Effective Coordination of Multiple Intelligent Agents for Command and Control The Robotics Institute Carnegie Mellon University PI: Katia Sycara

Slides:



Advertisements
Similar presentations
FIPA Interaction Protocol. Request Interaction Protocol Summary –Request Interaction Protocol allows one agent to request another to perform some action.
Advertisements

A component- and message-based architectural style for GUI software
Some questions o What are the appropriate control philosophies for Complex Manufacturing systems? Why????Holonic Manufacturing system o Is Object -Oriented.
Vendor Briefing May 26, 2006 AMI Overview & Communications TCM.
Software Modeling SWE5441 Lecture 3 Eng. Mohammed Timraz
0 General information Rate of acceptance 37% Papers from 15 Countries and 5 Geographical Areas –North America 5 –South America 2 –Europe 20 –Asia 2 –Australia.
© 2006 Carnegie Mellon University Establishing a Network Centric Capability: Implications for Acquisition and Engineering Dennis Smith Complex System Symposium.
PLANSERVE Planning and Scheduling Techniques for the Intelligent Problem Solving Grid Planning and Scheduling Team ISTC-CNR National Research Council of.
MokSAF: Agent-based Team Assistance for Time Critical Tasks Katia Sycara The Robotics Institute
Effective Coordination of Multiple Intelligent Agents for Command and Control The Robotics Institute Carnegie Mellon University PI: Katia Sycara
1 Sensor Networks and Networked Societies of Artifacts Jose Rolim University of Geneva.
Planning and Strategic Management
JACK Intelligent Agents and Applications Hitesh Bhambhani CSE 6362, SPRING 2003 Dr. Lawrence B. Holder.
Intelligent Software Agents Lab The Robotics Institute Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA (U.S.A.)
Brent Dingle Marco A. Morales Texas A&M University, Spring 2002
Las Vegas 1999Katia Sycara1 Effective Coordination of Multiple Intelligent Agents for Command and Control The Robotics Institute Carnegie Mellon University.
Distributed Rational Decision Making Sections By Tibor Moldovan.
RETSINA: A Distributed Multi-Agent Infrastructure for Information Gathering and Decision Support The Robotics Institute Carnegie Mellon University PI:
Managing Agent Platforms with the Simple Network Management Protocol Brian Remick Thesis Defense June 26, 2015.
DARPA CoABS Workshop Las Vegas, NV. Final Group 1 (TIE) Briefing Coordinator: Katia Sycara January 29, 1999.
Pertemuan Matakuliah: A0214/Audit Sistem Informasi Tahun: 2007.
1 FM Overview of Adaptation. 2 FM RAPIDware: Component-Based Design of Adaptive and Dependable Middleware Project Investigators: Philip McKinley, Kurt.
Lecture Nine Database Planning, Design, and Administration
The Robotics Institute
All content in this presentation is protected – © 2008 American Power Conversion Corporation Rael Haiboullin System Engineer Capacity Manager.
Enterprise Architecture
Module 3: Business Information Systems
Database System Development Lifecycle © Pearson Education Limited 1995, 2005.
Overview of the Database Development Process
Intelligent Software Agents Lab The Robotics Institute Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA (U.S.A.)
European Network of Excellence in AI Planning Intelligent Planning & Scheduling An Innovative Software Technology Susanne Biundo.
An Integration Framework for Sensor Networks and Data Stream Management Systems.
© 2007 Tom Beckman Features:  Are autonomous software entities that act as a user’s assistant to perform discrete tasks, simplifying or completely automating.
Software Agents: An Overview by Hyacinth S. Nwana and Designing Behaviors for Information Agents by Keith Decker, Anandeep Pannu, Katia Sycara and Mike.
ASG - Towards the Adaptive Semantic Services Enterprise Harald Meyer WWW Service Composition with Semantic Web Services
2Object-Oriented Analysis and Design with the Unified Process The Requirements Discipline in More Detail  Focus shifts from defining to realizing objectives.
