Robot Research Articles

A tightly-coupled PPP/visual positioning method for fast initialization and effective continuity

Precise Point Positioning (PPP) is one of the most widely used positioning methods, providing standalone positioning solutions with high accuracy. However, the algorithm usually requires tens of minutes to converge which makes the application restricted in many scenarios. The rapid developments of unmanned systems urge real-time positioning solutions with accuracy and continuity in complicated environments, where the GNSS observations get interrupted frequently. In view of this, we propose an integration positioning method tightly coupling PPP with visual localization. With the coordinates of the visual landmarks in the navigation frame measured priorly, the proposed method combines the observation equations of PPP and visual localizations providing accurate estimation of the position. Both simulation and real experiments are conducted to verify the effectiveness of the proposed method. With around five landmarks in sight simultaneously, the proposed method achieves its utmost performance to converge in seconds with a centimeter-level positioning accuracy, relatively better than the PPP-only method. The simulation based on real experiment data indicates that the proposed method keeps its output continuous and smooth when re-initialization happens once the observations of GNSS and visual get interrupted. The method offers positioning solutions with centimeter-level precision converging in 3–5 s, which indicates a promising application prospect in challenging environments in the future.

A novel method of suppressing machining vibration in robotic milling using magneto-rheological foam damper

Owing to their remarkable flexibility and favorable cost-effectiveness, industrial robots have found extensive applications to cutting of materials across sophisticated manufacturing fields. However, the structurally low rigidity of these robots renders the tool tip prone to substantial oscillations during machining processes, significantly impacting product fabrication quality. The objective of this study is to present a novel methodology employing magnetorheological dampers for mitigating vibrations during robotic milling operations. Specifically, a new type of ring nested Magneto-Rheological Foam Damper (MRFD) working in the squeeze mode is developed. Firstly, the MRFD's structure is designed considering the vibrational characteristics of robotic milling. Subsequently, a damping force model of the MRFD is derived. The feasibility of the MRFD’s structural design is validated by the finite element analyses, which is instrumental in comprehending the influence of structural parameters on the electromagnetic characteristics of the MRFD. Next, a prototype of the MRFD is fabricated selecting appropriate parameters. Finally, a series of excitation and milling experiments are conducted on a KUKA KR500 robot. The outcomes demonstrate a substantial reduction (37%-69%) in radial vibration amplitude at the tool tip during robotic milling, highlighting the effectiveness of the developed MRFD. This research endeavor has introduced a pioneering avenue and framework for vibration control in robotic milling, offering a novel paradigm for enhancing the precision of robotic machining.

무인카페 특성이 긍정적 감정과 지속이용의도에 미치는 영향

The aim of this study was to explore the relationship between positive emotions and the intention to continue using unmanned cafes, focusing on the characteristics experienced by consumers. To this end, a survey was conducted among individuals who have patronized unmanned cafes. A total of 203 responses were statistically analyzed using the SPSS 18.0 software. The findings revealed that: First, the ease of technology use, spatial arrangement and functionality, and payment convenience—all key features of unmanned cafes—significantly positively influence positive emotions. Second, positive emotions were found to significantly enhance the intention to continue usage. Third, the characteristics of unmanned cafes directly contributed to a positive continuous use intention. These results suggest that strategies to facilitate the easy use of unmanned system technology, improve spatial comfort and functionality, and enhance payment convenience are essential. Such strategies can elicit positive emotions, thereby fostering a continued desire to use unmanned cafes. Emphasizing the importance of convenience for consumers in using unmanned cafes is particularly crucial.

