Software Agent -applications-. Outline Overview of agent applications Agent applications –Interface agents –IBM Aglets –AgentSpace –The Open Agent Architecture.

Software Agent-applications-

Outline

• Overview of agent applications

• Agent applications– Interface agents– IBM Aglets– AgentSpace– The Open Agent Architecture– Etc.

• Some cases– Massive– RETSINA

• Summary

• Discussion

2/34

Overview of Agent Applications

• Where are agents used?– Robotics– On the web– Movie and game production– Scientific simulations– Defense applications– Distributed computing (e.g. XGrid)– Mobile applications

• Why are agents useful?– Software engineering.

• Modularity, abstraction, complexity, management, etc.– Match many problem domains– Good surrogates for humans– Cognitive and social models– Provide intelligent behavior

• Where artificial intelligence and software engineering meet

3/34

Agent Applications

1. Automated Office2. Unified Messaging3. Multimodal Maps4. CommandTalk5. ATIS-Web6. Spoken Dialog Summarization7. Agent Development

Tools8. InfoBroker9. Rental Finder10. InfoWiz Kiosk11. Multi-Robot Control12. MVIEWS Video Tools13. MARVEL 14. SOLVIT15. Surgical Training16. Instant Collaboration17.Crisis Response18. WebGrader19. Speech Translation20-25+ ...

4/34

Interface Agents

User

User'sAgent

OtherAgentAsking

Interacts with

Application

User feedback &programming by example

Observes &imitates

Communication

Interacts with

User

User'sAgent

OtherAgentAsking

Interacts with

Application

User feedback &programming by example

Observes &imitates

Communication

Interacts with

Agent Role Source

Letizia WWW guide Liebermann (1995)

Remembrance Agent memory aid Rhodes & Starner (1996)

NewT UseNet news filter Sheth & Maes (1993)

Yenta matchmaking andreferrals

Foner (1996)

Kasbah buy and sell items onthe WWW

Chavez & Maes (1996)

Ringo/HOMR entertainment selection Shardanand & Maes (1995)

Calender Apprentice(CAP)

schedule meetings Dent et al. (1992)

Agent Role Source

Letizia WWW guide Liebermann (1995)

Remembrance Agent memory aid Rhodes & Starner (1996)

NewT UseNet news filter Sheth & Maes (1993)

Yenta matchmaking andreferrals

Foner (1996)

Kasbah buy and sell items onthe WWW

Chavez & Maes (1996)

Ringo/HOMR entertainment selection Shardanand & Maes (1995)

Calender Apprentice(CAP)

schedule meetings Dent et al. (1992)

5/34

IBM Aglets: Overview

• System description :– Aglets for Agile Applets are Java mobile objects– The Aglets architecture consists of two APIs and two implementation layers

• Aglet API – Aglets Runtime Layer - The implementation of Aglet API – Agent Transport and Communication Interface (ATCI with ATP as an application-

level protocol)– Transport layer

6/34

IBM Aglets: Applications

• The Tabican software for finding a package tour or flight ticket

• Electronic commerce

7/34

AgentSpace (Ichiro Sato)

• System description :– AgentSpace is a Java-based middleware

for distributed environments– It runs on the Windows (9X, NT), MacO8,

Solaris 2.5, Linux

• Language : The system and related agents are written in Java

• Agent mobility

8/34

AgentSpace (Ichiro Sato): Applications

• Clock

• Mail service

• Paint tool

• Text editor

• Chat Tool

9/34

The Open Agent Architecture

• Agent System description:– OAA is a framework for integrating a community of heterogeneous software agents

in a distributed environment.

• Agents communication: multimodal cooperation and interactions

• OAA agent libraries exist for the following languages and platforms:

Quintus Prolog SunOs 4.1.3, Solaris 2.5+, Windows 95

ANSI C (Unix, Microsoft, Borland) SunOs 4.1.3, Solaris 2.5+, SGI IRIX, Windows 95

Common Lisp (Allegro & Lucid) SunOs 4.1.3, Solaris 2.5+

Java Any Java platform

Borland Delphi Windows 3.1, Windows 95

Visual Basic Windows 3.1, Windows 95

10/34

The Open Agent Architecture: Applications (1)

Wizard Info.

