This paper presents the design and implementation of a paralleldistributed control architecture for industrial multiple robot systems. The design methodology is based on a concept of discrete states and actions, and ...
详细信息
This paper presents the design and implementation of a paralleldistributed control architecture for industrial multiple robot systems. The design methodology is based on a concept of discrete states and actions, and a robotic task is represented as a sequence of primitive actions. For cooperative or exclusive tasks at the synchronous level of multiple robot systems, Petri net representation is applied, and discrete event-driven control is implemented as a data flow network of concurrent processes communicating with each other. Implementation of multiprocessing control on a microcomputer and a network of microcomputers is discussed.
For mobile robot navigation purposes, we use an object position measurement system. The measurement system is composed of two parts, a signal acquislion part and the signal procssing pari. The first part consists of t...
详细信息
The proceedings contain 88 papers. The topics discussed include: The design and implementation of a class manager in an object management system;load balance facility in distributed MINIX system;fault-tolerant mapping...
ISBN:
(纸本)0818664304
The proceedings contain 88 papers. The topics discussed include: The design and implementation of a class manager in an object management system;load balance facility in distributed MINIX system;fault-tolerant mapping onto VLSI/WSI processor arrays;computer assistance for a disabled user/operator to navigate a vehicle through a doorway;on the optimum recovery of distributed programs;a framework of classes for distributed controlling;simultaneous state encoding and communication cost optimization for FSM net design;a unified approach for FSM synthesis on FPGA architectures;a practical reconfiguration of a 2D massively parallel machine;non-linear optimization: artificial neural network solution techniques applied to the optimum linear feedback control of linear discrete-time dynamic systems;fault tolerant capability of multi-layer perceptron neural network;and synchronization issues of a customer premises networkbased on cell transmissions over fiber channel interfaces.
This paper presents a parallel memory-based parser called parallel, which is implemented on a marker-passing parallel AI computer called Semantic network Array Processor (SNAP). In the parallel memory-based parser, th...
详细信息
ISBN:
(纸本)081865550X
This paper presents a parallel memory-based parser called parallel, which is implemented on a marker-passing parallel AI computer called Semantic network Array Processor (SNAP). In the parallel memory-based parser, the parallelism in natural language processing is utilized by a memory search model of parsing. Linguistic information is stored as phrasal patterns in a semantic network knowledge base that is distributed over the memory of the parallel computer. Parsing is performed by recognizing and linking linguistic patterns that reflect a sentence interpretation. This is achieved via propagating markers over the distributednetwork. We have developed a system capable of processing newswire articles about terrorism domain with a large knowledge base of 12,000 semantic network nodes. The paper presents the structure of the system, the memory-based parsing method used and performance results obtained.
This paper presents a design methodology for developing efficient distributed-memory parallel programs for block-recursive algorithms such as the fast Fourier transform and bitonic sort. This design methodology is spe...
详细信息
This paper presents a design methodology for developing efficient distributed-memory parallel programs for block-recursive algorithms such as the fast Fourier transform and bitonic sort. This design methodology is specifically suited for most modern supercomputers having a distributed-memory architecture with circuit-switched or wormhole routed mesh or hypercube interconnection network. A mathematical framework based on the tensor product and other matrix operations is used for representing algorithms. Communication-efficient implementations with effectively overlapped computation and communication are achieved by manipulating the mathematical representation using the tensor algebra. Performance results for FFT programs on the Intel iPSC/860 and Intel Paragon are presented.
This paper presents a new approach to the hyper-distributed hyper-parallel implementation of the artificial intelligent (AI) heuristic algorithms for real-time searching, matching and planning. By using the competitiv...
详细信息
This paper presents a new approach to the hyper-distributed hyper-parallel implementation of the artificial intelligent (AI) heuristic algorithms for real-time searching, matching and planning. By using the competitive activation mechanism of dynamically clustering neural networks, the concurrent propagations and competitions of concurrent autowaves yielded by distributedparallel heuristic AI algorithms for searching any implicit AND/OR graph are realized. Compared with the AI approaches based on the conventional sequential symbolic logic and the conventional neural networks, the approach of this paper has many advantages in many respects, such as high processing speed, always successful obtainment of the optimal solution, local connections between cells, easy utilization of heuristic knowledge, and feasibility of the VLSI implementation.
Locating and accessing information in a large distributed system is a difficult problem of growing importance. This paper reports on our experience building and using a prototype system for transparent, user-guided as...
详细信息
Locating and accessing information in a large distributed system is a difficult problem of growing importance. This paper reports on our experience building and using a prototype system for transparent, user-guided associative access to the contents of a large, distributed set of WAIS servers. Our system is based on content routing, an architecture that makes use of content labels for locating and accessing information in large distributed systems [12]. Our content router for WAIS servers is implemented as a Semantic File System that constructs content labels from WAIS source and catalog files. The content router guides locating documents by suggesting terms that frequently appear with a given query term in document headlines. Sufficiently narrowed queries are routed to WAIS servers and processed in parallel. We have successfully used our content router to locate documents on a large number of WAIS servers. Along with demonstrating the feasibility of distributed finding in a large network of information servers, the prototype shows interactive performance limited primarily by the processing time at WAIS servers.
The objective of this paper is the description of WAVE model and language for highly parallelprocessing in open computer networks, as well as an efficient distributed implementation of the language. The WAVE language...
详细信息
This paper presents design consideration, machine architecture, and parallel programming environment for the parallel machine Cenju-3, the first MPP product of NEC. Cenju-3 utilized fast commodity RISC microprocessors...
详细信息
ISBN:
(纸本)0818656026
This paper presents design consideration, machine architecture, and parallel programming environment for the parallel machine Cenju-3, the first MPP product of NEC. Cenju-3 utilized fast commodity RISC microprocessors, VR4400s in a distributed shared-memory arrangement and can be configured up to 255 processing elements, connected through a multi-stage inter-connection network. It results a compact and scalable parallel machine, with operating speeds ranging from 255 MFLOPS to a maximum of 12.8GFLOPS. A hardware support for interprocessor communication realizes efficient message/data transmissions among processors. Also, a programming-environment, PCASE has being developed, in order to fully utilize the Cenju-3-PCASE translates a sequential user program into its efficient parallel form with minimum user intervention. Preliminary results and future direction are also described.
暂无评论