Earticle

In autonomous driving, environmental perception and decision-making are technologies that acquire signals based on various sensors and generate information that enables obstacle avoidance, emergency stops, and path planning. Such environmental perception technologies are limited in that they depend on expensive sensors such as LIDAR and RADAR, so research on environmental perception technologies using only cameras is actively being conducted. Studies predicting traffic accidents based on dashcam footage have also been performed as part of such research. This is challenging because only limited forward-looking footage can be acquired, and the surrounding environment is dynamic and changes quickly, making analysis difficult. Existing research has focused on learning the spatialtemporal feature representation to solve these problems. This paper extracts the trajectories of the ego-vehicle and surrounding vehicles using Visual SLAM and Multiple Object Tracking algorithms and uses them as inputs to the graph convolutional neural network(GCN) to learn the spatialtemporal feature representation. In addition, the features learned through the GCN are used as inputs to a bayesian neural network(BNN) to predict the probability of accidents, and its ability to predict accidents in advance has been verified by comparison with existing studies.

The advent of the convergence era led to the convergence of industries while increasing the uncertainty of R&D. R&D uncertainty can be addressed by identifying and addressing industrial innovation patterns, which Neo-Schumpeterian suggested can be identified through the process of identifying the technical characteristics of a particular industry, which can be embodied in the concept of technology trajectory. Thus, this study considered and proposed a method to track the technology trajectory of the convergence industry through topic modeling and patent citation network analysis, and applied it to the micro medical robot industry, which is a representative convergence industry, to track the technology trajectory of active catheter. In particular, it is intended to identify the unique characteristics of the industry by identifying the industry before the promotion of the national-led medical robot industry support policy. Therefore, we tried to understand the innovation pattern of the industry by tracking the technology trajectory of the industry before 2017, the time of full-scale support for the medical robot industry in the United States. Through tracking technology trajectories, the role of each technology classification, the development path, and the knowledge flow between applicants were analyzed empirically. The results of this study are expected to contribute to resolving the remaining uncertainties in the process of establishing an active catheter R&D strategy, one of the leading convergence industries, and furthermore, it is expected to be available for tracking technology trajectories in other industries.

드라이브나 티샷을 할 때 육안을 통해 수동적으로 골프공의 궤적을 시각화하는 것은 어려운 작업이 될 수 있는데, 그 이유는 공의 크기가 작고 공이 이동하는 속도가 빠르기 때문이다. 이러한 작업의 특성으로 인해 값비싼 센서 및 구성 요소를 사용하여 제조된 복잡한 장치가 항상 요구되어 왔습니다. 본 논문에서는 골프 티샷중 골프공의 궤적을 추적하는 시스템을 제안한다. 제안하는 시스템은 기존의 컴퓨터 비전 기술과 현대적인 심층 신경망을 결합하여 모노 스테레오 비디오에 궤적을 추적한다. 골프 볼 추적에 앞서, 골프공과 플레이어의 위치를 특정 짓기 위해 YOLO(You Only Look Once) V3 딥 신경망 모델을 사용한다. 우리는 클럽과 공 사이의 초기 충격 지점을 추적 하기 위해 허프 변환을 사용한다. 또한 볼을 추적하기 위해 차영상을 이용하여 비디오의 모션 정보를 추출한다. 제 안하는 시스템의 효과를 검증하기 위해 다수의 비디오에서 테스트되었으며 각각의 결과를 보여준다.

Manually visualizing the golf ball's trajectories during a drive or a tee shot could be an unsettling task for viewers, the reason being the small size of the ball and the high speed at which it travels. This nature of the job has always required intricate systems manufactured using an expensive set of sensors and components. In this paper, we propose a system to draw the trajectory of a golf ball during a drive. The proposed system combines the classical computer vision techniques and a modern deep neural network to project the trajectories over videos taken from monocular cameras. Before starting to track the ball, the system uses YOLO(You Only Look Once) V3, deep neural network model to perform localization of the golf ball and the player. To track the initial point of impact between the club and the ball the system uses Hough transform. Finally to track the ball, the system extracts motion information of the video by using frame differencing. Unto the information received from frame differencing, the system applies filters based on a few assumptions, size and direction of movement to obtain the detections of the golf ball. The proposed system was tested on a multitude of videos to verify its effectiveness and the respective results are presented.