Service Transition & Planning Service Validation & Testing
111 Notion of a Project Notes from OOSE Slides – a different textbook used in the past Read/review carefully and understand.
What is a Business Analyst? A Business Analyst is someone who works as a liaison among stakeholders in order to elicit, analyze, communicate and validate.
TitleIEEE Standard for Mostly RESTful Orchestration Interface Protocol (mREST) for Orchestrating Software-Controlled Assets via Web Services ScopeThe mREST.
NC-BSI: 3.3 Data Fusion for Decision Support Problem Statement/Objectives: Problem - Accurate situation awareness requires rapid integration of heterogeneous.
NAVEEN AGENT BASED SOFTWARE DEVELOPMENT. WHAT IS AN AGENT? A computer system capable of flexible, autonomous (problem-solving) action, situated in dynamic,
A G E N T S T O R M Copyright © 2000, Carnegie Mellon University
© 2012 xtUML.org Bill Chown – Mentor Graphics Model Driven Engineering.
Middleware for FIs Apeego House 4B, Tardeo Rd. Mumbai Tel: Fax:
Systems Analysis and Design in a Changing World, Fourth Edition
What’s MPEG-21 ? (a short summary of available papers by OCCAMM)
Information & Decision Superiority Case studies in applying AI planning technologies to military & civil applications Dr Roberto Desimone Innovations.
Christoph F. Eick University of Houston Organization 1. What are Ontologies? 2. What are they good for? 3. Ontologies and.
Integrating Intelligent Assistants into Human Teams Katia Sycara The Robotics Institute Carnegie Mellon University Pittsburgh, PA (412)
Software Architecture Evaluation Methodologies Presented By: Anthony Register.
Chapter 4 Decision Support System & Artificial Intelligence.
1 Reasons for Migrating Code The principle of dynamically configuring a client to communicate to a server. The client first fetches the necessary software,
Distributed Models for Decision Support Jose Cuena & Sascha Ossowski Pesented by: Gal Moshitch & Rica Gonen.
Multiagent System Katia P. Sycara 일반대학원 GE 랩 성연식.
CSE 303 – Software Design and Architecture
Foundations of Information Systems in Business. System ® System  A system is an interrelated set of business procedures used within one business unit.
1 Power to the Edge Agility Focus and Convergence Adapting C2 to the 21 st Century presented to the Focus, Agility and Convergence Team Inaugural Meeting.
Unit – I Presentation. Unit – 1 (Introduction to Software Project management) Definition:-  Software project management is the art and science of planning.
Unclassified//For Official Use Only 1 RAPID: Representation and Analysis of Probabilistic Intelligence Data Carnegie Mellon University PI : Prof. Jaime.
From Use Cases to Implementation 1. Structural and Behavioral Aspects of Collaborations  Two aspects of Collaborations Structural – specifies the static.
Las Vegas 1999Katia Sycara1 DARPA CoABS Workshop Las Vegas, NV. TIE Final Group 1 Briefing Coordinator: Katia Sycara January 29, 1999.
Introduction to Software Engineering 1. Software Engineering Failures – Complexity – Change 2. What is Software Engineering? – Using engineering approaches.
LECTURE 5 Nangwonvuma M/ Byansi D. Components, interfaces and integration Infrastructure, Middleware and Platforms Techniques – Data warehouses, extending.
From Use Cases to Implementation 1. Mapping Requirements Directly to Design and Code  For many, if not most, of our requirements it is relatively easy.
A Semi-Automated Digital Preservation System based on Semantic Web Services Jane Hunter Sharmin Choudhury DSTC PTY LTD, Brisbane, Australia Slides by Ananta.
Enabling Team Supervisory Control for Teams of Unmanned Vehicles
The Robotics Institute Carnegie Mellon University PI: Katia Sycara
Service Oriented Architectures (SOA): What Users Need to Know.
-A systemfor decision making and problem solving. Decision Support System - A system for decision making and problem solving.
Presentation transcript:

Effective Coordination of Multiple Intelligent Agents for Command and Control The Robotics Institute Carnegie Mellon University PI: Katia Sycara Key Personnel: Onn Shehory Michael Young

Current Situation Vast amounts of data from distributed and heterogeneous sources Uncertain and evolving tactical situation Shrinking decision cycles Decision makers distributed in space and time

Overall Goal To develop effective agent-based system technology to support command and control decision making in time stressed and uncertain situationsTo develop effective agent-based system technology to support command and control decision making in time stressed and uncertain situations

Research Approach Develop an adaptive, self-organizing collection of intelligent agents that interact with the humans and each other to –integrate information management and decision support –anticipate and satisfy human information processing and problem solving needs –perform real-time synchronization of domain activities –notify about significant changes in the environment –adapt to user, task and situation

Research Issues What coordination mechanisms are effective for large numbers of sophisticated agents? What are the scaling up properties of these coordination mechanisms? How do they perform with respect to dimensions, such as task complexity, interdependence, agent heterogeneity, solution quality? What guarantees do these mechanisms provide regarding predictability of overall system behavior? Do they mitigate against harmful system behaviors? How to achieve effective human-agent coordination?

Potential Impacts Reduce time for commanders to arrive at a decision Allow commanders to consider a broader range of alternatives Enable commanders to flexibly manage contingencies (replan, repair) Improve battle field awareness Enable in-context information filtering

Innovative Claims Scalable, robust and adaptive coordination and control multi-agent strategies Sophisticated individual agent control Reusable and customizable agent components Multi-agent infrastructure coordination tools and environment

Major Project Deliverables Prototype multiagent system that aids human military planners to perform effective “in context” information gathering, execution monitoring, and problem solving reusable “agent shell” that includes domain independent components for representing and controlling agent functionality, so that agents can be easily produced for different types of tasks effective multiagent coordination protocols, that are scalable, efficient and adaptive to user task and planning context multi agent coordination infrastructure consisting of a suite of tools for reliable and low cost building and experimenting with flexible multiagent systems

The RETSINA Multi-Agent Architecture User 1User 2User u Info Source 1 Info Source 1 Interface Agent 1 Interface Agent 2 Interface Agent i Task Agent 1 Task Agent 2 Task Agent t MiddleAgent 2 Info Agent n Info Source 2 Info Source 2 Info Source m Info Source m Goal and Task Specifications Results SolutionsTasks Info & Service Requests Information Integration Conflict Resolution Replies Advertisements Info Agent 1 Queries Answers distributed adaptive collections of information agents that coordinate to retrieve, filter and fuse information relevant to the user, task and situation, as well as anticipate user's information needs.

RETSINA Individual Agent Architecture

Capability-based coordination Open, uncertain environment: –Agents leave and join unpredictably –Agents have heterogeneous capabilities –Replication increases robustness Agent location via Middle agents: –Matchmakers match advertised capabilities –Blackboard agents collect requests –Broker agents process both

Capability-based coordination (cont) Advertisement: –Includes agent capability, cost, etc. –Supports interoperability –Agent interface to the agent society independent of agent internal structure We will test scale-up properties of capability-based coordination

Cooperation Problems with current methods: –Mechanisms not tested in real-world MAS –Simulations?size small (~20 agents) –Complex mechanism do not scale up We will provide algorithms for efficient group formation

Cooperation - solutions (continued) Approach:  Very large systems (millions of agents): –Constant complexity cooperation method –Based on models of multi-particle interaction  Structural organization: –Trade-off between reduced complexity and loss of autonomy –Effect on system flexibility, robustness

Cooperation - solutions (continued)  Communication planning: –Change communication patterns to reduce eavesdropping risk –Bundle small message together –Use networks when less congested

Competition and Markets Limited resources result in competition Market-based approaches: –Assume that agent can find one another – Otherwise, convergence results do not hold Approach:  Utilize financial option pricing: Prioritize tasks by dynamic valuation Allows flexible contingent contracting Analysis of large MAS via economics methods

Competition and Markets (contd)  Combine our capability-based coordination with market mechanisms  Mechanism design: –Design enforceable mechanisms for self-interested agents –Resolve 揟 ragedy of Commons?by pricing schemes. –Devise mechanisms to motivate truthful behavior

RETSINA: Testbed for Agent-Based Systems Continuing development of general purpose multi- agent infrastructure Agents built from domain-independent, reusable components Agent behaviors specified in declarative manner New agent configurations easily built and empirically tested.

Coordinating Agents With Human Users Problem: Commanders’ already overloaded For task delegation to be effective, communication with agents should be –natural flexible: providing planning information when appropriate concise: providing as little detail as possible –interactive : before and during task execution, agents: –provide explanations of plans –assist users in revising plans during task execution, agents: –report plan’s progress

Agent Task Delegation Languages for task description and delegation –Reconciling human and agent representation of tasks –Structured Natural Language/Graphical task description Interactive Planning and Execution –user input as constraints on plan formation –execution monitor brings user into loop Extending RETSINA’s –graphical task editor –planner and execution monitor

In-Context Information Management for C2 Agent-Based Information Management Dependent on –user preferences –decision-making tasks –evolving situation Agents’ responsibilities –Represent users’ task environment –Monitor significant changes –Provide appropriate notification to user or responsible agent –Learn to track and anticipate user’s information needs –Learn appropriate times and methods for presenting information

Agent Coordination in RETSINA Build information management agents for C2 based on RETSINA mechanisms for agent coordination Goal and task structures provide user and agent context Information agents form and execute plans that –involve queries for future information monitoring –take situational constraints into account –work around notification deadlines Build upon existing base of information management agents

Research Plan Agent Control –mapping of task model and requirements to the appropriate coordination strategy –mapping of constraints of the environment, other agents and available resources to appropriate coordination strategy –experimental evaluation, analysis and refinement Agent Coordination –design/refine coordination algorithm –implement appropriate experimental infrastructure –implement the coordination strategy and evaluate along different dimensions –analyze the results and refine algorithm design and experimental process

Research Plan (contd.) User-Agent Coordination –enhance the functionality of the current agent command language –develop and implement techniques for acquisition and maintenance of user tasks preferences and intentions –develop and implement protocols to enable an agent to accept task- related queries before, during or after task execution and generate natural descriptions of the unfolding execution of its plans –evaluate and refine Information Management and Decision Support –develop mechanisms for information management (e.g., filtering, integration) in the context of the current problem solving task –develop mechanisms for in-context information monitoring and notification –evaluate and refine