Automated office

Multi robot control

Speech recognitionover the web

11/34

The Open Agent Architecture: Applications (2)

Multimodal maps

Agent Development Tools

12/34

Interfacing Agents

• Talking heads– Naturalistic figures– Many possible platforms:

• Web, mobile device, set-top box– Applications

• News reading, signing, interactive digital TV programme guide• Electronic Virtual Assistants in e-commerce

• Vandrea– Thin client solution, that reads news scripts live from ITN

13/34

Microsoft Agent

• Components– Toolbox of technologies

• Speech rec, text-to-speech– Scripting language

• Controls animation at high-level• Good but rigid

– Pre-designed characters• Rather cutesy, but you can create your own

– Only viewable with Active X

• Microsoft Persona Project– The project is developing the technologies required to produce conversational as-

sistants - lifelike animated characters that interact with a user in a natural spoken dialogue

– The work is built upon the Whisper speaker-independent continuous speech recog-nition system and a broad coverage English understanding system, both also de-veloped at Microsoft Research

14/34

Web Search

15/34

Recommendation

16/34

Work Assistant

17/34

Agents in Defense

• Used to represent human military operators

– Fighter Pilots (enemy and friendly), commanders, sensor operators etc

• Training

• Human factors research

• Military operations research

18/34

Operations Research and Military Simulation

• Provide advice to the ADF– Influence $billion decisions– Impact on tactical decisions in actual operations

• Highly sophisticated systems

• Expensive/dangerous to operate

• Unknown/uncertain futures

• So we tend to work in virtual spaces – simulation– Purposes

• Tactics development and experimentation• Acquisitions

– Style• Heavyweight, BDI, usually less than 32• Not neural net, learning, or agent based distillation

19/34

F/A-18 Hornet Tactics

• Needed to develop tactics for use with RAAF F/A-18 Hornets, espe-cially with new weapons

• Client was F/A-18 squadrons (esp. 2 OCU)

• 2 OCU – Hornet pilot training, and FCI Course– FCI = Fighter Combat Instructor

• FCI is Australian equivalent of TOP GUN• Contributed to Australian Hornet TACMAN

20/34

RETSINA Agent Architecture

• Reusable Environment for Task-Structured Intelligent Networked Agents

• Four parallel threads:– Communicator for conversing with

other agents– Planner matches “sensory” input

and “beliefs” to possible plan actions– Scheduler schedules “enabled”

plans for execution– Execution Monitor executes sched-

uled plan & swaps-out plans for those with higher priorities http://www.cs.cmu.edu/~softagents/retsina.html

21/34

RETSINA Functional Architecture

User 1 User 2 User u

InfoSource 1

InfoSource 1

Interface Agent 1Interface Agent 1 Interface Agent 2Interface Agent 2 Interface Agent iInterface Agent i

Task Agent 1Task Agent 1 Task Agent 2Task Agent 2 Task Agent tTask Agent t

Middle Agent 2Middle Agent 2

Information Agent n

Information Agent n

InfoSource 2

InfoSource 2

InfoSource m

InfoSource m

Goal and TaskSpecifications Results

SolutionsTasks

Info & ServiceRequests

Information IntegrationConflict Resolution Replies

AdvertisementsInformation

Agent 1

Information Agent 1

Queries

Answers

22/34

Agent Description

• Interface Agents– Solicit input from user for the agent system– Present output to the user– Frequently part of task agent– Often representative of a device

• Task Agents– Know what to do and how to do it– Responsible for task delegation– May enlist the help of other task agents

• Middle Agents– Infrastructure agents that aid in MAS scalability– Many have been identified in Sycara & Wong ‘00– Most common:

• Agent Name Service (White Pages)• Matchmaker (Yellow Pages)• Broker• MAS Interoperator

RETSINA

23/34

Application: ModSAF

• Modular Semi- Automated Forces

• “Real world” events are simulated in Agent Storm by interaction with ModSAF

• minefield discovery• encountering Threat platoon• announcements of passed check-

points

• RETSINA Mission Agents control ModSAF platoon.

