The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Populations of simulated agents controlled by dynamical neural networks are trained by artificial evolution to access linguistic instructions and to execute them by indicating, touching, or moving specific target objects. During training the agent experiences only a subset of all object/action pairs. During postevaluation, some of the successful agents proved to be able to access and execute also...
The interaction experiment, between a robot and a rat, will benefit significantly when the rat's actions can be recognized automatically in real time. Regarding quantitative behavior analysis, the number and duration of a rat's actions should be measured efficiently and accurately. Therefore, aiming at the above-mentioned objectives, a novel cognition system capable of detecting rats' actions has...
Fingerprint image quality estimation is crucial in eliminating poor fingerprint images, which will affect the performance of the automatic fingerprint identification system. In this paper, we present an image quality estimation method based on neural network. Unlike other methods, which are also based on neural network, we directly take the gray value of fingerprints as inputs into the network. This...
This paper presents a new probabilistic neural network model, called IPNN (for Incremental Probabilistic Neural Network), which is able to learn continuously probability distributions from data flows. The proposed model is inspired in the Specht's general regression neural network, but have several improvements which makes it more suitable to be used in on-line and robotic tasks. Moreover, IPNN is...
Tests showed that, at the feeding beam's end, there are large position and pose error during the boring orientation of Rock-drilling robot. And the error are relate to both the roll angle and the extended length of the feeding beam. With analyzing the flexible deformation about different fed length, it is showed that flexible deformation is not the main reason of the error. The error is also caused...
Historically, learning algorithms have been applied to games as a test of their performance, and with the exponential increases in available computational power, machine learning has been attempted in increasingly complex environments. This paper details the application of neuroevolution of augmenting topologies (NEAT) and accuracy-based learning classifier system (XCS) to the Robocode game environment,...
This paper proposes self-organizing neural networks for modeling behavior of non-player characters (NPC) in first person shooting games. Specifically, two classes of self-organizing neural models, namely Self-Generating Neural Networks (SGNN) and Fusion Architecture for Learning and Cognition (FALCON) are used to learn non-player characters' behavior rules according to recorded patterns. Behavior...
This paper describes slide-bending formation of metallic sheet by using a neural network. The formation of parts made of very thin metallic sheets has become increasingly important miniaturizing industrial products, including electrical and mechanical devices. One of the authors proposed a new method called a slide-bending formation method for the bending of the metallic sheet. In this method, the...
This paper investigates the use of autonomous learning in the problems of complex robot assembly of miniature parts in the example of mating the gears of one multistage planetary speed reducer. Assembly of tube over the planetary gears was noticed as the most difficult problem of overall assembly and favourable influence of vibration and rotation movement on compensation of tolerance was also observed...
Applying evolution to generate simple agent behaviours has become a successful and heavily used practice. However the notion of scaling up behaviour into something more noteworthy and complex is far from elementary. In this paper we propose a method of combining neuroevolution practices with the subsumption paradigm; in which we generate Artificial Neural Network (ANN) layers ordered in a hierarchy...
The computation of a mobile robot position and orientation is a common task in the area of computer vision and image processing. For a successful application, it is important that the position and orientation of a mobile robot must be determined properly. In this paper, a simple procedure for determining the orientation of a mobile robot using two cameras is presented. The two cameras are used to...
This paper describes a method for developing control of high degree-of-freedom (DOF) mobile robots using the seventh generation (7G) system, a software system that incorporates learning, genetic algorithms, and scripting. The control agent is based on a neural network implementing a reinforcement learning process. The network accepts sensor data as input and learns to output control actions. A novel...
In this paper, we propose a swarm intelligence based reinforcement learning (SWIRL) method to train artificial neural networks (ANN). Basically, two swarm intelligence based algorithms are combined together to train the ANN models. Ant Colony Optimization (ACO) is applied to select ANN topology, while Particle Swarm Optimization (PSO) is applied to adjust ANN connection weights. To evaluate the performance...
In order to automate the excavating process, the path of the excavator bucket tip should be optimally generated. The following four factors must be considered when the bucket path is determined: bucket volume (soil capacity in a bucket), reachability (backhoe structure limitation), time efficiency, and soil property. Among them, the soil property is hardly quantified due to the complexity of its mechanical...
A major concern for robotic guidance systems is that a temporary or permanent failure of a given sensor within the system will erroneously trigger a potential system failure state. This paper introduces a generalised artificial neural system which is capable of addressing such problems by means of the inclusion of a weight value able to incorporate a distinct failure value. This will serve to significantly...
In this paper, the Bees algorithm was used to train multi-layer perceptron neural networks to model the inverse kinematics of an articulated robot manipulator arm. The Bees Algorithm is a recently developed parameter optimisation algorithm that is inspired by the foraging behaviour of honey bees. The Bees Algorithm performs a kind of exploitative neighbourhood search combined with random explorative...
In this paper we described a sound-source localization (SSL) system which can be applied to mobile robot and automatic control systems. A novel approach of using artificial neural network was proposed to obtain the horizontal direction angle (azimuth) of the sound source. According to humanoid characteristic only two microphones, which were attached symmetrically on both sides of the robot as its...
Semantic scene classification, robotic state recognition, and many other real-world applications involve multi-label classification with imbalanced data. In this paper, we address these problems by using an enrichment process in neural net training. The enrichment process can manage the imbalanced data and train the neural net with high classification accuracy. Experimental results on a robotic arm...
Shape recognition is an important part of machine intelligence in both decision making and data processing. A good shape representation in shape recognition should describe the shape in the way that makes it distinguishable from other shapes and be invariant to transform of position, size, angle and skew. More importantly, developing and finding appropriate shape representation are still a challenging...
This paper presents two approaches to surface roughness discrimination based on the use of a sensitive whisker system together with frequency spectrum analysis and neural networks classification methods. The key characteristic of the proposed methods is their ability to provide real-time feature classifications to help roboticspsila agents to scan their environmentpsilas properties such as objectpsilas...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.