Outline
What is an Agent?
Overview of the OAA
Implementation
OAA-based
Applications
Related Work
Summary
The Open Agent ArchitectureTM
Building communities of
distributed software agents
Adam Cheyer
David Martin
Douglas Moran
Artificial Intelligence Center
SRI International
333 Ravenswood Avenue
Menlo Park CA 94025
http://www.ai.sri.com/~oaa
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Examples
Voyager, Aglets,
Odyssey
Robots, Softbots
FireFly, MIT Media
Lab
Microsoft Agent, Julia
ModSAF, RoboCup
OAA, KQML, FIPA
What is an Agent?
Mobile Agents
Programs that move among computer hosts
Autonomous Agents
Based on planning technologies
Learning Agents
User preferences, collaborative filtering,...
Animated Interface Agents
Avatars, chatbots, ...
Simulation-based Entities
Cooperative Agents
Collaboration among distributed
heterogeneous components
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Overview of the OAA
Definition
OAA: A framework for integrating a
community of software agents in a
distributed environment
Distributed
Computing
Through
Delegation
What, not how or
who
User Interface
SRI International, AI Center
Facilitates flexible, adaptable
interactions among distributed
components through delegation of
tasks, data requests & triggers
Enables natural, mobile, multimodal
user interfaces to distributed services
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Approaches to Building Applications
OAA’s
Objective
Monolithic
Applications
Object-Oriented
Applications
Distributed Object
Applications
Virtual community of
dynamic services
Adaptable to
changing, evolving
network resources
Flexible interactions
among components
SRI International, AI Center
Dynamic addition
OAA
Applications
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Adaptable Interfaces
PlatformIndependent
Multimodal
User
Interfaces
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Agent Types
OAA Architecture
User Interface
Agents accept
multimodal input and
present results
Facilitator Agent
Natural Language
Agents produce
requests in ICL
Facilitator Agents
receive ICL requests
and coordinate
multiagent execution
App Agents wrap
legacy applications
Registry
Interagent Communication Language
User
Interface
Agent
NL to ICL
Agent
Application
Agent
Meta
Agent
API
Meta Agents apply
domain knowledge to
help coordinate other
agents
Modality Agents
SRI International, AI Center
Application
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Interagent Communication Language (ICL)
ICL:
unified means of
expressing
all agent
functionalities
Using ICL, agents:
- register capability specifications
- request services of community:
Perform queries, execute actions, exchange
information, set triggers, manipulate data
ICL defines both conversation layer of requests &
logic-based content layer
ICL delegation:
description of request + advice & constraints
ICL is platformindependent
Support for programming languages
C, C++, Visual Basic, Java, Delphi, Prolog, Lisp
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Delegation through ICL
Task
Management
oaa_Solve(TaskExpr, ParamList)
Expressions: logic-based (cf. Prolog)
Parameters: provide advice & constraints
• High-level task types: query, action, inform, ...
• Low-level: solution_limit(N), time_limit(T),
parallel_ok(TF), priority(P), address(Agt),
reply(Mode), block(TF), collect(Mode), ...
Data & Trigger
Management
oaa_AddData(DataExpr, ParamList)
oaa_AddTrigger(Typ,Cond,Action,Ps)
Example
oaa_Solve((manager(‘John Bear’,M),
phone_number(M,P)),
[query(var(P))])
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Multimodal User Interfaces
User is special
member of agent
community
User interfaces
to distributed
services, using
distributed
services
Natural language translation to and from ICL
• Multiple NL agents for different qualities
(fast, robust) and languages (English, French)
Multiagent cooperation for ambiguity resolution
• Pen: gesture or handwriting?
• Reference resolution: “photo of the hotel”
- NL Agent: hotel in language context
- Gesture Agent: hotel being pointed at
- UI Agent: only one hotel visible
- Database Agent: “hotel on Smith Street”
- Discourse Agent: “the other hotel”
- Human User: if still ambiguous, can clarify
• Cross-modality ambiguities
- Arrow + “scroll map” vs. Arrow + “show hotel”
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
OAA Triggers
Purpose
Adding a Trigger
Trigger Types
Actions
OAA agents can dynamically register interest in
any data change, communication event, or realworld occurrence accessible by any agent.
oaa_AddTrigger(Type, Cond, Action, Params)
comm: on_send, on_receive message
time: “in ten minutes”, “every day at 5pm”
data: on_change, on_remove, on_add
task: “when mail arrives about...”
The actions of triggers may be any ICL
expression solvable by the community of agents
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
A Sample Text-to-Speech Agent in C
Include libraries
List capabilities
Define
capabilities
Agent Startup
#include <libcom_tcp.h>
#include <liboaa.h>
ICLTerm capabilities = icl_TermFromStr(“[play(tts, Msg)]”);
ICLTerm oaa_AppDoEvent(ICLTerm Event, ICLTerm Params) {
if (strcmp(icl_Str(Event), “play”) == 0) {
return playTTS(icl_ArgumentAsStr(Event, 2));
}
else return NULL;
}
main() {
com_Connect(“parent”, connectionInfo);
oaa_Register(“parent”, “tts”, capabilities);
oaa_MainLoop(True);
}
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
A Sample Text-to-Speech Agent in Prolog
Include libraries
List capabilities
Define
capabilities
Agent Startup
:- [libcom_tcp].