이미지 메타 정보 기반 한국인 표정 감정 인식

Due to the recent pandemic and the development of ICT technology, the use of non-face-to-face and unmanned systems is expanding, and it is very important to understand emotions in communication in non-face-to-face situations. As emotion recognition methods for various facial expressions are required to understand emotions, artificial intelligence-based research is being conducted to improve facial expression emotion recognition in image data. However, existing research on facial expression emotion recognition requires high computing power and a lot of learning time because it utilizes a large amount of data to improve accuracy. To improve these limitations, this paper proposes a method of recognizing facial expressions using age and gender, which are image meta information, as a method of recognizing facial expressions with even a small amount of data. For facial expression emotion recognition, a face was detected using the Yolo Face model from the original image data, and age and gender were classified through the VGG model based on image meta information, and then seven emotions were recognized using the EfficientNet model. The accuracy of the proposed data classification learning model was higher as a result of comparing the meta-information-based data classification model with the model trained with all data.

A Path Planning Method for Collaborative Coverage Monitoring in Urban Scenarios

In recent years, unmanned aerial vehicles (UAVs) have become a popular and cost-effective technology in urban scenarios, encompassing applications such as material transportation, aerial photography, remote sensing, and disaster relief. However, the execution of prolonged tasks poses a heightened challenge owing to the constrained endurance of UAVs. This paper proposes a model to accurately represent urban scenarios and an unmanned system. Restricted zones, no-fly zones, and building obstructions to the detection range are introduced to make sure the model is realistic enough. We also introduced an unmanned ground vehicle (UGV) into the model to solve the endurance of the UAVs in this long-time task scenario. The UGV and UAVs constituted a heterogeneous unmanned system to collaboratively solve the path-planning problem in the model. Building upon this model, this paper designs a Three-stage Alternating Optimization Algorithm (TAOA), involving two crucial steps of prediction and rolling optimization. A three-stage scheme is introduced to rolling optimization to effectively address the complex optimization process for the unmanned system. Finally, the TAOA was experimentally validated in both synthetic scenarios and scenarios modeled based on a real-world location to demonstrate their reliability. The experiments conducted in the synthetic scenarios aimed to assess the algorithm under hypothetical conditions, while the experiments in the scenarios based on real-world locations provided a practical evaluation of the proposed methods in more complex and authentic environments. The consistent performance observed across these experiments underscores the robustness and effectiveness of the proposed approaches, supporting their potential applicability in various real-world scenarios.

A novel associative memory model based on semi-tensor product (STP).

A good intelligent learning model is the key to complete recognition of scene information and accurate recognition of specific targets in intelligent unmanned system. This study proposes a new associative memory model based on the semi-tensor product (STP) of matrices, to address the problems of information storage capacity and association. First, some preliminaries are introduced to facilitate modeling, and the problem of information storage capacity in the application of discrete Hopfield neural network (DHNN) to associative memory is pointed out. Second, learning modes are equivalently converted into their algebraic forms by using STP. A memory matrix is constructed to accurately remember these learning modes. Furthermore, an algorithm for updating the memory matrix is developed to improve the association ability of the model. And another algorithm is provided to show how our model learns and associates. Finally, some examples are given to demonstrate the effectiveness and advantages of our results. Compared with mainstream DHNNs, our model can remember learning modes more accurately with fewer nodes.

Unlocking Business Potential: Artificial Intelligence and Machine Learning Capabilities in SAP S/4HANA

This article explores the transformative role of artificial intelligence (AI) and machine learning (ML) capabilities within SAP S/4HANA, a leading digital platform for enterprise resource planning (ERP). This article elucidates how AI and ML technologies embedded in SAP S/4HANA empower businesses to drive innovation, optimize operations, and gain actionable insights. From predictive analytics and intelligent automation to advanced decision support systems, SAP S/4HANA's AI and ML capabilities are revolutionizing the way organizations operate in today's fast-paced business landscape. SAP S/4HANA, a leading enterprise resource planning (ERP) platform, stands at the forefront of this digital transformation, offering a comprehensive suite of AI and ML capabilities designed to empower businesses to optimize operations, enhance decision-making, and unlock new growth opportunities. This article provides a succinct overview of the transformative role of AI and ML in SAP S/4HANA, highlighting key functionalities and their potential impact on business operations. SAP S/4HANA's AI and ML capabilities encompass a range of functionalities, including predictive analytics, intelligent automation, and decision support systems. Intelligent automation features, such as robotic process automation (RPA) and machine learning-based algorithms, automate manual tasks, reduce errors, and accelerate decision- making processes, thereby enhancing operational efficiency and agility. Moreover, SAP S/4HANA's decision support systems leverage real-time data insights to provide actionable recommendations to users across the organization, enabling organizations to make informed decisions and drive strategic initiatives. Through real- world examples and case studies, this article illustrates how organizations across industries are leveraging SAP S/4HANA's AI and ML capabilities to drive business transformation, streamline processes, and achieve measurable outcomes. This article aims to provide a comprehensive exploration of the AI and ML capabilities within SAP S/4HANA, examining their potential impact on business operations and outlining best practices for implementation and utilization. Through real-world examples, case studies, and expert insights, readers will gain a deeper understanding of how SAP S/4HANA's AI and ML functionalities can unlock new opportunities, drive innovation, and propel business growth.