세계화와 디지털 전환이 가속화되는 상황에서 동아시아 경제체는 기술 공급과 수요의 불균 형, 인구 고령화, 청년 실업률 상승 및 비정규 고용 확대 등 노동시장의 도전에 직면해 있다. 본 연 구는 CiteSpace 소프트웨어를 이용하여 Web of Science와 CNKI 데이터베이스의 문헌에 대한 키워드 클러스터링과 지식 도감 분석을 실시하는 문헌계량 분석 방법에 기초한다. 연구 결과 국제 연구는 사회 경제 정책 개입, 직업 심리 건강, 직업 복지 등의 주제에 초점을 맞추고 있는 반면, 중국 국내 연구는 디지털 경제 취업 잠재력 활성화와 혁신 직업 교육 체계의 현지화 특징을 강조한다. 게다가 문헌의 수는 기하급수적으로 증가하고 있지만, 지역적 편중과 학술 공동체의 분리 문제가 있다. 이 를 바탕으로 이 글은 미래 연구 방향을 제시한다: ① 이론-실천이 결합된 취업품질 평가 프레임워크 구축; ② 디지털 경제가 노동 형태에 미치는 영향 메커니즘을 해석한다. ③ 지역적 한계를 돌파하기 위해 다국적 비교연구를 강화한다.

Amid accelerating globalization and digital transformation, East Asian economies face labor market challenges such as technological imbalances, aging populations, rising youth unemployment, and expanding informal employment. This study employs bibliometric analysis with CiteSpace to examine keyword clustering and knowledge graphs from Web of Science and CNKI databases. Results show international research focuses on socio-economic policy intervention, occupational mental health, and work well-being, while Chinese research emphasizes activating digital economy employment potential and innovating vocational education systems. Despite exponential growth in publications, regional bias and academic fragmentation persist. Future research should:①develop integrated employment quality frameworks,③ analyze the digital economy’s impact on labor forms, and② enhance cross-national comparative studies.

The precise control of mobile robot is an important issue in robotics field. In this paper, the motion model of mobile robot is established by mechanism analysis. Then, a fuzzy PID controller is designed for trajectory tracking of mobile robot. The controller consists of a PID controller and a fuzzy inference unit with two inputs and three outputs to tune the parameters of PID controller according to the error and error rate. Finally, the model of a four-wheel mobile robot, fuzzy PID and traditional PID controller are all simulated in Simulink. Simulation experiments are reached in different conditions. The result shows that the mobile robot with the fuzzy PID controller can track the desired trail by about 3 seconds in advance and the overshoot of the system will decrease by 40 percent, comparing to the mobile robot with the traditional PID controller. The advantages of fuzzy PID controller for trajectory tracking control of mobile robot are major in its rapidity, stability, anti-interference and tracking precision.

For the complex combat environment, considering the flyable performance constrains and the safety constrains, an online trajectory planning algorithm of UAVs(Unmanned Aerial Vehicles) based on Pythagorean Hodograph (PH) curve is put forward, which is easy to traced. When the unexpected obstacles are detected, based on the velocity obstacles avoidance method, the collision avoidance trajectory is planned online. The position of the interrupt point and the direction of the UAV turn are calculated. To fully use the PH trajectories performance that the curvature of the curve is continuous and precisely known, the location and crossing heading error equations were established within the Serret-Frenet coordinates. The corresponding asymptotically stable convergence backstepping trajectory tracking control law was designed based on the error formulations. The autonomous collision avoidance trajectory simulation result and its tracking control result show that the proposed trajectory generation method and the corresponding adaptive tracking control method are effective and can improve the tracking accuracy.

This paper addresses the trajectory tracking problem of underactuated autonomous underwater vehicles (AUVs) in the presence of ocean currents on the horizontal plane. The tracking control problem is reduced the problem of stabilizing the nonlinear tracking error system to two separate problems. The backstepping technique is applied to design tracking controller, and the conditions of control gains are derived such that the AUV can track a reference AUV. Simulations results show the effectiveness of the proposed trajectory tracking controller.

