1,720,969 research outputs found
Tele-operated climbing and mobile service robots for remote inspection and maintenance in nuclear industry
No full textCombined genetic algorithm optimization and regularized orthogonal least squares learning for radial basis function networks
No full textThe paper presents a two-level learning method for radial basis function (RBF) networks. A regularized orthogonal least squares (ROLS) algorithm is employed at the lower level to construct RBF networks while the two key learning parameters, the regularization parameter and the RBF width, are optimized using a genetic algorithm (GA) at the upper level. Nonlinear time series modeling and prediction is used as an example to demonstrate the effectiveness of this hierarchical learning approach
Intelligent legged climbing service robot for remote inspection and maintenance in hazardous environments
No full text
Using genetic algorithms to establish efficient walking gaits for an eight-legged robot
No full textIn the design and development of a legged robot, many factors need to be considered. As a consequence, creating a legged robot that can efficiently and autonomously negotiate a wide range of terrain is a challenging task. Many researchers working in the area of legged robotics have traditionally looked towards the natural world for inspiration and solutions, reasoning that these evolutionary solutions are appropriate and effective because they have passed the hard tests for survival over time and generations. This paper reports the use of genetically inspired learning strategies, commonly referred to as genetic algorithms, as an evolutionary design tool for improving the design and performance of an algorithm for controlling the leg stepping sequences of a walking robot. The paper presents a specific case of finding optimal walking gaits for an 8-legged robot called Robug IV and simulated results are provided
Walking and climbing service robots for safety inspection of nuclear reactor pressure vessels
Full text linkInspection and maintenance are essential in the nuclear industry. Failure to carry out proper maintenance could increase the chance of accidents which could result in severe casualties not only inside the nuclear plant but also in the nearby community. However, it is not easy to carry out such maintenance tasks since the environments are usually highly radioactive and unsafe for humans to workin. The usual way of carrying out inspection and maintenance tasks in these hazardous environments is by using long-reach fixed base manipulators. However, these manipulators suffer from low payload capacity and relatively large end-point deflections. Also, the installation and the storage of these long manipulators could be costly. An alternative solution is to use walking-climbing robots, which overcome the problems encountered by the long-reach manipulators.Over the years, a number of climbing robots have been developed for various applications [1-15]. However, most of these robots are only engineering prototypes and have not been used for any extensive inspection and maintenance operations. In this paper, we describe a number of teleoperated walking-climbing robots developed by the authors, which includeNERO series and SADIE series. These robots have been designed for remote inspection and maintenance applications, especially for the nuclear industry. All of these robots have been applied successfully in practical applications
Climbing service robot for duct inspection and maintenance applications in a nuclear reactor
No full textIntelligent legged climbing service robot for remote maintenance applications in hazardous environments
No full text
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