Development of the multi purpose simulation complex for training of unmanned systems operators

Development of the multi purpose simulation complex for training of unmanned systems operators

Multimodal 1D CNN for delamination prediction in CFRP drilling process with industrial robots

There is a growing demand for carbon fiber-reinforced plastics (CFRPs) in the aerospace and automotive industries. Consequently, the assembly and repair of CFRP components has garnered considerable attention. However, at industrial sites, there are potential difficulties in the CFRP drilling process. These challenges arise from the anisotropic properties of CFRP and the limitations of using an optical microscope to assess the quality of millions of drilled holes. Therefore, this study introduced an advanced indirect prediction method for the CFRP hole quality based on multisensor data. During the drilling process, data including force, torque, acceleration, voltage, current, sound, and images of the hole exits were acquired via a robotic machining system. The delamination factors, Fd and Fa, which quantify the quality of the hole, can be calculated from the hole images. Preprocessing was employed to segment the sensor data into discrete drilling trials and extract spectral features from the data. This paper proposed a multimodal one-dimensional convolutional neural network (1D CNN) that predicts delamination factors from time series multi-sensor data. A case study, using a test set of 100 trials, validated the proposed model. The performance of the proposed model was evaluated by the mean squared error (MSE) and inference time, yielding 8.42 ± 0.167 × 10−2 and 3.48 ± 0.192 s for Fd, and 6.1 ± 0.729 × 10−2 and 3.13 ± 0.098 s for Fa, respectively, across the entire test set with 100 trials. This result exceeds those of previous studies in terms of both the MSE value and inference time for multimodality, emphasizing the predictive accuracy and real-time operational capabilities of the proposed model in industrial settings. Furthermore, this approach provides practicality and flexibility, facilitating the easy integration or removal of sensors through data-driven preprocessing and a multimodal learning scheme.

A study of the accuracy of industrial robots and laser-tracking for timber machining across the workspace

ABSTRACT The aim of the present study was to investigate the accuracy of an industrial robot when milling glued-laminated timber along a vertical work plane while maximising the advantageous size of the workspace. The authors discovered a research gap in the machining accuracy within the workspace of an industrial robot. Hence, the examination comprises 50 distinct positions allocated in a grid, each with 3 machined specimens resulting in a total of 150 samples. The workpiece positions were referenced using laser-tracking technology to adjust the robot machining code to the actual workpiece position, while simultaneously assessing the machining accuracy using laser scans of the samples. As a result, accuracy maps are presented indicating the nominal-actual deviation including referencing errors and workpiece dimensional deviations (absolute accuracy) and the robot-only nominal-actual deviation (relative accuracy), subsequently proving that both comply with the EN 14080 standard. Furthermore, a calculation of the centre of accuracy defines the point of highest relative accuracy. The objective was achieved and advocated for a more pronounced utilisation of the workspace when machining timber with industrial robots. Applying these insights to the machining of large complex parts, multi-workpiece stacks and mobile robot platforms can enhance the possibilities and efficiency within timber construction.