The multi degrees of freedom actuator is an important joint, which has attracted worldwide developing interests for its medical, industry and aerospace applications. This paper addresses the problem of trajectory tracking of three dimensions joint in the presence of model uncertainties and external disturbances. An adaptive fuzzy sliding mode controller (AFLSMC) is proposed to steer a three dimension joint along a desired trajectory precisely. First, the dynamics model of a three dimension joint is formulated and the trajectory tracking problem is described. Second, a sliding mode controller (SMC) is designed to track a time-varying trajectory. The fuzzy logic system (FLS) is employed to approximate the uncertain model of the three dimension joint, with the tracking error and its derivatives and the commanded trajectory and its derivatives as FLS inputs and the approximation of the uncertain model as FLS output. And a fuzzy logic system is also adopted to attenuate the chattering results from the SMC. The control gains are tuned synchronously with the sliding surface according to fuzzy rules, with switching sliding surface as fuzzy logic inputs and control gains as fuzzy logic outputs. The stability and convergence of the closed-loop controller is proven using the Lyapunov stability theorem. Finally, the effectiveness and robustness of the proposed controller are demonstrated via simulation results. Contrasting simulation results indicate that the AFLSMC attenuates the chattering effectively and has better performance against the SMC.

Fuzzy tracking control discuss the pure model behavior and ignore the original mathematical model, make the picking robot arm gain accurate perception ability to complex environmental condition, control its velocity and reach smoothly the target position. This paper proposed fuzzy tracking controller algorithm for obtaining the joints position relative to the desired trajectory, which drive stably 3 joints tending to be stable in 1.5s on the conditions of changeable environment, reflecting the strong robustness and stability of the tracking control system, enhancing their positioning and grasping stability to restrain picking robot arm chattering.

For an interior permanent magnet synchronous motor (IPMSM) control system, the actual maximum torque per ampere (MTPA) trajectory may deviate from the ideal one with parameter variances, and thus the system may not obtain the maximum torque output. In view of this problem, a novel parameter identification method based on the model reference adaptive system (MRAS) is proposed in this paper. In this method, the deviations of MTPA trajectories with parameter variances are analyzed and evaluated firstly, and then the q-axis inductance and the rotor flux linkage are identified on-line in a full rank MRAS model according to Popov Hyper Stability Theorem. Finally, the feasibility and validity of the designed method are proved through simulation results.

This paper addresses the problem of adaptive trajectory tracking control for the wheeled mobile robot (WMR) based on cascade-design method. The condition is considered that there is a distance between the mass center of the robot and the geometrical center. The tracking error system is divided into two subsystems: the position error system and the orientation error system. In order to deal with the circumstance with the unknown parameters, an adaptive tracking control law is proposed. Simulation results illustrate the effectiveness of the proposed control methods.

Robotic surgery, computer-assisted surgery, and robotically-assisted surgery are terms for technological developments that use robotic systems to aid in surgical procedures. Robotically-assisted surgery was developed to overcome the limitations of minimally-invasive surgery and to enhance the capabilities of surgeons performing open surgery. In the case of robotically-assisted minimally-invasive surgery, instead of directly moving the instruments, the surgeon uses one of two methods to control the instruments; either a direct telemanipulator or through computer control. A telemanipulator is a remote manipulator that allows the surgeon to perform the normal movements associated with the surgery whilst the robotic arms carry out those movements using end-effectors and manipulators to perform the actual surgery on the patient. In computer-controlled systems the surgeon uses a computer to control the robotic arms and its end-effectors, though these systems can also still use telemanipulators for their input. One advantage of using the computerised method is that the surgeon does not have to be present, but can be anywhere in the world, leading to the possibility for remote surgery. The multi degrees of freedom actuator is an important joint, which has attracted worldwide developing interests for its medical, industry and aerospace applications. This paper addresses the problem of trajectory tracking of three dimensions joint in the presence of model uncertainties and external disturbances. An adaptive fuzzy sliding mode controller (AFLSMC) is proposed to steer a three dimension joint along a desired trajectory precisely. First, the dynamics model of a three dimension joint is formulated and the trajectory tracking problem is described. Second, a sliding mode controller (SMC) is designed to track a time-varying trajectory. The fuzzy logic system (FLS) is employed to approximate the uncertain model of the three dimension joint, with the tracking error and its derivatives and the commanded trajectory and its derivatives as FLS inputs and the approximation of the uncertain model as FLS output. And a fuzzy logic system is also adopted to attenuate the chattering results from the SMC. The control gains are tuned synchronously with the sliding surface according to fuzzy rules, with switching sliding surface as fuzzy logic inputs and control gains as fuzzy logic outputs. The stability and convergence of the closed-loop controller is proven using the Lyapunov stability theorem. Finally, the effectiveness and robustness of the proposed controller are demonstrated via simulation results. Contrasting simulation results indicate that the AFLSMC attenuates the chattering effectively and has better performance against the SMC.

