Pose estimation is a typical problem encountered in computer vision. Therefore, it is important to improve the accuracy of this method. Aiming at the accuracy of pose estimation, we propose a high-accuracy pose estimation algorithm based on the you only look once network and residual network with a monocular camera as the sensor for visual acquisition. This algorithm uses ArUco markers as a reference for object localization and uses the red, green, and blue (RGB) image as the input. The input image is sampled 16 and 32 times to extract the feature image, and the feature image extracted by 16 times sampling is passed through the pass-through layer and then combined with the feature image extracted by 32 times sampling to accomplish the dimension expansion. The feature image is identified by the convolutional layer. The EPnP algorithm is used to solve the camera poses. The pose information of the target object in the RGB image is used as the output. By comparing the pose estimation accuracy for the LINEMOD dataset with three evaluation metrics—the 2D projection metric, ADD metric, and 5 cm to 5 deg metric—it can be observed that the pose estimation algorithm proposed has advantages in terms of accuracy compared with traditional pose estimation algorithms. When the target is very similar to the background objects, the algorithm also achieves good performance.
Sensor network integrates sensor technology, MEMS (Micro-Electro-Mechanical system) technology, embedded
computing, wireless communication technology and distributed information management technology. It is of great value
to use it where human is quite difficult to reach. Power consumption and size are the most important consideration when
nodes are designed for distributed WSN (wireless sensor networks). Consequently, it is of great importance to decrease
the size of a node, reduce its power consumption and extend its life in network. WSN nodes have been designed using
JN5121-Z01-M01 module produced by jennic company and IEEE 802.15.4/ZigBee technology. Its new features include
support for CPU sleep modes and a long-term ultra low power sleep mode for the entire node. In low power
configuration the node resembles existing small low power nodes. An embedded temperature sensor node has been
developed to verify and explore our architecture. The experiment results indicate that the WSN has the characteristic of
high reliability, good stability and ultra low power consumption.
A digital temperature testing system has been developed using a programmable chip for a ZY cutting-type quartz tuning
fork temperature sensor. The system consists of hardware and software functionalities and it is implemented on an Altera
Cyclone II EP2C35 Field Programmable Gate Array including a NIOS core processor. To satisfy the real time processing
constraints on the one hand, and parameterization on the other hand, part of the algorithm are implemented in hardware
and others are implemented in software. Experimental results indicate that the testing system can be used to measure the
temperature with an accuracy of 0.01 degree C, and the effective resolution is better than 0.003 degree C in the range of -
20 degree C to 140 degree C.
KEYWORDS: Control systems, 3D modeling, Digital signal processing, Mathematical modeling, Sensors, Video, Three dimensional sensing, Information visualization, Data modeling, Environmental sensing
A novel control method, called Interactive Partial Modeling-based Teleoperation Control (IPMTC) was developed to realize the intelligent control of the telerobot system in unstructured environment, combined with the intelligent digital hybrid controller that have been developed. This method can estimate task status and environment perception information, and send requests for intervention of human operation (HO) real time during autonomy. In order to guarantee real time transition of HO intervention and autonomy, the intelligent control module was developed based on the results of task estimation, which can realize the functions of task plan, subtask autonomous execution, and automated reasoning about the task. A new remote predictive control method and the single/double delay time compensation strategy are introduced to improve the real time performance of the system. The performances of the teleoperation system in unstructured environments are guaranteed with above control techniques.
KEYWORDS: Quartz, Resonators, Temperature sensors, Crystals, Sensors, Electrodes, Finite element methods, Temperature metrology, Lithium, Crystallography
The miniature frequency-temperature sensor based on quartz tuning fork resonators with a new ZYtw-cut and vibrating
in the flexural mode has been described. The resonance frequency of a quartz tuning fork crystal was comprehensively
analyzed by an analytical method, Sezawa's approximations and the finite element method. The influence of the sensor
structural dimension on the resonant frequency and structural modes is investigated, which offers reliable basis for the
structure design tuning fork geometry, tine electrode pattern and thickness of the micro quartz crystal tuning fork
temperature sensor. The validity of calculated and simulated results is experimentally confirmed. The experimental
results has shown that this new type of sensor with sensitivity about 0.001 degree C and accuracies 0.05 degree C
within temperature range from -50 degree C to 200 degree C.
