Nazir A. Warsi

Cooperative assistance for remote robot supervision

This paper describes current work on the design of a computer system which provides cooperative assistance for the supervision of remote semi-autonomous robots. It consists of a blackboard-based framework which allows communication between the remote robot, the local human supervisor, and an intelligent mediating system, which aids interactive exception handling when the remote robot requires the assistance of the local operator.

A high-level computing algorithm for diverging and converging branch nonserial dynamic programming systems

Abstract We present high-level computing algorithms for efficiently processing the diverging and converging branch systems in nonserial dynamic programming. A special technique in devised for processing the network functions such that the minimum amount of storage is employed. It is shown that if k is the discretization level of the state and decision variables then the space complexities are O ( k ) and O ( k 2 ) for the diverging and converging branch systems, respectively. The resultant time complexities are also developed. These savings in computational complexities enhance the attractiveness of dynamic programming as a tool for processing more complex nonserial systems.

Multilevel Master-Slave Parallel Programming Models

We develop a multilevel master-slave (MMS) model that is useful for large-scale master-slave problems. The MMS model implements the MS model at multiple levels and allows parallel creation of slave processes. We describe an MMS structure called the minimum-generation-time (MGT) tree. The results of our experiments show that the MMS model improves the performance of parallel computation.

An Efficient Multilevel Master-slave Model ForDistributed Parallel Computation

The master-slave (MS) parallel computing model is one of the most widely used model in a networked computing environment due to its ease of implementation. This model, however, suffers from the disadvantages of the sequential generation of slave processes and heavy communication overheads imposed on the master processor. To overcome this problem, we present in this paper an efficient multilevel master-slave (MMS) scheme which is especially useful for solving decomposable large-scale problems such as structure mechanics or dynamics problems with rotational symmetry, on networked workstations. Our MMS model implements the MS model at multiple levels and generates processes using a special class of tree structures, allowing parallel creation of slave processes. It also improves performance in the distribution of initial data and merging of computed results to and from slave processes. We shall describe the generation of processes using different MMS structures to generate a prescribed number of processes and to broadcast global data to all processes. We then present the implementation of the optimal MMS model via PVM on a networked computer system consisting of workstations for a plate-bending problem that is discretized using the finite strip method The performance of our numerical experiments employing this MMS model is reported to demonstrate its efficiency. This scheme can be applied equally well to other types of problems that can be decomposed using the Fourier decomposition or circular decomposition, no matter whether the physical problem is discretized by the boundary element method or finite element method.

Knowledge-Based Image Enhancement for Cooperative Tele-Assistance

There is an increasing need in complex environments for computerized assistance, both for the effective filtering and display of pertinent information or data, and also for the decision-making task itself. The combination of artificial intelligence techniques with image processing and graphics capabilities provides the foundation for building intelligent systems which act as mediaries between the human and the task domain. In the filed of tele-assistance, this type of system enables cooperative problem-solving between a remote semi-autonomous robot and a local human supervisor, this paper describes current work on such a system, with an emphasis on the development of knowledge-based image enhancement capabilities. These allow the intelligent assistant to request particular images related to a failure state, and to automatically enhance those image in such a manner that the local supervisor may quickly and effectively make a decision.

A knowledge-based system for multiple pattern recognition paradigms support

This paper focuses on developing a knowledge-based system with multiple pattern recognition paradigms to support a variety of facilities for an intelligent pattern classifier design. Since re-developing a pattern recognition system to fulfill the new requirements can be quite expensive, our work has inspired with research in software re-engineering by treating the existing pattern recognition software as a valuable resource. The approach lies in extracting knowledge intended to be reused from original pattern recognition programs and replacing them with libraries containing pre-generated packages. We then integrate these transformed packages into a specific application.

A high level dynamic programming algorithm for processing nonserial looped systems

Nonserial dynamic programming networks involving feedforward and feedback loops are discussed. Efficient high level computing algorithms are developed for processing them in a manner resulting in the minimum computational drain on resources. Their complexity analyses are also presented. It is shown that the space complexity for each is O(k2) while their time complexity is O ((m + n)k3).