This paper presents the comparison of two approaches based on artificial intelligence techniques solving the task of on-line recognition of metabolic state of baker's yeast culture in a fed-batch cultivation. The ...
详细信息
Guidance through waypoinis is common for small autonomous marine vehicles. Guidance by the line of sight, which turns the vehicle directly towards the next waypoint without any reference path calculation, is computati...
详细信息
Guidance through waypoinis is common for small autonomous marine vehicles. Guidance by the line of sight, which turns the vehicle directly towards the next waypoint without any reference path calculation, is computationally the simplest form of waypoint guidance. However, the basic algorithm gives rather poor guidance due to the missed waypoint problem, lack of sea current compensation and abrupt transitions between the consecutive waypoinis. Significant path deviations and even deadlocks are possible due to these problems. Therefore, more complex algorithms are usually used in real world applications. The research reported in this paper aims to demonstrate that significant improvements of the basic line-of-sight guidance algorithm can be achieved by several intuitive, simple corrections and additions. The simplicity of the basic line-of-sight guidance algorithm is not compromised. In particular, missed waypoint detection is performed by monitoring the distance between the vehicle and the waypoint. Introduced reference heading corrections are based upon the location of the next waypoint after the one the vehicle is currently approaching, and upon the sea current direction and intensity. The results of these corrections are shown in several simulation examples. In addition, the paper includes a short discussion about the lineof-sight guidance in the diving plane. Copyright 2004 IFAC.
Guidance through waypoints is common for small autonomous marine vehicles. Guidance by the line of sight, the basic waypoint guidance algorithm, is very simple, computationally inexpensive, and flexible to sudden chan...
详细信息
Guidance through waypoints is common for small autonomous marine vehicles. Guidance by the line of sight, the basic waypoint guidance algorithm, is very simple, computationally inexpensive, and flexible to sudden changes in the desired path specification. On the other side, the basic algorithm achieves unoptimal vehicle trajectory, ignores possible side disturbances as sea currents, and can even lead to deadlock situations. Therefore it should be improved to use in the real world applications. This paper introduces several such improvements: missed waypoint detection to prevent deadlocks, novel reference heading correction method to give smoother vehicle path in turns at waypoints, and sea current compensation method to cancel its influence. This improvements address the mentioned flaws of the basic algorithm, as is demonstrated by the simulations, and yet keep it simpler than is the case for the most used waypoint-derived guidance methods.
A class of sparse regularization functions is considered for the developing sparse classifiers for determining facial gender. The sparse classification method aims to both select the most important features and maximi...
详细信息
A class of sparse regularization functions is considered for the developing sparse classifiers for determining facial gender. The sparse classification method aims to both select the most important features and maximize the classification margin, in a manner similar to support vector machines. An efficient process for directly calculating the complete set of optimal, sparse classifiers is developed. A single classification hyper-plane, which maximizes posterior probability of describing training data, is then efficiently selected. The classifier is tested on a Japanese gender-divided ensemble, described via a collection of appearance models. Performance is comparable with a linear SVM, and allows effective manipulation of apparent gender.
Feature and structure selection is an important part of many classification problems, in previous papers, an approach called basis pursuit classification has been proposed which poses feature selection as a regulariza...
详细信息
Feature and structure selection is an important part of many classification problems, in previous papers, an approach called basis pursuit classification has been proposed which poses feature selection as a regularization problem using a 1-norm to measure parameter complexity. In addition, a complete optimal parameter set, here called the locus, can be calculated which contains every optimal collection of sparse features as a function of the regularization parameter. This paper considers how to iteratively calculate the parameter locus using a set of rank-1 inverse matrix updates. The algorithm is tested on both artificial and real data and it is shown that the computational cost is reduced from a cubed to a squared problem in the number of features.
In most applications, a mobile robot must be able to determine its position and orientation in the environment using only own sensors. The problem of pose tracking can be seen as a constituent part of the more general...