KEYWORDS: Quartz, Crystals, Resonators, Temperature sensors, Temperature metrology, Finite element methods, Semiconducting wafers, Electrodes, 3D modeling, Crystallography
A new type of piezoelectric resonance quartz crystal temperature sensors which exhibits a high precision and a good stability has been developed. A Y-cut (4.05°) quartz resonator operating on low-frequency thickness C-mode was chosen as the temperature sensor because of its availability and its good linear frequency versus temperature characteristic. In order to reduce the mounting effects and to decouple interfering modes of motion, the contour structures of the quartz wafers having a biconvex type and bat metallic electrodes with the sine ripple on the surfaces of the quartz wafer are used. The resonance frequency was analyzed by three-dimensional Finite Element Method and the results are compared with the theoretical values whenever they are available. Using low-cost oscillators connected to a microcontroller, a precise measurement system of temperature is implemented. Experimentally, the accuracy of measurement is better than 0.05 degree C (The errors include non-linearity, reproducibility and influence of load temperature) over the temperature range -60 degree C to 200 degree C.
The automatic gelatinizing system described in this paper adopts a DRC robot controller and a programmable controller (PLC) as its core. The DRC controller receives signals from the glue gun, cylinder sensors on the worktable, arms' limit switches of the SCARA robot, control signals from PLC, and so on. After systematic calculation and analysis, the DRC drives the robot's motors of every axis, electromagnetic valves, indicator lights, ancillary components on the claw, etc. The PLC receives input signals from the robot controller and detection sensors to control the air cylinder of clamps, loading and unloading devices, support panel and electrical motors, and it can also control the motor of the feeding glue system precisely. An automatic off-line programming system is developed with Visual C++ 6.0 programmable language to solve problems in the course of applying automatic gelatinizing robot, by which the users can easily design their own gelatinizing schemes at their will according to different gelatinizing tasks.
This paper detailedly presents a moving robot with multi-sensor, which can be programmed on-line. The main controller of moving robot is designed based on the controlling function of 80C552 microprocessor, and the graph programming software developed with VC++ 6.0 is used, making the robot easy to be manipulated. By downloading programs to its controller through the serial port of computers, the moving robot can avoid obstructions, recognize sound and move off-line automatically depending on various sensors and micro operating system.
Automatic deephole admeasuring apparatus is an automatic synthetical multiparameter instrument which makes use of the automatic crawl capability of pipeline robot to drive the measuring device moving forward and adopts optical measuring method to measure deephole inside diameter, interior surface roughness concentration and straightness accuracy. This apparatus has distinguishability of 1 μm with measuring precision less than 5 μm, range of roughness between 1.6 and 2.0, measuring error between 1/8 to 1/4 grade; straightness accuracy measuring precision of deephole as long as 10 meters is less than 100 μm.
KEYWORDS: Control systems, Databases, Local area networks, Data transmission, Telecommunications, Computer programming, Cutting equipment, Motion controllers, Data communications, Data storage
The system combines the motion control technology and LAN advantages. Usually there are one center computer and several or more subordinate computers, which form star-topotaxy mode. The data transmission strategy makes use of mature database management system SQLSERVER, which can automatically deal with data communication, so the programmer can avoid complicated communication programming. The system construction is simple and mainly oriented to small-middle scale enterprise and CIMS project. By practice, the system has been developed and used for industry production and control successfully.
KEYWORDS: Visualization, Servomechanisms, Space robots, Control systems, Cameras, Robotic systems, Information visualization, Computing systems, Intelligence systems, 3D acquisition
In this paper, a PUMA562 robot, a micro CCD camera and an image acquisition card, along with IBM/PC 586 host computer, formed eye-in-hand visual servoing experimental system of an intelligent space robot. A novel robot visual servo control method is adopted, based on FMF neural network. Computer simulation and many experiments of object tracking with the capture of floating object were carried out in this eye-in- hand visual servoing system. It is an important reference to further research in the future.
Through the study of 3D information acquisition technique, this paper proposed an experiment system for robot eye-in-hand vision 3D information acquisition. The system adopts to a singer camera, and realizes object space 3D information through the detection to object for PUMA562 robot system. This system has been successfully implied in space robot system and intelligent grippers.
Grinding is one of the most complex and unpredictable metal- removing processes. Based on the in situ repairing operation in turbine blades, this paper presents a novel welding and grinding system, which consists of a portable robot and its control system, a novel waist F/T sensor and its control system, camera and image processing card, welding gun and grinding well. The robot can be moved and can be conveniently operated by one man. At the same time, it is fit into a 600 mm hole (access hole) and can reach over 90% of the total blade surface. Its productivity increases three times compared to man operation.
A hybrid position/force controller is designed for the joint 2 and the joint 3 of the PUMA 560 robot. The hybrid controller includes a multilayered neural network, which can identify the dynamics of the contacted environment and can optimize the parameters of the PID controller. The experimental results show that after having been trained, the robot has both stable response to the training patterns and strong adaptive ability to the situation between the patterns.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.