Advanced Robotic Systems Research Articles

Urban traffic flows forecasting by recurrent neural networks with spiral structures of layers

The problem of neural network forecasting of processes with changing laws of their behavior and imperfection of time-series samples is considered on the example of analysis of urban traffic flows. The goal is to improve the accuracy of such forecasting. To achieve this goal, we analyze the applicability of self-learning recurrent neural networks with controlled elements and the spiral structure of layers. Based on the development and application of these neural networks, the new methods and the system implementing them are proposed. These methods, in contrast to known solutions, allow continuous training of neural networks and forecasting of processes. There is no need to interrupt training to perform forecasting. For forecasting, it is possible to continuously take into account the properties of the observed processes. In addition, improved controlling of associative recall of information from the memory of recurrent neural networks is provided to improve the accuracy of forecasting. The results of traffic flow forecasting are presented. The results are compared with estimates obtained using other methods. It is shown that the proposed methods have advantages in accuracy compared to the known solutions. The developed methods are recommended for use in advanced robotic and other intelligent systems.

Advanced robotic surgical systems in ophthalmology.

In this paper, an overview of advanced robotic surgical systems in ophthalmology is provided. The systems are introduced as representative examples of the degree of human vs. robotic control during surgical procedures. The details are presented on each system and the latest advancements of each are described. Future potential applications for surgical robotics in ophthalmology are discussed in detail, with representative examples provided alongside recent progress.

Robust model reconstruction for intelligent health monitoring of tunnel structures

Advanced robotic systems will encounter a rapid breakthrough opportunity and become increasingly important, especially with the aid of the accelerated development of artificial intelligence technology. Nowadays, advanced robotic systems are widely used in various fields. However, the development of artificial intelligence-based robot systems for structural health monitoring of tunnels needs to be further investigated, especially for data modeling and intelligent processing for noises. This research focuses on integrated B-spline approximation with a nonparametric rank method and reveals its advantages of high efficiency and noise resistance for the automatic health monitoring of tunnel structures. Furthermore, the root-mean-square error and time consumption of the rank-based and Huber’s M-estimator methods are compared based on various profiles. The results imply that the rank-based method to model point cloud data has a comparative advantage in the monitoring of tunnel, as well as the large-area structures, which requires high degrees of efficiency and robustness.

Towards a Low-Cost Solution to Learn Robot Manipulator Control

Learn a robot manipulator in university requires a physical robot so students can learn to program it straight away. However, it is expensive and not affordable by most universities in Indonesia. We turn to a ROS-based solution for an open source, free and advanced robotic software system. Using ROS and Gazebo simulator, we develop a low-cost solution where students can learn an advanced robot manipulator such as Baxter. We divide our labwork into five sections: controlling the arm w.r.t. joints position, controlling the arm based on its inverse kinematics, object detection by a camera attached in robot’s wrist, executing a simple plan: pick and place task, and enabling a robot to perform a tool-use task. By gradually increasing the complexities of the labwork material we expect students get a better understanding in controlling a robot manipulator. We provide an affordable solution for students to learn robot manipulator control.

Multi-field-coupling energy conversion for flexible manipulation of graphene-based soft robots

Soft robots enabling controllable movement in a predicable manner have attracted enormous research interests. However, current researches on soft robots are mainly limited to single actuation mode, and thus complex and multidimensional motility is significantly limited. Here, we propose and demonstrate for the first time a multi-field-coupling energy conversion strategy for flexible manipulation of soft robots, by which 3D-positioning, rotating, levitating, capturing and releasing of a small object by a smart claw are synergistically realized via magnetic, ultrasonic, humidity and light fields. The essence of the strategy is coupling design of the robot compositional materials that can convert energy from different fields into efficient mechanical works. As a typical example, we developed a magnetic-field-assisted gradient assembly method for preparing asymmetric Fe3O4 nanoparticles (NPs) and graphene oxide (GO) composite film. The asymmetric distribution of Fe3O4 NPs in GO leads to an reasonable mechanical stiffness and alters the water adsorption capability of the two sides, which not only imparts multi-responsiveness but also suitably addresses the problem of interlayer detachment in the case of bimorph actuators. The robust soft robots demonstrate good durability, revealing great potential for developing advanced robotic systems that permit direct conversion of multi-field energies to mechanical works.

