration, and human-to-robot cooperation. The efficacy of the proposed method is demonstrated through validation on real maps gathered from robotic experiments: 1) a structured indoor environment, 2) an unstructured cave-like subterranean environment, and 3) a large-scale outdoor environment, which comprises pathways, buildings, and scattered objects. Additionally, the proposed framework has been compared with state-of-the-art topological mapping solutions and is able to produce a topometric and topological map with up to 92% fewer nodes than the next best solution. The method proposed in this article has been implemented in the robotics framework ROS and is open-sourced. The code is available at: https://github.com/LTU-RAI/GRID-FAST.

Stereo and LiDAR Loosely Coupled SLAM Constrained Ground Detection.

In many robotic applications, creating a map is crucial, and 3D maps provide a method for estimating the positions of other objects or obstacles. Most of the previous research processes 3D point clouds through projection-based or voxel-based models, but both approaches have certain limitations. This paper proposes a hybrid localization and mapping method using stereo vision and LiDAR. Unlike the traditional single-sensor systems, we construct a pose optimization model by matching ground information between LiDAR maps and visual images. We use stereo vision to extract ground information and fuse it with LiDAR tensor voting data to establish coplanarity constraints. Pose optimization is achieved through a graph-based optimization algorithm and a local window optimization method. The proposed method is evaluated using the KITTI dataset and compared against the ORB-SLAM3, F-LOAM, LOAM, and LeGO-LOAM methods. Additionally, we generate 3D point cloud maps for the corresponding sequences and high-definition point cloud maps of the streets in sequence 00. The experimental results demonstrate significant improvements in trajectory accuracy and robustness, enabling the construction of clear, dense 3D maps.

Real-Time Semantic Segmentation of 3D LiDAR Point Clouds for Aircraft Engine Detection in Autonomous Jetbridge Operations

This paper presents a study on aircraft engine identification using real-time 3D LiDAR point cloud segmentation technology, a key element for the development of automated docking systems in airport boarding facilities, known as jetbridges. To achieve this, 3D LiDAR sensors utilizing a spinning method were employed to gather surrounding environmental 3D point cloud data. The raw 3D environmental data were then filtered using the 3D RANSAC technique, excluding ground data and irrelevant apron areas. Segmentation was subsequently conducted based on the filtered data, focusing on aircraft sections. For the segmented aircraft engine parts, the centroid of the grouped data was computed to determine the 3D position of the aircraft engine. Additionally, PointNet was applied to identify aircraft engines from the segmented data. Dynamic tests were conducted in various weather and environmental conditions, evaluating the detection performance across different jetbridge movement speeds and object-to-object distances. The study achieved a mean intersection over union (mIoU) of 81.25% in detecting aircraft engines, despite experiencing challenging conditions such as low-frequency vibrations and changes in the field of view during jetbridge maneuvers. This research provides a strong foundation for enhancing the robustness of jetbridge autonomous docking systems by reducing the sensor noise and distortion in real-time applications. Our future research will focus on optimizing sensor configurations, especially in environments where sea fog, snow, and rain are frequent, by combining RGB image data with 3D LiDAR information. The ultimate goal is to further improve the system’s reliability and efficiency, not only in jetbridge operations but also in broader autonomous vehicle and robotics applications, where precision and reliability are critical. The methodologies and findings of this study hold the potential to significantly advance the development of autonomous technologies across various industrial sectors.

Effect of Anions on Deformation of Gallium-Based Liquid Metal in Solution.

In this study, deformation behaviors of gallium-based liquid metals in acidified cupric sulfate or cupric chloride solutions with varying concentrations of chloride anion or sulfate anion were investigated to explore their potential applications in soft machines and electronics. Gallium-based liquid metals are known for their unique deformability, making them promising materials for various fields. Previous research has shown that deformation of the liquid metal can be achieved in the presence of acidified cupric or ferric salts. However, the specific influence of different anions on the deformation process remains unclear. Our findings indicate that the deformation rate of the liquid metal increases with higher concentrations of chloride ions and decreases with higher concentrations of sulfate ions in the solution. UV-vis absorbance spectra of the solutions were analyzed to identify the formation of hydrated cupric cations. It was observed that increasing the concentration of Cl- ions promotes the formation of cupric-chloro complexes, thereby reducing the concentration of hydrated cupric ions in the solution. Furthermore, the addition of sulfate ions to the solution enhances the ionic strength of the medium, leading to the dissociation of cupric-chloro complexes. Additionally, sulfate ions can form insoluble layers with gallium ions, which impede the deformation of the liquid metal. The deformation rate of the liquid metal was found to be inversely correlated with the concentration of cupric ions in the solution. These results provide valuable insights into the deformable behavior of gallium-based liquid metals and their potential applications in liquid metal-based soft robots. This study highlights the importance of understanding the role of different anions in the deformation process of liquid metals, shedding light on the design and optimization of soft machines and electronics utilizing these materials.

Stretchable printed circuit boards using a silicone substrate of variable stiffness and conventional PCB fabrication methods

Abstract Stretchable printed circuit boards (S-PCBs) offer unique advantages over rigid PCBs such as enabling conformability to changing environments and ergonomic designs with increased lifetime under dynamic loads. This study introduces an innovative fabrication method and a cost-effective solution for rapid prototyping S-PCBs using commercially available materials. By utilizing silicone substrates with different levels of stiffness and structured copper sheets for electrical connections, the S-PCBs feature ‘stiff islands’ embedded in a flexible base material. This fabrication method helps alleviate mechanical strain on strain-sensitive components while allowing local deformation of the S-PCB. The proposed fabrication method does therefore enable to integrate surface mount device components into S-PCBs and facilitates complex circuit designs while maintaining stretchability and fatigue resistance. Through material characterization, video strain analysis, as well as quasi-static and cyclic loading tests, this article demonstrates the efficacy of our approach. Based on the experimental results, we provide insights into failure modes and suggest design principles to further enhance the durability of S-PCBs fabricated with our method. We then conclude by presenting a soft wearable S-PCB demonstrator. The S-PCBs fabricated with this method withstood mechanical strains up to 100% and cyclic loads with 30% strain up to 625 cycles. The results are very promising for applications in soft robotics, wearable devices, and soft sensors and actuators. Overall, our study offers a comprehensive toolkit for fast S-PCB prototyping, paving the way for advancements in stretchable electronics with a high degree of complexity and stretchability.

Vision-based target localization and online error correction for high-precision robotic drilling

Abstract This article presents a detailed examination of circular target localization techniques for measuring robot pose and performing online pose correction. The investigated target localization methods include centroiding, ellipse fitting with point data and gradient information, and ellipse fitting methods with augmented and corrected input data. The performance of each method is evaluated in terms of accuracy and precision of measurements through experimental comparison with a laser tracker. This study provides technical and practical insights for selecting an appropriate target localization method in robotic applications. It also introduces a vision-based solution for robot relative error correction, comprising the calibration procedure and a closed-loop control with a proportional–integral-derivative controller for pose correction. Results show enhanced accuracy in robot positioning relative to workpiece, highlighting the effectiveness of the proposed solution in robotic drilling applications.