In this paper we present a computational approach for extracting three-dimensional structure of controllable resolution, depth of field, and accuracy, all made available at real-time speeds, This approach utilizes the...
详细信息
In this paper we present a computational approach for extracting three-dimensional structure of controllable resolution, depth of field, and accuracy, all made available at real-time speeds, This approach utilizes the spatial and the temporal gradients of the streams of images acquired using an actively controlled camera, Depending on the requirements of a particular task, appropriate parameters such as disparity value sought, interframe camera displacement, and number of frames in a stream are chosen to control the resolution, depth of field, and accuracy, The acquisition and processing of the image stream are done in real time on a pipeline architecture based processor. Extensive experiments are presented to demonstrate the system's accuracy, controllability of depth of field and resolution, and ability to perform successfully in a variety of scenes. The system operated with no latency between image acquisition and processing. The total acquisition and processing time in these experiments is in the range from 0.27 to 1.56 s. The depth results have an accuracy of 85% to 92%. (C) 1996 Academic Press, Inc.
作者：
Bonitz, RGHsia, TCSystems
Controland Robotics LaboratoryDepartment of Electrical and Computer Engineering University of California Davis CA USA
An internal force-based impedance control scheme for cooperating manipulators is introduced which controls the motion of the objects being manipulated and the internal force on the objects. The controller enforces a r...
详细信息
An internal force-based impedance control scheme for cooperating manipulators is introduced which controls the motion of the objects being manipulated and the internal force on the objects. The controller enforces a relationship between the velocity of each manipulator and the internal force on the manipulated objects. Each manipulator is directly given the properties of an impedance by the controller;thus, eliminating the gain limitation inherent in the structure of previously proposed schemes. The controller uses the forces sensed at the robot end effecters to compensate for the effects of the objects' dynamics and to compute the internal force using only kinematic relationships. Thus, knowledge of the objects' dynamics is not required. Stability of the system is proven using Lyapunov theory and simulation results are presented validating the proposed concepts. The effect of computational delays in digital control implementations is analyzed vis-a-vis stability and a lower bound derived on the size of the desired manipulator inertia relative to the actual manipulator endpoint inertia. The bound is independent of the sample time.
This paper presents an Expert Data Rejection (EDR) system, developed to accompany a real-time data acquisition tool for industrial plants. The EDR system is an integrated software tool responsible for the first stage ...
详细信息
This paper presents an Expert Data Rejection (EDR) system, developed to accompany a real-time data acquisition tool for industrial plants. The EDR system is an integrated software tool responsible for the first stage process of multiple raw measurements coming from the plant. It provides different algorithms, which operate in real time, recognizing faulty patterns according to the user requirements. For each specific measurement the user may define a different way of treatment. The system checks the signal values and filters the incoming data. Various adaptive techniques have been adopted, such as digital filtering and variations of the recursive least-squares algorithm, as well as the neural network based algorithms. The system was applied and tested in a subprocess of a refinery plant in Athens. The EDR system removes the measurement noise and provides reliable data for further processing. It also gives information about the existence of faulty instruments monitoring the operation of the industrial process.
Neural networks or connectionist models are massively parallel interconnections of simple neurons that work as a collective system, can emulate human performance and provide high computation rates. On the other hand, ...
详细信息
Neural networks or connectionist models are massively parallel interconnections of simple neurons that work as a collective system, can emulate human performance and provide high computation rates. On the other hand, fuzzy systems are capable to model uncertain or ambiguous situations that are so often encountered in real life. One way for implementing fuzzy systems is through utilizations of the expert system architecture. Recently, many attempts have been made to ''fuse'' fuzzy systems and neural nets in order to achieve better performance in reasoning and decision making processes. The systems that result from such a fusion are called neuro-fuzzy inference systems and possess combined features. The purpose of the present paper is to propose such a neuro-fuzzy system by extending and improving the system of Keller et al. (1992). The present system makes use of Hamacher's fuzzy intersection function and Sugeno's complement function. After a brief outline of the operation of the system its features are established with the aid of four theorems which are fully proved. The capabilities of the system are shown by a set of simulation results derived for the case of trapezoidal fuzzy sets. These results are shown to be better than the ones obtained with the original neuro-fuzzy system of Keller et al.