Improvement of Heavy Load Robot Positioning Accuracy by Combining a Model-Based Identification for Geometric Parameters and an Optimized Neural Network for the Compensation of Nongeometric Errors

The positioning accuracy of a robot is of great significance in advanced robotic manufacturing systems. This paper proposes a novel calibration method for improving robot positioning accuracy. First of all, geometric parameters are identified on the basis of the product of exponentials (POE) formula. The errors of the reduction ratio and the coupling ratio are identified at the same time. Then, joint stiffness identification is carried out by adding a load to the end-effector. Finally, residual errors caused by nongeometric parameters are compensated by a multilayer perceptron neural network (MLPNN) based on beetle swarm optimization algorithm. The calibration is implemented on a SIASUN SR210D robot manipulator. Results show that the proposed method possesses better performance in terms of faster convergence and higher precision.

FPGA-Based Design for Real-Time Crack Detection Based on Particle Filter

Due to the related hazards, costly down-time, and detection inconsistencies associated with manual visual inspection for cracks in structures, there has been an emergence of real-time systems capable of conducting inspections. Advanced robotic systems have been used for scanning structures located in remote areas or that pose significant hazards to personnel. However, due to their inherent resource limitations, the current solution is to transfer all applicable sensor data to a ground station where detection will occur at a later time, thereby preventing real-time decision based on the results. To allow on-board decision making, in this article, a crack detection particle filter is optimized for parallel computation and implemented onto an Field-programmable gate array (FPGA). This article shows that an FPGA holds distinct tradeoffs between computational speed, energy consumption, and physical footprint compared to that of traditional CPU designs, allowing for it to be an ideal system for autonomous applications.

Mobile robotic fabrication beyond factory conditions: case study Mesh Mould wall of the DFAB HOUSE

The development of novel robotic fabrication technologies in architecture concentrates largely on integrating stationary industrial-type robots into off-site prefabrication processes. By contrast, few enabling robotic technologies exist today that allow robotic fabrication processes to be mobile and implemented directly on building sites. While mobile in situ fabrication offers a large range of architectural potentials, its realization requires to address fundamental challenges. First, the production of large-scale and potentially monolithic structures on-site requires an advanced robotic fabrication system that can fulfill the material, structural- and architectural-related demands associated with it. Second, the poorly structured nature of building sites requires mobile robotic systems to be equipped with advanced sensing and control solutions to contend with uncertain conditions found on-site. The research discussed in this paper addresses both of these subjects. It applies a novel construction system for non-standard reinforced concrete structures, termed Mesh Mould, to explore the fabrication of large-scale and monolithic building structures using a mobile robot on site. It further investigates sensor-integrated adaptive fabrication strategies to achieve the accurate fabrication of such a large-scale structure, and this is done despite prevalent uncertainties related to the building site environment, the mobile robotic system, and the material behavior during fabrication. The results of this research were realized in a slender, doubly curved, reinforced concrete wall at the DFAB HOUSE at NEST. This research demonstrator provides the unique opportunity to present robotic in situ fabrication not merely as a future possibility, but as a reality applied to a tangible construction project.

Feasibility of Transcervical Robotic-Assisted Esophagectomy (TC-RAMIE) in a Cadaver Study—A Future Outlook for an Extrapleural Approach

In recent years, the evolution of advanced robotic medical systems has increased rapidly. These technical developments have led to advanced robotic systems, such as the da Vinci Xi, which allows superior controlled complex procedures and innovative surgical strategies. In esophageal surgery, the robotic-assisted minimally invasive esophagectomy (RAMIE) procedure is being developed and carried out with increasing frequency at centers worldwide. Recently, a new single port robotic system was introduced (da Vinci Single Port (SP)), which may allow for the exploration of new routes, such as transcervical robotic assisted minimally invasive esophagectomy (TC-RAMIE). This approach avoids opening the pleura by entering the mediastinum through the jugular window. In this report, we describe the technical steps of the TC-RAMIE using the new da Vinci SP system and compare it to the da Vinci Xi system.