In this paper, we investigate the trajectory tracking problem for the 6-DOF quadrotor aircraft with both internal uncertainties and external disturbances. The nonlinear system model is established based on Modified Rodrigues Parameters and the error model is then obtained based on the trajectory tracking task. To deal with the cascade property of the controlled objective, the system is divided into the translational and rotational subsystem, respectively. Hence, a hierarchical technique is introduced to implement the control system. Then, nonlinear disturbance observer based backstepping control strategy is proposed based on each subsystem. Global stability of the closed-loop system is analyzed based on Lyapunov theorem. Simulation results verify the effectiveness of the proposed control scheme.

This paper presents investigations into the development of a Proportional-Integral Sliding Mode Control (PI-SMC) for trajectory tracking and vibration control of a flexible single link manipulator. The motor at the single rotating joint is the control actuator. Two SMC control laws are reviewed. The classical discontinuous control based on the signum function and a modified control law where the servomotor output voltage depends on the instantaneous values of the states. The selection of the discontinuity gain is reviewed for exact model (certain case) as well as when the parameter variations are present (uncertain case). To prove the reaching condition, we use the Lyapunov stability criteria. It is proven that this design is equivalent to a full state feedback with its steady state motion constrained to the sliding hyper-surfaces. Simulation results of the response of the flexible manipulator with both controllers are presented. The performances of the control schemes are examined for input tracking capability, level of vibration reduction and time response specifications. A comparative assessment of both control techniques shows the effectiveness of the second control law and its invariance to so-called matched uncertainty.

In this paper, an adaptive Kalman Filtering method is presented for the state prediction of random systems. It is shown that the adaptive Kalman Filtering method in conjunction with equilibrium optimization solution can estimate the initial accelerations of targets effectively since the equilibrium optimization solution tunes the state prediction vector to diminish the error between measured value and prediction estimation value. We evaluate our model on special and random trajectories. Experimental evidence shows that the proposed method can robustly estimate an initial acceleration from a dynamic model and stably track a trajectory which is moving randomly.

Object tracking is important and challenging task in many computer vision applications such as surveillance, vehicle navigation, and autonomous robot navigation. Video surveillance in a dynamic environment, especially for humans and vehicles, is one of the current challenging research topics in computer vision. It is a key technology to fight against terrorism, crime, public safety and for efficient management of traffic. In this paper, in order To get an accurate description of the trajectory points, regression analysis technique is used. This technique has the ability to summarize the collection of trajectory points by fitting it to mathematical models which will accurately describe these points and consequently describe object behavior. The regression analysis technique uses the least square method to obtain the best fit of equations for the given set of trajectory points. The least square method assumes that the best fit curve has the minimal sum of the deviations squared error from the given set of data. In this paper, propose new method to deal with the trajectory by converting the trajectory points into 3D approximation function using best fit plane after interpolation the time factor this method offers high flexibility as well as statistical tools for the analysis behavior of object. Planar regression calculates the best fit plane through a group of 3 or more data points. The plane is calculated by minimizing the residuals (or errors) between the plane and the original points using least squares minimization. The objective of this paper was to develop methods for optimization of least square best fit geometry for planes.

