BotSpot Categories Knowledge Bots  (Page 3) Research on Software Agents Research of Software Agents by the Artificial Intelligence Laboratory of the Department of Computer Science of the Vrije University, Brussels, Belgium includes many excellent on going projects with their goal to develop agent architectures that operate on the Internet and use Mosaic-like interfaces. Projects include MAGICA, GEOMED, CONSTRUCT, SACEA, NMS and ECRAN TOTAL. They are also working on specific examples of intelligent software agents for flexible presentation of information, navigation through large amounts of distributed information sources on the WWW, follow up and support for administrative procedures, and negotiations. Resource Discovery Unit The Resource Discovery Unit (RDU) is a project from the Research Data Network CRC and is operated by the DSTC. The RDU aims to investigate and develop tools, technologies, and information management processes that will allow organizations to locate, access, retrieve, and manage information on highly distributed heterogeneous networks. Soar Project The Soar project is a long term, multi-disciplinary, multi-site attempt at building, understanding, and applying an integrated model of intelligent behavior that can serve both as a useful AI system and as an unified theory of human cognition. At the University of Southern California, the Soar project is joint between the Information Sciences Institute (ISI) and the Computer Science Department. The site hosts the current projects and participants. TACOMA Project The TACOMA (Tromso And COrnell Moving Agents) Project focuses on operating system support for agents and how agents can be used to solve problems traditionally addressed by operating systems. They have completed a series of TACOMA distributed systems where agents can be moved about in the Internet. Source code for three TACOMA versions can be obtained through these pages. The Agent Building Shell: Programming Cooperative Enterprise Agents A dynamic agent building project from the Enterprise Integration Laboratory of the University of Toronto with a TOC covering Introduction, Architecture of the Agent Building Shell, Coordination, Integrating the Supply Chain and Finding Out More About this Project including Thesis, Publications, Presentations, System Documentation and Screen Dumps and Traces of the System in action. The Experimental Knowledge Systems Laboratory The Experimental Knowledge Systems Laboratory (EKSL) is part of the Department of Computer Science at the University of Massachusetts and seeks to understand the requirements of autonomous agents operating in complex, real-world environments, and to develop a science of agent design grounded in this understanding. The Frankfurt Mobile Agents Infrastructure The Frankfurt Mobile Agents Infrastructure (ffMAIN) implements an infrastructure for mobile agents which provide for agent mobility across heterogeneous networks as well as communications among agents. It supports agents written using diverse languages and lets agent programmers implement a variety of interaction schemes based on a basic, but general communication mechanism. The Sim_Agent Toolkit The Sim_Agent toolkit was developed within the Cognition and Affect project at the University of Birmingham. The ftp repository for the project includes papers reporting on theoretical work and preliminary designs. UM-PRS UM-PRS (University of Michigan's implementation of the Procedural Reasoning System) is composed of four components: a database representing the current world model, a library of plans called Knowledge Areas (KAs), a primitive function library and primitive function interface for performing low-level functions, and an intention structure that maintains the runtime state of the set of currently active goals. URL - The InfoBot URL - The InfoBot is a perl script that runs under SIRC as well as MACPERL and MACSirc. What makes URL - the InfoBot different from a Lycos is that it learns by observing and that you can query it in intuitive ways. Virtual Environments for Training The Virtual Environments for Training (VET) project is a collaboration with Lockheed AI Center and USC Behavioral Technologies Lab developing training systems which integrate virtual reality and intelligent tutoring technologies. The site also has an excellent area of relevant publications. USC/ISI is developing a pedagogical agent called Steve (Soar Training Experts for Virtual Environments) that supports the learning process. Steve agents can demonstrate skills to students, answer student questions, watch the student as they perform the tasks, and give advice if the students run into difficulties. Virtual Secretary Project The motivation of the Virtual Secretary (ViSe) Project is to construct user-model-based intelligent software agents, which could in most cases replace human secretarial tasks, based on modern mobile computing and computer network. The project includes two diferent phases: the first phase (ViSe1) focuses on using informatin filtering and process migration, its goal is to create a secure environment for software agents using the concept of user models; the second phase (ViSe2) concentrates on agents' intelligence and efficient cooperation in a distributed environment, its goal is to construct cooperative agents for achieving high intelligence. The VeSe1 agents focus on three secretarial tasks: local information filtering (email, news and diary), global inforation filtering (file retrieval and WWW), and user environment personification. WebLS WebLS (pronounced webbles) is a system that can dispense advice, analyze circumstances, diagnose problems, recommend configurations and similar tasks. Some applications include provide advice on consumer issues such as pets, health, gardening, foods, lifestyle, home repair, relationships, etc; Advise site visitors on what resources would be most appropriate based on the visitor's background and interests; Answer commonly asked tech support questions; and Diagnose equipment malfunctions and recommend repairs. WebWatcher WebWatcher Project is a "tour guide" agent for the world wide web. Once you tell it what kind of information you seek, it accompanies you from page to page as you browse the web, highlighting hyperlinks that it believes will be of interest. Its strategy for giving advice is learned from feedback from earlier tours. World Wide Knowledge Base Project The goal of CMU's World Wide Knowledge Base Project is to develop a probabilistic, symbolic knowledge base that mirrors the content of the World Wide Web. If successful, this will make text information on the web available in computer-understandable form, enabling much more sophisticated information retrieval and problem solving. 1    2     3    4