Robotic surgery: finding value in 2019 and beyond

Despite its significant associated costs, demand for robotic surgery continues to grow exponentially, with surgeons and patients alike increasingly gravitating towards health systems that provide access to robotic surgery. As it continues to develop its competitive advantage in robotic surgery, it is imperative for the modern health care systems to remain well-informed on the current state of robotic surgery and its role in improving health care quality and providing value to the system. The demand for robotic surgery is at an all-time high and continues to grow. Heavy marketing of da Vinci , and its role in improving minimally invasive surgery have led to substantial growth at hospitals and surgical centers around the country. However, current offerings require large initial capital investments and have high recurrent costs. Moreover, research to date has not proven robotic surgery superior to conventional laparoscopy for a majority of surgeries. As healthcare executives, this raises a dilemma: “Is robotic surgery worth it?” In short, the answer is “yes!” This requires careful consideration of several factors including a shift in frame of comparison, a focus on long-term outcomes, finding ways to increase robotic volume, and considering the effect of competition. The robotic surgery industry continues to grow exponentially; it is clear that it is here to stay. Intuitive Surgical has entrenched itself in the American Healthcare system with its aggressive marketing and advanced robotic surgery system. However, in current research, robotic surgery has not proven itself superior to conventional laparoscopy; costs often exceed those of laparoscopy. The increased demand and da Vinci’s perceived flaws have sparked new competition aimed at improving value by improving quality and lowering costs. While more research is needed, this report suggests that it is indeed possible to derive significant value from robotic surgery.

A Sliding Mode Force and Position Controller Synthesis for Series Elastic Actuators

SummaryThis paper deals with the robust force and position control problems of series elastic actuators (SEAs). It is shown that an SEA’s force control problem can be described by a second-order dynamic model which suffers from only matched disturbances. However, the position control dynamics of an SEA is of fourth order and includes matched and mismatched disturbances. In other words, an SEA’s position control is more complicated than its force control, particularly when disturbances are considered. A novel robust motion controller is proposed for SEAs by using disturbance observer (DOb) and sliding mode control. When the proposed robust motion controller is implemented, an SEA can precisely track desired trajectories and safely contact with an unknown and dynamic environment. The proposed motion controller does not require precise dynamic models of environments and SEAs. Therefore, it can be applied to many different advanced robotic systems such as compliant humanoids, industrial robots and exoskeletons. The validity of the proposed motion controller is experimentally verified.

Development of a ring cavity-based fibre optic sensor for MR-compatible medical sensing applications

Advances in robotic systems and rapid developments in minimally invasive surgery (MIS) have made their use possible in the operating room due to many distinct advantages offered by MIS over conventional surgical procedures. The constant increase of medical examinations, surgeries and surgical interventions using intraoperative guidance with magnetic resonance imaging (MRI) has promoted research on new sensors to be applied in this scenario. However, due to the challenging environment under MRI system limits the applicability of materials and traditional electronic sensors. Optical fibres are small in size, chemically inert, immune to electromagnetic interference and offer the real-time in vivo multi-parameter measurement capability. Herein, we report a ring cavity-based fibre optic sensor design using MR-compatible polymer material. Optical fibres were used to excite surface resonance modes (SRM) of the ring cavity-based sensor. The paper reports initial investigations on ring cavity based MR-compatible fibre optic sensor design. Computational simulations were carried out to study the effect of structural and material parameters on the sensor design. Ring cavity was developed using polymethyl methacrylate. Developed ring cavity will be used to develop the MR-compatible fibre optic sensor for medical applications.

Advanced Robotic Angiography Systems for Image Guidance During Conventional Transarterial Chemoembolization

