This paper addresses the issues arising when transmitting video across wireless and heterogenous networks. Key factors considered in this application are the large volumes raw data created by the video sources. These ...
详细信息
This paper addresses the issues arising when transmitting video across wireless and heterogenous networks. Key factors considered in this application are the large volumes raw data created by the video sources. These factors combine to conflicting requirements: aggressive compression ratios of 1000-10000 with simple decoding algorithms. Also, the Generative Video (GV), a content-based video meta representation that reduces video sequences to a small number of still images (world images) and site information (ancillary data) is presented. The GV representation is particularly suited to the wireless environment: it has the potential of large compression ratios at acceptable perceptual quality, it is easily scalable, and it is an asymmetric encoding/decoding algorithm.
Accurate navigation of a mobile robot in cluttered rooms using a range-measuring laser as a sensor has been achieved. To extract the directions and distances to the walls of the room the range-weighted Hough transform...
详细信息
Accurate navigation of a mobile robot in cluttered rooms using a range-measuring laser as a sensor has been achieved. To extract the directions and distances to the walls of the room the range-weighted Hough transform is used. The following experimental results are emphasized: The robot extracts the walls of the surrounding room from the range measurements. The distances between parallel walls are estimated with a standard deviation smaller than 1 cm. It is possible to navigate the robot along any preselected trajectory in the room. One special case is navigation through an open door detected by the laser. The accuracy of the passage is 1 cm at a speed of 0.5 m/s. The trajectory is perpendicular to the wall within 0.5 degrees in angle. When navigating through corridors, the accuracy is better than I cm at 0.8 m/s - the maximum speed of the robot. Odometric data and laser measurements are combined using the extended Kalman filter. The size of the cluttered rectangular room and the position and orientation (pose) of the robot are estimated during motion. The extraction and the resulting navigation are very robust against bath spurious measurements in the laser measurements and disturbing objects.
作者:
KIM, JHCHO, HSCenter for Robotics and Automation
Department of Precision Engineering and Mechatronics Korea Advanced Institute of Science and Technology 373-1 Kusong-dong Yusong-gu Taejon 305-701 Korea
In this paper, we describe an approach to inspection of solder joints on printed circuit boards by using a circular illumination technique and a neural network classifier. The illumination technique, consisting of thr...
详细信息
In this paper, we describe an approach to inspection of solder joints on printed circuit boards by using a circular illumination technique and a neural network classifier. The illumination technique, consisting of three tiered circular colour lamps and one colour camera, gives good visual cues to infer 3D shape of the solder joint surface. A general aspect of this inspection is that the shape of the solder joint tends to greatly vary according to soldering conditions. Due to this, a neural network classifier based on a supervised version of Kohonen learning vector quantization (LVQ) is proposed to automatically and efficiently make classification criteria of the solder joint shapes according to their quality. The practical feasibility of the proposed approach is demonstrated by building a prototype inspection machine and testing its performance.
This paper presents a robot and algorithms for autonomous spray plastering of walls and ceilings during the construction of apartment houses. Successful experimental tests are described where the robot measures the si...
详细信息
This paper presents a robot and algorithms for autonomous spray plastering of walls and ceilings during the construction of apartment houses. Successful experimental tests are described where the robot measures the size of the room and the location of doors and windows. The work sequence is then planned and executed autonomously. To sense the environment the robot uses a range measuring scanning laser. The range weighted Hough transform is used to observe the walls and the resulting observations are used to update estimates in an extended Kalman filter based map. Association of observations to estimates is performed using the estimated probability of a correct match, taking correlations between estimates into account when needed.
This paper proposes a new method of estimating the position and heading angle of a mobile robot moving on a flat surface. The proposed localization method utilizes two passive beacons and a single rotating ultrasonic ...