DCT는 효율적인 에너지의 집중과 공간적 중복성을 제거하는 장점을 가지고 있어 영상압축 또는 비디오 신호처리등 다양한 분야에서 널리 사용되고 있다. 하지만 DCT는 많은 연산량의 문제를 가지고 있다. Loeffler에 의해 제안된 1차원 8-point DCT는 최소 11개의 곱셈과 29개의 덧셈을 이용하여 DCT 계수를 얻게 된다. 정수형 binDCT는 시스템의 복잡도를 증가시키는 곱셈 연산을 리프팅 구조를 이용해 덧셈과 지연으로 전환하여 DCT 계수를 구하게 되고 실수형 계수를 정수형의 계수로 바꾸어서 처리함으로써 시스템의 복잡도를 줄일 수 있다. DCT를 이용한 스케일러블 영상압축 알고리즘은 EZW[6], SPIHT와 같이 원하는 비트율까지 압축을 수행하게 되는데 다해상도 변환을 사용하는 경우에 비해 복잡도가 낮으면서도 높은 성능의 영상을 얻을 수 있는 장점이 있다.

The DCT has merit such effects of energy compression and removing redundancy that we found wide applications in image compression and video signal processing and other field. But DCT has high complexity. The theoretical lower bound on the number of multiplications required for the 1-D 8-pont DCT by loeffler has been proven to be 11 multiplications and 29 additions. The integer binDCT exchanges multiplication with addition and delay by using lifting scheme. Also, the integer binDCT reduce the complexity of the system by processing of exchanging floating point coefficients with integer coefficients. The scalable image compression using integer DCT accomplishes the compression on variable bit rate similar to EZW and SPIHT. It has the merit of lower complexity and higher performance than using multi-resolution transform.

Modeling, control and implementation of a real redundant robot with five Degrees Freedom (DOF) of the SCARA (Selective Compliant Assembly Robot Arm) manipulator type is presented. Through geometric methods and structural and functional considerations, the inverse kinematics for redundant robot can be obtained. By means of a modification of the classical sliding mode control law through a hyperbolic function, we get a new algorithm which enables reducing the chattering effect of the real actuators, which together with the learning and adaptive controllers, is applied to the model and to the real robot. A simulation environment including the actuator dynamics is elaborated. A 5 DOF robot, a communication interface and a signal conditioning circuit are designed and implemented for feedback. Three control laws are executed in: a simulation structure (together with the dynamic model of the SCARA type redundant manipulator and the actuator dynamics) and a real redundant manipulator of the SCARA type carried out using MatLab/Simulink programming tools. The results, obtained through simulation and implementation, were represented by comparative curves and RMS indices of the joint errors, and they showed that the redundant manipulator, both in the simulation and the implementation, followed the test trajectory with less pronounced maximum errors using the adaptive controller than the other controllers, with more homogeneous motions of the manipulator.

This paper presents a state feedback based backstepping control algorithm to address the trajectory tracking problem of an underactuated Unmanned Surface Vessel (USV) in the horizontal plane. A nonlinear three Degree of Freedom (DOF) underactuated dynamic model for USV is considered, and trajectory tracking controller that can track both curve trajectory and straight line trajectory with high accuracy is designed as the well known Persistent Exciting (PE) conditions of yaw velocity is completely relaxed in our study. The proposed controller has further been enriched by incorporating an integral action additionally for enhancing the steady state performance and control precision of the USV trajectory tracking control system. Global stability of the overall system is proved by Lyapunov theory and Barbalat's Lemma, and then simulation experiments are carried out to demonstrate the effectiveness of the controller designed.

This work presents a trajectory control for non-redundant serial-link manipulators that is valid for trajectories with ordinary singularities of codimension one and non-ordinary singularities of any codimension. For this purpose, several singularity classifications are considered and a procedure is developed in order to solve the indeterminate motion of non-ordinary singularities. The proposed trajectory control is validated by simulation and by experiments with the six-revolute (6R) industrial robot KUKAKR 15/2.