The aim of this study was to compare 2 advanced robotic angiography systems for real-time image guidance in terms of radiation dose and image quality (IQ) during conventional transarterial chemoembolization (C-TACE) of hepatic malignant tumors. One hundred six patients (57 women/49 men; mean age, 60 ± 11 years) who had undergone C-TACE using 2 generations of robotic angiography platforms for image guidance were included in this retrospective study. Patients were divided into 2 groups (n = 53, respectively): group 1 (first generation) and group 2 (second generation). Radiation dose for fluoroscopy and digital subtraction angiography (DSA) was compared between first-generation and second-generation angiography equipment, respectively. Among several features of the second-generation compared with the first-generation system, improvements included a refined crystalline detector system for enhanced noise reduction and advanced CARE filter software for lowering radiation dose. Radiation dose was measured using an ionization chamber. Image quality was assessed by 3 radiologists using 5-point Likert scales. Both groups were comparable in terms of number and location of lesions, as well as body weight, body mass index, and anatomical variants of feeding hepatic arteries (all P > 0.05). Dose-area product (DAP) for fluoroscopy was significantly lower in group 2 (1.4 ± 1.1 Gy·cm) compared with group 1 (2.8 ± 3.4 Gy·cm; P = 0.001). For DSA, DAP was significantly lower (P = 0.003) in group 2 (2.2 ± 1.2 Gy·cm) versus group 1 (4.7 ± 2.3 Gy·cm). Scores for DSA IQ indicated significant improvements for group 2 by 30% compared with group 1 (P = 0.004). Regarding fluoroscopy, scores for IQ were 76% higher in group 2 compared with group 1 (P = 0.001). Good to excellent interrater agreement with Fleiss kappa coefficients of κ = 0.75 for group 1 and κ = 0.74 for group 2 were achieved. Most recent generation robotic angiography equipment allows for considerable radiation dose reductions while improving IQ in fluoroscopy and DSA image guidance during C-TACE treatment.

An Oxide Schottky Junction Artificial Optoelectronic Synapse.

The rapid development of artificial intelligence techniques and future advanced robot systems sparks emergent demand on the accurate perception and understanding of the external environments via visual sensing systems that can co-locate the self-adaptive detecting, processing, and memorizing of optical signals. In this contribution, a simple indium-tin oxide/Nb-doped SrTiO3 (ITO/Nb:SrTiO3) heterojunction artificial optoelectronic synapse is proposed and demonstrated. Through the light and electric field co-modulation of the Schottky barrier profile at the ITO/Nb:SrTiO3 interface, the oxide heterojunction device can respond to the entire visible light region in a neuromorphic manner, allowing synaptic paired-pulse facilitation, short/long-term memory, and "learning-experience" behavior for optical information manipulation. More importantly, the photoplasticity of the artificial synapse has been modulated by heterosynaptic means with a sub-1 V external voltage, not only enabling an optoelectronic analog of the mechanical aperture device showing adaptive and stable optical perception capability under different illuminating conditions but also making the artificial synapse suitable for the mimicry of interest-modulated human visual memories.

The role of robotics in liver surgery

Laparoscopic surgery has become a staple in many tertiary care centres worldwide. However, due to the inherent limitations of laparoscopic surgery, adoption of minimal access approaches in surgery of the liver has been slow and patchy. Every hepatobiliary surgeon knows the limitations of laparoscopic surgery of the liver. Advanced robotic surgical systems have been introduced to fill gaps in the technical feasibility of minimal access liver resections We try to explore the use of advanced robotic systems in hepatobiliary surgery and how the novel system could help circumvent the inherent limitations of laparoscopic liver surgery. The manuscript reviews the current data concerning laparoscopic, as well as, open versus robotic approaches in liver surgery. Authors show that although robotic surgery is in its infancy, the promising role cannot be ignored. With the increasing trend towards parenchymal saving liver resection, robotics will only positively aid in the wider adoption and growth of minimally invasive techniques. Although robotics is still evolving, the need in liver surgery is evident. Further long-term research is required, however, to confirm the huge potential of robotics in liver surgery.

Digital Transformation Process and SMEs

The process of digital transformation is a period in which entities, universities, public and employees are transformed and; new business models and business practices are formed. Digital transformation is a functional use of web in design, manufacturing, marketing, selling, promotion and is data-oriented management model. Therefore, capabilities of firms are increased and their processes are improved. Digital technologies are developments regarding smartphones, cloud computing, big data, artificial intelligence, robotics systems, internet of things, 3D printing, virtualization, cyber security, sensor technologies, advanced robotics systems, automation and etc. which all is intensely used in many fields of economic and social life.SME’s consist of 99,83 % total enterprises, and 72,7 % of total employment, 50,6 % of total value added and provide 55,1 % of export, take an important role in economy. They should transform their organizational structures and business making cultures starting from manufacturing technologies to management percepts as to get a productive digital transformation process. The fact that SME’s being able to perform cost-benefit analysis of digital technologies and being aware of that technologies is significant.This paper provides a comprehensive view of the factors affecting digital transformation process and describes the digital transformation of the manufacturing sector in Turkey.The programs and softwares that SMEs can use to perform digital transformation, and can benefit from it, are explained. Empirical studies on SMEs shows that SMEs have erratic behaviors in terms of information and communications technology (ICT) investment and need external support to integrate digital transformations in the overall strategy of the firm.