Indoor Environment Reconstruction for Unmanned System Using Multiple Low-Cost Sensors

Considering that laser scan stations are expensive and heavy for the indoor environment reconstruction of unmanned systems, a low-cost and light reconstruction system is proposed in this research. The system consists of a cross-structured light visual (SLV) sensor and an inertial navigation system (INS). The cross-SLV sensor is used to scan the surroundings and to estimate the angle change between two adjacent measurements. To improve the robustness and accuracy of the angle measurement, a Kalman Filter (KF) with simple construction is designed to fuse the inertial information from the INS. The factors which influence ranging accuracy are analyzed and ranging experiments show that the SLV sensor has an accuracy of higher than 2% when the distance is less than 4 m. Then the reconstruction results of a kitchen and corridor show that the error of most points is less than 50 mm for either kitchen (94%) or corridor (85%), and the mean errors and standard deviations of kitchen and corridor are less than 20 mm and 30 mm, respectively.

Autonomous Landing of Quadrotor Unmanned Aerial Vehicles Based on Multi-Level Marker and Linear Active Disturbance Reject Control.

Landing on unmanned surface vehicles (USV) autonomously is a critical task for unmanned aerial vehicles (UAV) due to complex environments. To solve this problem, an autonomous landing method is proposed based on a multi-level marker and linear active disturbance rejection control (LADRC) in this study. A specially designed landing board is placed on the USV, and ArUco codes with different scales are employed. Then, the landing marker is captured and processed by a camera mounted below the UAV body. Using the efficient perspective-n-point method, the position and attitude of the UAV are estimated and further fused by the Kalman filter, which improves the estimation accuracy and stability. On this basis, LADRC is used for UAV landing control, in which an extended state observer with adjustable bandwidth is employed to evaluate disturbance and proportional-derivative control is adopted to eliminate control error. The results of simulations and experiments demonstrate the feasibility and effectiveness of the proposed method, which provides an effective solution for the autonomous recovery of unmanned systems.

Sustainable Urban Drone Operations: FF2020 view

Experts worldwide agree that development of operations of Unmanned Aircraft Systems (UAS, commonly known as drones) above populated areas, to remain socially acceptable, must satisfy a set of crucial criteria: safety, security, environmental sustainability (including noise and pollution reduction) and compliance with legal requirements (encompassing liability, privacy and alignment with urban land use regulations). However, for both commercial organisations and entities carrying flights in the public interest, these operations need to also be economically sustainable. This article considers two illustrative scenarios: (1) the urgent transport of medical equipment (e.g., defibrillators) on an ad-hoc basis, precisely when and where required, rather than on a routine schedule; (2) security or plant safety applications, where a drone remains on standby, recharging its batteries in a designated ‘nest,’ ready to take-off for capturing imagery or sensory data when triggered by security personnel or by automatic alerts (e.g., a camera detecting an individual penetrating a perimeter). Deploying one remote pilot for each ‘sleeping’ drone 24/7 would lead to enormous service costs, difficult to be sustained by any organisation. The drone hence needs to be completely autonomous, meaning that a remote pilot would no longer be necessary. The concept, often referred to as ‘Drones in the Box,’ is technically feasible and currently exists. Organisation of the operations, however, goes beyond technical feasibility. According to the Automation Concept by the Joint Authorities for Rulemaking on Unmanned Systems (JARUS), this falls under level 5 of automation. In this highest level, there is neither involvement of a remote pilot in aircraft flight functions, both on the ground and in the air, nor any human awareness of dynamic operational parameters. In essence, to ensure economic sustainability, the 24/7 operations must entirely eliminate the need for remote pilots. Nonetheless, a UAS operator would still exist as the legal entity responsible for organising and overseeing operations, securing necessary approvals and being accountable for the process. Therefore, a professional job profile would still be necessary, to possibly trigger the flight, receive the collected information and act upon or activate the Emergency Response Plan (ERP) when required. This professional would neither need to be trained nor licenced as Remote Pilot but the position should be 24/7. In scenarios such as the two mentioned examples, security personnel may already be on duty 24/7 to safeguard certain facilities (e.g., hospitals) or provide emergency medical services (e.g., 118 in Italy). These operations could thus become economically viable if these personnel were trained by the operator for this on-demand duty. The Flying Forward 2020 (FF2020) project has coined this role as the ‘Fleet Manager’ and intends to standardise it through ISO (International Organisation for Standardisation), for global harmonisation.

