document7

Post on 28-Oct-2014

294 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

DESCRIPTION

 

TRANSCRIPT

Design IssuesDesign Issues

OutlineOutline

• Agent review

• Approaches to building applications

• Agent & interagent programming tips

• Incremental system development & evaluation

• Summary

22/20/20

What is an Agent?What is an Agent?

Mobile AgentsPrograms that move among computer hosts

Autonomous Agents Based on planning technologies

Learning AgentsUser preferences, collaborative filtering,...

Animated Interface AgentsAvatars, chatbots, ...

Simulation-based EntitiesData/Info finding, filtering and mergingCooperative Agents

Cooperation among distributed heterogeneous programmatic components

Voyager, Aglets, Odyssey

Robots, Softbots, BDI

Microsoft Agent, Julia

ModSAF, RoboCup

OAA, KQML, FIPA

FireFly, MIT Media Lab

SIMS, InfoSleuth, IR

33/20/20

Approaches to Building ApplicationsApproaches to Building Applications

MonolithicApplications

Object-Oriented Applications

Distributed ObjectApplications

OAAApplications

Dynamic addition

Objective

Suitable for Internet environment

Virtual community of dynamic services

Adaptable to changing, evolving network resources

Flexible interactions among components

44/20/20

Approaches to Distributed ComputingApproaches to Distributed Computing

• Mobile objects

• Blackboard architectures

• Agent communication languages (ACL)

• Publish & subscribe brokers

55/20/20

Mobile Objects (Agents)Mobile Objects (Agents)

• Objects move under their own power (e.g., Voyager, Aglets)

• Advantages– Network bandwidth for certain classes of problems– Parallelism - many objects can be spawned

• Disadvantages– Programmatically specify where to go and what to do, through a known interface– Little automated support for inter-object cooperation– Programming language specific (non-heterogeneous)

66/20/20

Blackboard ArchitecturesBlackboard Architectures

• Knowledge Sources read and write tuples from a common information space (e.g. LINDA, FLiPSiDE)

• Advantages– Eliminates explicitly programmed interactions among participants

• Disadvantages– KS cannot coordinate interactions– Polling

tuple(abc,1,2,3)

77/20/20

Publish & Subscribe BrokersPublish & Subscribe Brokers

• Clients register interest, broker routes/filters msgs

• Examples: Talarian SmartSockets, Active Software’s ActiveWeb, ACL Brokers

• Advantages– Destination process(es) not explicitly encoded– No polling

• Disadvantages– Simple filtering, unitary messages

Broker

88/20/20

Agent Communication LanguagesAgent Communication Languages

• Communication message types based on speech acts (e.g., ask, tell, deny) + conversational policies

• Examples: FIPA ACL, KQML

• Advantages– Rich interaction model, peer-to-peer based– Standardized message types, content-agnostic

• Disadvantages– Conformance to specs not universal– Explicitly coded interactions among participants

ANS, Service BrokerAsk

Reply

99/20/20

Comparison of Distributed ApproachesComparison of Distributed Approaches

Distributed Dist. Objects, Mobile Agents, ACL, Blackboards, Pub/Sub

Heterogeneous languages Distributed Objects,ACL, Blackboards

Non-coded interactions Blackboards, Pub/Sub

Parallel Services Blackboards

Compound Expressions (Mobile Agents)

Constraints No

1010/20/20

Agent & Interagent Programming TipsAgent & Interagent Programming Tips

• Choosing an agent Interface

• Information sharing strategies

• Domain-specific vs. domain-independent agents

• Adding speech & NL to interfaces

1111/20/20

Choosing an Agent InterfaceChoosing an Agent Interface

• Natural-language inspired interfaces– Imperative Verb, Direct Object, ParamList, (Result)– Parameter lists hold Adjs, Advs & Prepositions as well as extensible programmatic

instruction

• Classes tagged by type– inform(phone, ringing, Params)– send_message(MsgRef, Params) :-

memberchk(by(fax), Params)

• Succeed once with list vs. Multiple success– get(email, message_headers, +Params, -ListOfHeaders)– phone_number(Person, PhoneNum)

1212/20/20

Information Sharing Strategies (1)Information Sharing Strategies (1)

• Example: Phone dialer agent

• 1. Query– When an agent wants to know the status of the

phone, it asks the Facilitator who asks the phone agent

– pa: oaa_Declare(status(phone, S),[])– ?a: oaa_Solve(status(phone, S), [])

• 2. Post (Blackboard)– The phone agent writes its status to the Facilitator;

agents can query the facilitator for status, and install a trigger which proactively monitors changes to status

– pa: oaa_AddData(status(phone, busy), [])– ia: oaa_Solve(status(phone, S), []),

oaa_AddTrigger(data, status(phone,S), notify(Me, phone(S)), [on(change)])

1313/20/20

Information Sharing Strategies (2)Information Sharing Strategies (2)

• 3. Inform– Broadcast time-critical events to interested parties– ia: oaa_Declare(msg(phone, Msg), [])– pa: oaa_Solve(msg(phone, ringing, []), [inform])

1414/20/20

Domain-specific vs. Domain-independentDomain-specific vs. Domain-independent

• Move domain-dependent code into separate agent• Employ hooks and parameters to allow domain-specific tailoring of

functionality

• Always ask:Domain-specific or domain independent?

– Phone agent?– Office interface?– Notify agent?– Speech recognition?– Natural language?– Facilitator?

1515/20/20

Adding Speech & NLAdding Speech & NL

• User Interface responsible for:– accepting user input, sending requests, displaying results– controlling interactions of speech and NL

• Complex interpretation processed by external domain agent

1616/20/20

Incremental System Development & EvaluationIncremental System Development & Evaluation

• Collaborative Multimodal Map application adapted for Wizard Of Oz (WOZ) experiment to elicit data about coordinated use of language and gesture

1717/20/20

Subject Screen vs. Wizard ScreenSubject Screen vs. Wizard Screen

1818/20/20

Hybrid Wizard Of Oz ExperimentHybrid Wizard Of Oz Experiment

• Naive user free to write, draw, or speak without constraints imposed by current technology

• Wizard must respond quickly and accurately by using existing means, including pen and voice

• Simultaneous evaluation of:– Experienced user manipulating real system– New user, providing data for future extensions

• Bootstrap effect: continuous loop from data to theory, to system enhancement

• Improvements from data analysis quantifiable

• General-purpose approach1919/20/20

Hybrid WOZ: ImplementationHybrid WOZ: Implementation

• System logging and playback “for free” using OAA collaboration facilities

• “Subject mode”: functional interpretation (mostly) turned off

• Addition of simple Wizard Feedback panel (separate agent) for text-to-speech messages (e.g., “Function not available.”)

2020/20/20

SummarySummary

• Review of designing issues in software agents

• Not good for every application, but good for:– integrating numerous components which need to cooperate, often across language

boundaries– supporting media translation– distributed reference resolution– tasking through adaptable or multimodal user interfaces– human/agent collaborative systems & incremental dvpt– exploring direct manipulation/task delegation tradeoffs

2121/20/20

top related