In industry, it is becoming common to detect and recognize industrial workpieces using deep learning methods. In this field, the lack of datasets is a big problem, and collecting and annotating datasets in this field is very labor intensive. The researchers need to perform dataset annotation if a dataset is generated by themselves. It is also one of the restrictive factors that the current method based on deep learning cannot expand well. At present, there are very few workpiece datasets for industrial fields, and the existing datasets are generated from ideal workpiece computer aided design (CAD) models, for which few actual workpiece images were collected and utilized. We propose an automatic industrial workpiece dataset generation method and an automatic ground truth annotation method. Included in our methods are three algorithms that we proposed: a point cloud based spatial plane segmentation algorithm to segment the workpieces in the real scene and to obtain the annotation information of the workpieces in the images captured in the real scene; a random multiple workpiece generation algorithm to generate abundant composition datasets with random rotation workpiece angles and positions; and a tangent vector based contour tracking and completion algorithm to get improved contour images. With our procedures, annotation information can be obtained using the algorithms proposed in this paper. Upon completion of the annotation process, a json format file is generated. Faster R-CNN (Faster R-convolutional neural network), SSD (single shot multibox detector) and YOLO (you only look once: unified, real-time object detection) are trained using the datasets proposed in this paper. The experimental results show the effectiveness and integrity of this dataset generation and annotation method.
Accurate classification of cardiac arrhythmias is a crucial task because of the non-stationary nature of electrocardiogram (ECG) signals. In a life-threatening situation, an automated system is necessary for early detection of beat abnormalities in order to reduce the mortality rate. In this paper, we propose an automatic classification system of ECG beats based on the multi-domain features derived from the ECG signals. The experimental study was evaluated on ECG signals obtained from the MIT-BIH Arrhythmia Database. The feature set comprises eight empirical mode decomposition (EMD) based features, three features from variational mode decomposition (VMD) and four features from RR intervals. In total, 15 features are ranked according to a ranker search approach and then used as input to the support vector machine (SVM) and C4.5 decision tree classifiers for classifying six types of arrhythmia beats. The proposed method achieved best result in C4.5 decision tree classier with an accuracy of 98.89% compared to cubic-SVM classifier which achieved an accuracy of 95.35% only. Besides accuracy measures, all other parameters such as sensitivity (Se), specificity (Sp) and precision rates of 95.68%, 99.28% and 95.8% was achieved better in C4.5 classifier. Also the computational time of 0.65 s with an error rate of 0.11 was achieved which is very less compared to SVM. The multi-domain based features with decision tree classifier obtained the best results in classifying cardiac arrhythmias hence the system could be used efficiently in clinical practices.
Remote sensing image registration is still a challenging task owing to the significant influence of nonlinear differences between remote sensing images. To solve this problem, this paper proposes a novel approach with regard to feature-based remote sensing image registration. There are two key contributions: 1) we bring forward an improved strategy of composite nonlinear diffusion filtering according to the scale factors in multi-scale space and 2) we design a gradually decreasing resolution of multi-scale pyramid space. And a binary code string is served as feature descriptors to improve matching efficiency. Extensive experiments of different categories of remote image datasets on feature extraction and feature registration are performed. The experimental results demonstrate the superiority of our proposed scheme compared with other classical algorithms in terms of correct matching ratio, accuracy and computation efficiency.
Dragline excavators are closed-loop mining manipulators that operate using a rigid multilink framework and rope and rigging system, which constitute its front-end assembly. The arrangements of dragline front-end assembly provide the necessary motion of the dragline bucket within its operating radius. The assembly resembles a five-link closed kinematic chain that has two independent generalized coordinates of drag and hoist ropes and one dependent generalized coordinate of dump rope. Previous models failed to represent the actual closed loop of dragline front-end assembly, nor did they describe the maneuverability of dragline ropes under imposed geometric constraints. Therefore, a three degrees of freedom kinematic model of the dragline front-end is developed using the concept of generalized speeds. It contains all relevant configuration and kinematic constraint conditions to perform complete digging and swinging cycles. The model also uses three inputs of hoist and drag ropes linear and a rotational displacement of swinging along their trajectories. The inverse kinematics is resolved using a feedforward displacement algorithm coupled with the Newton-Raphson method to accurately estimate the trajectories of the ropes. The trajectories are solved only during the digging phase and the singularity was eliminated using Baumgarte′s stabilization technique (BST), with appropriate inequality constraint equations. It is shown that the feedforward displacement algorithm can produce accurate trajectories without the need to manually solve the inverse kinematics from the geometry. The research findings are well in agreement with the dragline real operational limits and they contribute to the efficiency and the reduction in machine downtime due to better control strategies of the dragline cycles.