:- [liboaa].
capabilities([solvable(play(tts, Msg),
[type(procedure), callback(tts_events)], [])]).
tts_events(play(tts, Msg), Params) :tts_api(Msg).
start :capabilities(C),
com_Connect(parent, ConnectionInfo),
oaa_Register(parent, tts, C),
oaa_MainLoop(true).
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
1.
2.
3.
4.
5.
6.
Automated Office
Unified Messaging
Multimodal Maps
CommandTalk
ATIS-Web
Spoken Dialog
Summarization
7. Agent Development
Tools
8. InfoBroker
9. Rental Finder
10. InfoWiz Kiosk
11. Multi-Robot Control
12. MVIEWS Video Tools
13. MARVEL
14. SOLVIT
15. Surgical Training
16. Instant Collaboration
17.Crisis Response
18. WebGrader
19. Speech Translation
20-25+ ...
SRI International, AI Center
OAA-based Applications
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Main Points
Automated Office Application
Mobile access to
distributed services
Legacy applications
interacting with
AI technologies
High-level tasking of
agents through NL
and speech
Flexible interactions
among components
Delegated Triggers
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Main Points
Multimodal Maps Application
Natural interface to
distributed (web)
data
Synergistic
combination of
handwriting, drawing,
speech, direct
manipulation
Parallel cooperation
and competition
among many agents
Human & Agent
collaboration
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Main Points
Unified Messaging
Mobile, adaptable
access to distributed
services
Integrated
Messaging:
web, email, voice,
fax
Distributed reference
resolution and media
format translation
Flexible interactions
among components
Delegated Triggers
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Main Points
MVIEWS Application
Live and
Live
and Video
Archived
Archived Video
Multimodal
annotation of video
using speech & pen
Automated detection,
tracking, and
geolocation of
moving objects
Interactive
Interactive
Map
Map
Search and replay of
videos indexed by
multimodal and
auxilliary data
Applications:
multi-sensor
surveillance,
Predator UAV,
Olympic bombing
SRI International, AI Center
Video browser with multimedia timeline
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Main Points
InfoWiz Application
An information kiosk
with an animated
wizard who :
answers questions,
gives tours,
and helps navigate
the information
space
OAA integrates SRI’s
speech recognition,
NL, and knowledge
representation with
Microsoft Agent
graphics and
Netscape’s
webbrowser
Soon in SRI ’s lobby
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
CommandTalk Application
A spoken language interface to the LeatherNet
military simulation and training system
Main Points
Spoken language
interface adapts to
dynamic changes in
simulated world
Advantages of
speech:
- More realistic
training
- Faster, more
natural interface
Supports Army, Navy,
Marine Corp and
Airforce versions of
ModSAF simulator
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Agent Development Tools
Tools are implemented themselves in OAA
Guide user through process of creating an agent:
• Definition of capabilities
• Documentation management
(publication on Web)
• Code generation of agent template
• Definition of NL vocabulary
• Update NL & speech recognition systems
• Assembly of multiagent projects
Runtime tool for launching and monitoring
agent communities
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
Related Work
Distributed objects (CORBA, DCOM)
+
+
+
-
Object-based integration of heterogeneous components
Network services (e.g. security, transactions)
Commercial implementations exist (e.g. Iona,Visigenic)
Interactions primarily hard-coded (method calls)
Agent Communication Languages (KQML, FIPA)
+ Asynchronous message-passing communication richer
than object model. Facilitates parallelism
+/- Communication acts separate from content (KIF, SL)
- Interactions primarily hard-coded (peer-to-peer msgs)
OAA focuses on providing delegation services for
flexible interactions on tasks, triggers and data mgmt
+ Research applicable to both DOBJ and ACL models
+ Bridges can be built from and to other models
+ OAA concepts could be layered on top of other models
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
OAA vs. Distributed Objects (CORBA, DCOM)
• Distributed, heterogeneous
• Retrieve obj, call obj
– interface: C++ -like
– hardcoded interactions
• Distributed, heterogeneous
• Ask Facilitator to call service
+ interface: declarative specs
+ delegated goal & advice
• parallel, compound goals,
backtracking, constraints
• Data & Trigger management
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
OAA vs. Agent Communication Languages (KQML,FIPA)
• Distributed, heterogeneous • Distributed, heterogeneous
• Ask Agent Name Server
• Ask Facilitator to distribute and
or Service Broker for Addr,
coordinate complex requests
send msg, handle reply
+ parallel, compound goals,
– hardcoded interactions
backtracking, constraints
+/- conversation policies
+ tasks, triggers, data mgmt
• Logic-based content (KIF,SL) • Logic-based content (ICL)
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
OAA and Scalability
Limitations:
Facilitator is single point of failure
Facilitator is bottleneck for communication
Solutions?
Multi-Facilitator
topologies
Distribution of planning
& execution functions
of Facilitator + peer-to-peer
communication
Facilitator
Facilitator
Facilitator
Replicated
Plan + Exe
Registry &
Planner
Agent E
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa
OAA Characteristics
Open:
Extensible:
Distributed:
Parallel:
Mobile:
High-level:
Multimodal:
agents can be created in many languages and
interface with existing systems
agents can be added or replaced dynamically
agents are spread across many computers
Parallel execution of subtasks
Lightweight interfaces on phone and/or PDA
hides software and hardware dependencies
handwriting, speech, gestures, and direct
manipulation can be combined together
SRI International, AI Center
Open Agent ArchitectureTM
http://www.ai.sri.com/~oaa