• route directions• marching orders

RETSINA

24/34

Application: RETSINA De-mining SystemRETSINA

http://www.cs.cmu.edu/~softagents/demining.html

Without Team-Aware Coordination With Team-Aware Coordination

• Using simple homogenous strategy• Robots interfere with each other• Robots attempt to de-mine same mine

• Using simple homogenous strategy and rule that they cannot diffuse the same mine• Robots do not interfere with each other• A path is more rapidly cleared

25/34

Application: MORSERETSINA

26/34

Application: RCAL

• RETSINA Calendar Agent and Electronic Secretary

RETSINA

27/34

Application: MokSAFRETSINA

Alpha’s Shared Route

Charlie’s Shared Route

Information about shared routes…

Bravo’s Shared Route.

Note that this route initially support’s Charlie’s route, then crosses to intercept Alpha’s route.

28/34

Application: PalmSAF

• Miniaturized form of MokSAF for hand-held computers

• Full RETSINA multi-agent system available to PalmSAF user

• Technical challenges:– little memory– very few communication ports– intermittent communication connections

RETSINA

29/34

Game AI, Bots and Agents

30/34

Nintendogs

31/34

Massive (www.massivesoftware.com)

32/34

Summary

• (Etzioni & Weld, 1995) identify the following specific types of agent that are likely to appear soon:

– Tour guides: The idea here is to have agents that help to answer the question ‘where do I go next’ when browsing the WWW. Such agents can learn about the user’s preferences in the same way that MAXIMS does, and rather than just provid-ing a single, uniform type of hyperlink actually indicate the likely interest of a link.

– Indexing agents: Indexing agents will provide an extra layer of abstraction on top of the services provided by search/indexing agents such as LYCOS and InfoSeek. The idea is to use the raw information provided by such engines, together with knowledge of the users goals, preferences, etc., to provide a personalized service.

– FAQ-finders: The idea here is to direct users to FAQ documents in order to answer specific questions. Since FAQS tend to be knowledge intensive, structured docu-ments, there is a lot of potential for automated FAQ servers.

– Expertise finders: Suppose I want to know about people interested in temporal be-lief logics. Current WWW search tools would simply take the 3 words ‘temporal’, ‘belief’, ‘logic’, and search on them. This is not ideal: LYCOS has no model of what you mean by this search, or what you really want. Expertise finders ‘try to under-stand the users wants and the contents of information services’, in order to provide a better information provision service.

33/34

Discussion on Apple’s Knowledge Navigator

• Hardware platform?

• Intelligent functions?

• Present vs. future?

• Proposal topics for discussion– 김용준 : 사용자의 명령을 인식하고 의도를 파악한 후에 실제로 그 의도를 어떤 식으로 수행하고 필요한 기술은 무엇일까

– 최봉환 : 사용자의 의도를 어떻게 인식하는가 – 이승현

• 사용자로부터의 불충분한 정보를 바탕으로 무언가를 어떻게 효율적으로 검색해서 사용자가 원하는 결과를 내주는가

• 웹 페이지 연결에 있어서  URL을 통한 것이 아니라  "학교 홈페이지 " 등  기능이나 이름을 통한 연결

– 노홍찬 : 어떻게 에이젼트가 사용자의 성향에 대해 학습할 수 있는가

34/34

주요 기능

• 일정관리• 문서 검색 및 관리• 정보추천• 상황인식 (시각 /청각 )• 전화연결 /자동응답• 문맥관리• 대화기능 (음성인식 /대화관리 /음성합성 )• 아바타 관리

35/34

입력 인간기능 통합모델 출력

행위

서비스

시각

청각

온도

습도

Etc.

사용자 질의 사용자 응답

학습판단

계획

추론

모델링

대화기능

행동기능상황인식

지식관리