In order to satisfy the robotic personalized service requirements that can select exclusive items to perform inference and planning according to different service individuals, the service robots need to have the ability to independently obtain the ownership relationship between humans and their carrying items. In this work, we present a novel semantic learning strategy for item ownership. Firstly, a human-carrying-items detection network based on human posture estimation and object detection model is used. Then, the transferred convolutional neural network is used to extract the characteristics of the objects and the back-end classifier to recognize the object instance. At the same time, the face detection and recognition model are used to identify the service individual. Finally, on the basis of the former two, the active learning of ownership items is completed. The experimental results show that the proposed ownership semantic learning strategy can determine the ownership relationship of private goods accurately and efficiently. The solution of this problem can improve the intelligence level of robot life service.
Methods to stabilize discrete-time linear control systems subject to variable sampling rates, i.e., using state feedback controllers, are well known in the literature. Several recent works address the use of the Tikhonov regularization method, originally designed to attenuate the noise effects on ill-posed problems, with the aim of improving performance and stabilizing approximately controllable dynamical systems. Inspired by these works, we propose the use of a feedback controller designed using the Tikhonov method to regularize discrete-time linear systems subject to varying sampling rates. The goal is to minimize an error function, thus improving the performance of the closed loop system and reducing the possibility of instability. Illustrative examples show the effectiveness of the proposed method.
The multi-robot systems (MRS) exploration and fire searching problem is an important application of mobile robots which require massive computation capability that exceeds the ability of traditional MRS′s. This paper propose a cloud-based hybrid decentralized partially observable semi-Markov decision process (HDec-POSMDPs) model. The proposed model is implemented for MRS exploration and fire searching application based on the Internet of things (IoT) cloud robotics framework. In this implementation the heavy and expensive computational tasks are offloaded to the cloud servers. The proposed model achieves a significant improvement in the computation burden of the whole task relative to a traditional MRS. The proposed model is applied to explore and search for fire objects in an unknown environment; using different sets of robots sizes. The preliminary evaluation of this implementation demonstrates that as the parallelism of computational instances increase the delay of new actuation commands which will be decreased, the mean time of task completion is decreased, the number of turns in the path from the start pose cells to the target cells is minimized and the energy consumption for each robot is reduced.
The return capsule needs to be launched to the moon and return back to earth in the third stage of the Chinese lunar exploration project. Therefore, it is necessary to perform simulations on the ground. This paper presents an 8-cable-driven parallel manipulator to achieve end-force output in a low-gravity environment. End-force output refers to the vector sum of the external force on the end-effector. A model of end-force output is established based on a kinematics model, a dynamic model, and a force analysis of an 8-cable driven parallel manipulator. To obtain end-force output in a low-gravity environment, the cable force has to be controlled to counteract gravity. In addition, a force-position mix control strategy is proposed to proactively control the cable force according to the force optimal distribution given by the closed-form force distribution method. Furthermore, a suitable choice for an end-force output is obtained by modeling the effect of cable force on end-force output. Experimental results show that the actual cable force agrees well with the calculated force distribution, indicating that it is feasible to realize end-force output in a low gravity environment.
Computer based automation and control systems are becoming increasingly important in smart sustainable buildings, often referred to as automated buildings (ABs), in order to automatically control, optimize and supervise a wide range of building performance applications over a network while minimizing energy consumption and associated green house gas emission. This technology generally refers to building automation and control systems (BACS) architecture. Instead of costly and time-consuming experiments, this paper focuses on development and design of a distributed dynamic simulation environment with the capability to represent BACS architecture in simulation by run-time coupling two or more different software tools over a network. This involves using distributed dynamic simulations as means to analyze the performance and enhance networked real-time control systems in ABs and improve the functions of real BACS technology. The application and capability of this new dynamic simulation environment are demonstrated by an experimental design, in this paper.
Pneumatic artificial muscles (PAM) have been recently considered as a prominent challenge regarding pneumatic actuators specifically for rehabilitation and medical applications. Since accomplishing accurate control of the PAM is comparatively complicated due to time-varying behavior, elasticity and ambiguous characteristics, a high performance and efficient control approach should be adopted. Besides of the mentioned challenges, limited course length is another predicament with the PAM control. In this regard, this paper proposes a new hybrid dynamic neural network (DNN) and proportional integral derivative (PID) controller for the position of the PAM. In order to enhance the proficiency of the controller, the problem under study is designed in the form of an optimization trend. Considering the potential of particle swarm optimization, it has been applied to optimally tune the PID-DNN parameters. To verify the performance of the proposed controller, it has been implemented on a real-time system and compared to a conventional sliding mode controller. Simulation and experimental results show the effectiveness of the proposed controller in tracking the reference signals in the entire course of the PAM.
Energy Efficient Scheduler of Aperiodic jobs for Real-Time Embedded Systems
- Experimental Evaluation of Certain Pursuit and Evasion Schemes for Wheeled Mobile Robots
- Time-space Viewpoint Planning for Guard Robot with Chance Constraint
- Synthesizing Robot Programs with Interactive Tutor Mode