Treatment Outcomes of Stereotactic Ablative Body Radiotherapy on Extra-cranial Oligometastatic and Oligoprogressive Breast Cancer: Mature Results from a Single Institution Experience

AimsEvidence shows stereotactic ablative body radiotherapy (SABR) is used as a non-invasive ablative therapy in the treatment of multisite oligometastatic (OM) and oligoprogressive (OP) diseases originating from metastatic breast cancer. This study aims to report the treatment outcomes and to investigate what factors that are prognostic in terms of local control, progression-free survival (PFS) and overall survival (OS) in patients receiving SABR for extracranial OM and OP diseases originating from metastatic breast cancer. Materials and methodsA retrospective review on treatment records of patients with OM and OP from metastatic breast cancer who underwent SABR at a single was carried out. SABR was performed with daily image-guided radiotherapy (IGRT) using a dedicated robotic SABR machine. Local control, PFS and OS were calculated using Kaplan-Meier statistics and the post-treatment toxicity data was scored following the CTCAE v4.0 protocol. Univariate and multivariate Cox regression tests were used in the subgroup analysis of prognostic factors on PFS and OS including patients’ age, types of follow-up imaging (staging CT only vs whole-body MR/PET), metastases status (OM vs OP), primary breast cancer tumour grade, hormone receptors (ER/PR/HER2) status, change of systemic treatments at SABR, number of metastases, SABR treatment sites and doses. Results56 metastatic breast cancer patients (38 patients with OM and 18 patients with OP) were involved in this retrospective review. The median follow-up was 35.6 months (range 4.0–132.9 months). The estimated local control at 1 , 2 and 5 years were 90.9%, 88.7% and 88.7%, respectively. The estimated median PFS was 19.2 months (95%CI 10.3–28.1 months); the PFS at 1, 2 and 5 years were 63.3%, 44.4% and 33.2%. The estimated OS at 1, 2 and 5 years were 98.0%, 91.9% and 74.3%, respectively with the estimated median OS of 105.1 months (95%CI 51.5–158.7 months). The vast majority of patients tolerated the treatment well with the commonest acute side effects as grade 1 fatigue. There were no statistically significant factors found in OS regression analysis. The types of follow-up imaging, metastases status, oestrogen receptor status, and number of metastases for SABR were statistically significant factors (p < 0.05) in the multivariate Cox regression analysis on PFS. ConclusionThere are limited studies published on the efficacy and post-treatment toxicities of metastatic breast cancer OM and OP SABR with adequate length of follow-up. This study confirmed that SABR was a safe, non-invasive treatment option for patients with extracranial OM and OP diseases originated from primary breast cancer in terms of the acceptable post-treatment toxicities.

Low-frequency chatter suppression in robotic milling using Magnetorheological Joint Damper (MRJD)

Low-frequency structural vibrations caused by poor rigidity are one of the main obstacles limiting the machining efficiency of robotic milling. Existing vibration suppression strategies primarily focus on passive vibration absorption at the robotic end and feedback control at the joint motor. Although these strategies have a certain vibration suppression effect, the limitations of robotic flexibility and the extremely limited applicable speed range remain to be overcome. In this study, a Magnetorheological Joint Damper (MRJD) is developed. The joint-mounted feature ensures machining flexibility of the robot, and the millisecond response time of the Magnetorheological Fluid (MRF) ensures a large effective spindle speed range. More importantly, the evolution law of the damping performance of MRJD was revealed based on a low-frequency chatter mechanism, which guarantees the application of MRJD in robotic milling machining. To analyze the influence of the robotic joint angle on the suppression effect of the MRJD, the joint braking coefficient and end braking coefficient were proposed. Parallel coordinate plots were used to visualize the joint range with the optimal vibration suppression effect. Finally, a combination of different postures and cutting parameters was used to verify the vibration suppression effect and feasibility of the joint angle optimization. The experimental results show that the MRJD, which directly improves the joint vibration resistance, can effectively suppress the low-frequency vibration of robotic milling under a variety of cutting conditions.

