constructing the future with intelligent agents raju pathmeswaran dr vian ahmed prof ghassan aouad
TRANSCRIPT
Constructing the Future with Intelligent AgentsConstructing the Future with Intelligent Agents
Raju Pathmeswaran
Dr Vian Ahmed
Prof Ghassan Aouad
Today's presentationToday's presentation
Aim of the research Introduction to agents Abilities of intelligent agents Types of agents configuration Example industrial adoptions Application of agents in construction Future trends
AimAim
Aim of this research is to investigate the extent to which we can develop and use intelligent agents to evaluate designs from multiple perspectives and under various scenarios
ScopeScope
nD Modelling Environment
Intelligent Agents
Decision Making Failure Prediction
Site Safety Hazard Detection
Design Model s Assembly Sequence
Site Layouts Design Query
Rule B ased System Knowledge Repository
Reasoner Ontology
Services Oriented Architecture
What is an agent?What is an agent?
An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through effectors.
Some agentsSome agents
Human agent – eyes, ears, other organs for sensors; hands, legs etc for effectors
Robot agent – camera, infrared for sensors; various motors for effectors
Software agent – encoded bit strings as its percepts and actions
What is an intelligent agent?What is an intelligent agent?
An intelligent agent is a computer system that is capable of flexible autonomous action in order to meet its design objectives. responsive: agents should perceive their environment
and respond in a timely fashion to changes that occur in it
proactive: agents should not simply act in response to their environment, they should be able to exhibit opportunistic, goal-directed behaviour and take the initiative where appropriate
social: agents should be able to interact, when they deem appropriate, with other artificial agents and humans in order to complete their own problem solving and to help others with their activities.
What do agents have to offer?What do agents have to offer?
the ability to solve problems that have been beyond the scope of automation: either because no existing technology could be used
to solve the problem, or because it was considered too expensive (difficult,
time-consuming, risky) to develop solutions using existing technology;
the ability to solve problems that can already be solved in a significantly better (cheaper, more natural, easier, more efficient, or faster) way.
Belief-Desire-Intention (BDI) Belief-Desire-Intention (BDI) model of agencymodel of agency
Some philosophical basis in the Belief-Desire-Intention theory of human practical reasoning
Belief - informational state of the agent i.e. beliefs about the world including itself & other agents
Desire - motivational state of the agent i.e. objectives or situations that agent would like to accomplish
Intention - deliberative state of the agent i.e. what the agent has chosen to do
3. Applications3. Applications
Decision support systems E-commerce systems Financial systems e.g. anti money
laundering
Agent development toolkitsAgent development toolkits
The JADE (Java Agent Development Environment) is an open source platform that develops Java agents
JACK - operates on top of the Java programming language, acting as an extension of object-oriented development that provides agent-related concepts.
IMPACT provides an agent development environment, called AgentDE, that allows developers to define every aspect of the agent that forms part of the agent wrapper
Agent toolkits cont.Agent toolkits cont.
JACK makes use of just TCP and UDP for communication
IMPACT and JADE make use of RMI which is costly
Current trend is towards more lightweight approaches Web Service technologies beginning to play
an important role
Industrial adoption of agent Industrial adoption of agent based technologies based technologies
Manufacturing Control Daimler Chrysler demonstrated very high flexibility, increased
throughput, robustness and reliability of the agent-based manufacturing facility
Logistics and Supply Chains ABX use agent-based solution in order to (i) achieve
performance scalability, (ii) reflect the geographical distribution of the nodes, (iii) provide local re-planning without the need to rebuild the whole plan and (iv) increase robustness so that a single point of failure would be avoided
Production Planning Simulation Unmanned Aerial Vehicle control Space Exploration Applications
Intelligent agents in Intelligent agents in construction researchconstruction research
Collaborative design of structures (Anumba et al, 2002)
Designing steel skeleton structures of tall buildings (Skolicki and Kicinger, 2002)
Supporting construction procurement negotiation (Dzeng and Lin, 2004)
Constructing the future trendsConstructing the future trends
Simulation: potential of wider deployment of multi-agent systems in the field of simulation. E.g. Healthcare simulation
Prototyping: Agents enabled virtual prototyping; to identify design errors
Hardware: E.g. agent applications linked to the utilisation of RFID technology for construction materials and equipments