This paper presents and investigates a neural network structure which can perform general fuzzy inference. This system consists of a number of parallel neural network units which are called ''flexible inferenc...
详细信息
This paper presents and investigates a neural network structure which can perform general fuzzy inference. This system consists of a number of parallel neural network units which are called ''flexible inference cells'' (FICs). Each FIC implements a single-input/single-output (SISO) IF-THEN rule of a fuzzy knowledge base. The assumption of SISO fuzzy rules allows the implementation of any complex fuzzy inference algorithm (for control or other decision making purposes), since any MIMO (multi-input/multi-output) rule can be decomposed into an equivalent set of MISO (multi-input/single-output) rules, and a MISO rule can be decomposed to a set of SISO rules. The paper discusses the assumptions and requirements for the proposed neurofuzzy structure, and classifies the FICs into four categories. Some results derived by simulation using 3125 exemplar patterns produced computationally are provided.
A new technique to recognise 3D free-form objects via registration is proposed. This technique attempts to register a free-form surface, represented by a set of 2 1/2D sensed data points, to the model surface, represe...
详细信息
A new technique to recognise 3D free-form objects via registration is proposed. This technique attempts to register a free-form surface, represented by a set of 2 1/2D sensed data points, to the model surface, represented by another set of 2 1/2D model data points, without prior knowledge of correspondence or vie;tv points between the two point sets. With an initial assumption that the sensed surface be part of a more complete model surface, the algorithm begins by selecting three dispersed, reliable points on the sensed surface. To find the three corresponding model points, the method uses the principal curvatures and the Darboux frames to restrict the search over the model space. Invariably, many possible model 3-tuples will be found. For each hypothesized model 3-tuple, the transformation to match the sensed 3-tuple to the model 3 tuple can be determined. A heuristic search is proposed to single out the optimal transformation in low order time. For realistic object recognition or registration, where the two range images are often extracted from different view points of the model, the earlier assumption that the sensed surface be part of a more complete model surface cannot be relied on. With this, the sensed 3-tuple must be chosen such that the three sensed points lie on the common region visible to both the sensed and model views. We propose an algorithm to select a minimal non-redundant set of 3-tuples such that at least one of the S-tuples will lie on the overlap. Applying the previous algorithm to each 3-tuple within this set, the optimal transformation can be determined. Experiments using data obtained from a range finder have indicated fast registration for relatively complex test cases. If the optimal registrations between the sensed data (candidate) and each of a set of model data are found, then, for 3D object recognition purposes, the minimal best fit error can be used as the decision rule.
The basic robot control technique is the model based computer-torque control which is known to suffer performance degradation due to model uncertainties. Adding a neural network (NN) controller in the control system i...
详细信息
The basic robot control technique is the model based computer-torque control which is known to suffer performance degradation due to model uncertainties. Adding a neural network (NN) controller in the control system is one effective way to compensate for the ill effects of these uncertainties. In this paper a systematic study of NN controller for a robot manipulator under a unified computed-torque control framework is presented. Both feedforward and feedback NN control schemes are studied and compared using a common back-propagation training algorithm. Effects on system performance for different choices of NN input types, hidden neurons, weight update rates, and initial weight values are also investigated. Extensive simulation studies for trajectory tracking are carried out and compared with other established robot control schemes.
This paper describes the analysis, modeling, and simulation of a notional air defense system using SMOOCHES (State Machines for Object-Oriented, Concurrent, Hierarchical engineering Specifications). SMOOCHES is an obj...
详细信息
This paper describes the analysis, modeling, and simulation of a notional air defense system using SMOOCHES (State Machines for Object-Oriented, Concurrent, Hierarchical engineering Specifications). SMOOCHES is an object-oriented environment based on hierarchical state machines and extensions to Statecharts, specifically developed as an environment to specify, model, simulate and analyze/evaluate distributed, reactive systems. Using a high level system specification language, an object-oriented, herarchical state specification of a radar tracking system with realistic constraints is derived. A graphical statechart representation of the tracking system behavior is also derived and implemented within the SMOOCHES environment.
A novel paradigm for the synthesis of convergent-axis stereo geometries is presented. This paradigm incorporates constraints that represent task-oriented properties that can be easily derived in many applications of s...
详细信息
暂无评论