Transferring Human Manipulation Knowledge to Industrial Robots Using Reinforcement Learning

Nowadays in the context of Industry 4.0, manufacturing companies are faced by increasing global competition and challenges, which requires them to become more flexible and able to adapt fast to rapid market changes. Advanced robot system is an enabler for achieving greater flexibility and adaptability, however, programming such systems also become increasingly more complex. Thus, new methods for programming robot systems and enabling self-learning capabilities to accommodate the natural variation exhibited in real-world tasks are needed. In this paper, we propose a Reinforcement Learning (RL) enabled robot system, which learns task trajectories from human workers. The presented work demonstrates that with minimal human effort, we can transfer manual manipulation tasks in certain domains to a robot system without the requirement for a complicated hardware system model or tedious and complex programming. Furthermore, the robot is able to build upon the learned concepts from the human expert and improve its performance over time. Initially, Q-learning is applied, which has shown very promising results. Preliminary experiments, from a use case in slaughterhouses, demonstrate the viability of the proposed approach. We conclude that the feasibility and applicability of RL for industrial robots and industrial processes, holds and unseen potential, especially for tasks where natural variation is exhibited in either the product or process.

Robotized Systems in Medicine: What Should They Be Like?

On March 13, 2018, a meeting of the RAS Presidium discussed the introduction of robotics into domestic medicine. It heard several coreports, the presenters of which—O.O. Yanushevich, E.V. Shlyakhto, D.Yu. Pushkar’, V.V. Krylov, I.V. Reshetov, A.V. Golanov, S.A. Sheptunov, Yu.V. Poduraev, S.A. Kraevoi, A.V. Alekhin, A.V. Koroteev, G.V. Savrasov, and V.P. Chekhonin—showed an exhaustive picture of the application and development of medical robotized systems in Russia and determined the prospects of further studies in this field. After having pointed to the advantages and drawbacks of the currently widely used da Vinci surgical systems, the presenters emphasized that copying foreign prototypes had no prospects. The general idea can be reduced to the urgent need for developing and designing original advanced digital robotic systems.

Upper limb rehabilitation using robotic exoskeleton systems: a systematic review

Exoskeleton assisted therapy has been reported as a significant reduction in impairment and gain in functional abilities of stroke patients. In this paper, we conduct a systematic review on the upper limb rehabilitation using robotic exoskeleton systems. This review is based on typical mechanical structures and control strategies for exoskeletons in clinical rehabilitation conditions. A variety of upper limb exoskeletons are classified and reviewed according to their rehabilitation joints. Special attentions are paid to the performance control strategies and mechanism designs in clinical trials and to promote the adaptability to different patients and conditions. Finally, we analyze and highlight the current research gaps and the future directions in this field. We intend to offer informative resources and reliable guidance for relevant researcher’s further studies, and exert a far-reaching influence on the development of advanced upper limb exoskeleton robotic systems.

Explicit dynamics of redundant parallel cable robots

Precise model-based control of parallel robots necessitates an analytically accurate and consolidated model of the robotic platform. Lack of accuracy in modeling causes lots of dynamic uncertainties. This fact can result in higher control gains and efforts. Furthermore, imposing modification for optimization purposes is implausible without the derivation of an exact model. Hence, in this paper an elaborative kinematical and dynamical model of redundant cable-driven parallel robots is studied. In fact, a general procedure for modeling of cable-actuated parallel robots is presented to tackle down the difficulties for model-based control. The presented dynamic modeling approach rigorously enumerates the kinematics of robot winches and pulleys. The intrinsic behavior of cables is represented with a linear spring and damper having variable mass and constant density in the workspace. To this end, sagging in cables is neglected as a computationally intractable effect with insignificant impact on robot’s dynamics. Next, model validation is carried out within an experimental study of a redundant cable-driven parallel robot, the RoboCab which is designed and manufactured in Advanced Robotics and Automated Systems (ARAS) Lab. Experimental results reveal the merits and capabilities of proposed model to capture the explicit dynamics of robot. Results also demonstrate the high rate of flexibility and applicability of model for dealing with diverse control applications.