Coordinated Navigation Control of Cross-Domain Unmanned Systems via Guiding Vector Fields

Coordinated Navigation Control of Cross-Domain Unmanned Systems via Guiding Vector Fields

How Challenging is a Challenge? CEMS: a Challenge Evaluation Module for SLAM Visual Perception

Despite promising SLAM research in both vision and robotics communities, which fundamentally sustains the autonomy of intelligent unmanned systems, visual challenges still threaten its robust operation severely. Existing SLAM methods usually focus on specific challenges and solve the problem with sophisticated enhancement or multi-modal fusion. However, they are basically limited to particular scenes with a non-quantitative understanding and awareness of challenges, resulting in a significant performance decline with poor generalization and(or) redundant computation with inflexible mechanisms. To push the frontier of visual SLAM, we propose a fully computational reliable evaluation module called CEMS (Challenge Evaluation Module for SLAM) for general visual perception based on a clear definition and systematic analysis. It decomposes various challenges into several common aspects and evaluates degradation with corresponding indicators. Extensive experiments demonstrate our feasibility and outperformance. The proposed module has a high consistency of 88.298% compared with annotation ground truth, and a strong correlation of 0.879 compared with SLAM tracking performance. Moreover, we show the prototype SLAM based on CEMS with better performance and the first comprehensive CET (Challenge Evaluation Table) for common SLAM datasets (EuRoC, KITTI, etc.) with objective and fair evaluations of various challenges. We make it available online to benefit the community on our website.

Research on underwater unmanned platform route planning based on marine environment constraints

Since the development of unmanned systems, autonomous underwater unmanned platforms have become an important facility for countries to explore the ocean field which play an important role in both military and civilian. In this paper, the route planning of underwater unmanned platform is carried out from three constraints: the risk that affects the operational effectiveness of the unmanned underwater platform, the navigation resistance and the navigation path length. The simulation results show that the model can deal with three constraints reasonably and plan a suitable route.

Multi-Criteria Evaluation of UAV Control Efficiency in Hybrid Communication Networks

Currently, there is an active growth in the use of unmanned systems in various spheres of activity. The qualitative fulfillment by unmanned systems of their target tasks depends on the efficiency of information exchange channels for their control, which consists of several criteria, which makes the problem of its evaluation a multi-criteria one. This article presents the corresponding evaluation methodology, which is based on the use of the probability of achieving a set of functioning goals as a generalized efficiency indicator. To determine the probability, the widely used Rosenblatt-Parzen nuclear estimation method is used. The main stages of the methodology are described and recommendations for its use in the framework of ensuring qualitative fulfillment by unmanned systems of their target tasks are offered.

A novel vision-based multi-functional sensor for normality and position measurements in precise robotic manufacturing

Cobots play an essential role in the fourth industrial revolution and the automation of complex manufacturing processes. However, cobots still face challenges in achieving high precision, which obstructs their usage in precise applications such as the aerospace industry. Nonetheless, advances in perception systems unlock new cobot manufacturing capabilities. This paper presents a novel multi-functional sensor that combines visual and tactile feedback using a single optical sensor, featuring a moving gate mechanism. This work also marks the first integration of Vision-Based Tactile Sensing (VBTS) into a robotic machining end-effector. The sensor provides vision-based tactile perception capabilities for precise normality control and exteroceptive perception for robot localization and positioning. Its performance is experimentally demonstrated in a precise robotic deburring application, where the sensor achieves the high-precision requirements of the aerospace industry with a mean normality error of 0.13° and a mean positioning error of 0.2 mm. These results open a new paradigm for using vision-based sensing for precise robotic manufacturing, which surpasses conventional approaches in terms of precision, weight, size, and cost-effectiveness.