详细信息
In most applications, a mobile robot must be able to determine its position and orientation in the environment using only own sensors. The problem of pose tracking can be seen as a constituent part of the more general navigation problem. Our proposed approach is able to track the mobile robot pose without environment model. It is based on combining histograms and Hough transform (HHT). While histograms for position tracking (x and y histograms) are extracted directly from local occupancy grid maps, angle histogram is obtained indirectly via Hough transformation combined with a non-iterative algorithm for determination of end points and length of straight-line parts contained in obtained histograms. Histograms obtained at the actual mobile robot pose are compared to histograms saved at previous mobile robot poses to compute position displacement and orientation correction. Orientation estimation accuracy greatly influences the position estimation accuracy and is crucial for a reliable mobile robot pose tracking. Sensors used for local occupancy grid generation are sonars but other exteroceptive sensors like a laser range finder can also be used. Test results with mobile robot Pioneer 2DX simulator show the capacity of this method.
This paper presents the comparison of two approaches based on artificial intelligence techniques solving the task of on-line recognition of metabolic state of baker's yeast culture in a fed-batch cultivation. The ...
详细信息
This paper presents the comparison of two approaches based on artificial intelligence techniques solving the task of on-line recognition of metabolic state of baker's yeast culture in a fed-batch cultivation. The first approach iS represented by a knowledge-based system containing expert knowledge in the form of production rules. The other approach is based on the application of the fuzzy neural network paradigm enabling the automatic extraction of the recognition rules from. experimental data. Performance of both approaches is discussed using results obtamed from tests on experimental data from a laboratory cultivation unit.
Electronic throttle body (ETB) is a car device that regulates air inflow into the motor's combustion system. Its performance has a major impact on the quality of the overall engine speed control. However, due to t...
详细信息
Electronic throttle body (ETB) is a car device that regulates air inflow into the motor's combustion system. Its performance has a major impact on the quality of the overall engine speed control. However, due to the usage of cheap components and some design features the ETB exhibits several nonlinear phenomena. This nonlinear behavior and the fact that there is only one measurement available - low quality measurement of the throttle position makes a design of the throttle controller a challenging task. Our approach is to model the ETB as a discrete time piecewise affine (PWA) system and apply model predictive control (MPC) strategy to design an explicit state feedback control law. Since MPC is a full-state controller and there is only one measurement available the rest of the states have to be estimated. We have chosen unscented Kalman filter (UKF) for the estimation purpose since it was performing the best in the presence of strong, almost discontinuous, process nonlinearities. In the end, MPC and UKF algorithm were implemented and tested on the real electronic throttle for the case of set-point reference. Experimental results indicate that the performance of cheaply produced components can be significantly improved with a good control strategy.
Over the past two years ExxonMobil Research and engineering group, along with Emerson Process Management, have tested the self-diagnostic capabilities of pressure transmitters with FOUNDATION FIELDBUS (FF) capability ...
详细信息
Over the past two years ExxonMobil Research and engineering group, along with Emerson Process Management, have tested the self-diagnostic capabilities of pressure transmitters with FOUNDATION FIELDBUS (FF) capability while installed on a fluid catalytic cracking (FCC) unit in an operating refinery. This project involved conducting a series of tests on the ability of the devices to diagnose plugged impulse lines.
Guidance through waypoints is common for small autonomous marine vehicles. Guidance by the line of sight, which turns the vehicle directly towards the next waypoint without any reference path calculation, is computati...
详细信息
Guidance through waypoints is common for small autonomous marine vehicles. Guidance by the line of sight, which turns the vehicle directly towards the next waypoint without any reference path calculation, is computationally the simplest form of waypoint guidance. However, the basic algorithm gives rather poor guidance due to the missed waypoint problem, lack of sea current compensation and abrupt transitions between the consecutive waypoints. Significant path deviations and even deadlocks are possible due to these problems. Therefore, more complex algorithms are usually used in real world applications. The research reported in this paper aims to demonstrate that significant improvements of the basic line-of-sight guidance algorithm can be achieved by several intuitive, simple corrections and additions. The simplicity of the basic line-of-sight guidance algorithm is not compromised. In particular, missed waypoint detection is performed by monitoring the distance between the vehicle and the waypoint. Introduced reference heading corrections are based upon the location of the next waypoint after the one the vehicle is currently approaching, and upon the sea current direction and intensity. The results of these corrections are shown in several simulation examples. In addition, the paper includes a short discussion about the line-of-sight guidance in the diving plane.
暂无评论