详细信息
This paper proposes a new method of estimating the position and heading angle of a mobile robot moving on a flat surface. The proposed localization method utilizes two passive beacons and a single rotating ultrasonic sensor. The passive beacons consist of two cylinders with different diameters and reflect the ultrasonic pulses coming from the sonar sensor mounted on the mobile robot. The sonar sensor, again, mounted on a pan-tilt device then receives the reflected pulses while scanning over a wide area. The geometric parameter set of beacon is acquired from the sonar scan data obtained at a single mobile robot location using a new data processing algorithm. The presented algorithm is especially suitable for processing the sonar scan data obtained by ultrasonic sensor with wide beam spread. From this parameter set, the position and heading angle of the mobile robot is determined directly. The performance and validity of the proposed method are evaluated using two beacons and a single sonar sensor attached at the pan-tilt device mounted on a mobile robot, named LCAR, in our laboratory.
This paper discusses the use of neural networks in the modelling of complex systems in an industrial environment. In particular, issues related to hybrid and hierarchical system modelling and control are presented and...
详细信息
This paper discusses the use of neural networks in the modelling of complex systems in an industrial environment. In particular, issues related to hybrid and hierarchical system modelling and control are presented and neural network architectures that can be applied in such situations arc examined. Also, the model of a laboratory size pilot head box of a paper machine using a neural network is presented as an example process
This paper is on sensor based control for guiding a robot to correct gripping of objects having a large position uncertainty. An eye-in-hand mounted range camera is considered. A probabilistic problem formulation base...
详细信息
This paper is on sensor based control for guiding a robot to correct gripping of objects having a large position uncertainty. An eye-in-hand mounted range camera is considered. A probabilistic problem formulation based on the requested posture at gripping and corresponding tolerances is presented. The problem is solved approximately using dynamic programming for a 1-degree-of-freedom manipulator. A five-step dual control law is studied in more detail. A typical case is that in the first part of the control sequence the robot steers towards the optimal sensing position and in the last part the error with respect to the gripping posture is minimized. Since range camera sensing introduces both range dependent noise and occlusion there is a need for 'exploratory moves'. This behavior is formalized and includes 'dual control'.
This paper describes an algorithm for adjusting a robot motion plan in order to make it feasible in spite of control and sensing uncertainties in the robot configuration. The type of motion plan considered consists of...
详细信息
This paper describes an algorithm for adjusting a robot motion plan in order to make it feasible in spite of control and sensing uncertainties in the robot configuration. The type of motion plan considered consists of a nominal commanded path, augmented by sensing mode specifications. The algorithm uses a bounding-set representation of uncertainties, which is also described. The control uncertainty is history independent, but the sensing uncertainty at one point in a plan depends on the prior sensing actions and the path traversed. The algorithm is a path-space algorithm, because it adjusts the entire plan simultaneously as it carries out the search.
Summary form only given. While industrial automation has long been associated with the increase of manufacturing productivity, much of the current motivation behind the development of advanced automation techniques is...
详细信息
Summary form only given. While industrial automation has long been associated with the increase of manufacturing productivity, much of the current motivation behind the development of advanced automation techniques is driven by the need to enhance product quality, increase the safety of the operational environment, and quickly respond to changing consumer demands for new products. In this paper, we introduce some modern principles underlying the design and operation of advanced automation systems, then describe several industrial implementations in both manufacturing and service sectors. Special attention is paid to the concept of mass customization, and its potential impact on the growth of small enterprises. We start with the design stage, then look at the manufacturing process, and discuss the application of advanced automation concepts to the processing of both metals and textiles. The role of computer based modeling and inspection as quality control tools is examined. Finally, we present several recent developments in intelligent robotic systems, and describe their applications. Specific examples involving maintenance and repairs in nuclear power generation plants are discussed.
The demand for effective project management increases as the complexity and cost of a project grown. This paper introduces an interactive project management approach based on the Petri net to overcome the limitations ...
详细信息
The demand for effective project management increases as the complexity and cost of a project grown. This paper introduces an interactive project management approach based on the Petri net to overcome the limitations of network diagrams. In the Petri net based approach, the project manager does fine tuning of the planning and scheduling with the resource constraints embedded in the plan representation. The Petri net controller maintains three plan representations. The reference, monitor and predictor Petri nets. These three nets are configured with the resource database to form a feedback loop such that the controller can monitor and control the project online. This structure is applicable to the control of more general discrete event dynamic systems as well as the project management problem. In case no admissible control action can be found, the manager turns to the rescheduling/replanning mode to generate a new plan and schedule.
暂无评论