a multi-agent system for visualization simulated user behaviour b. de vries, j. dijkstra
Post on 15-Jan-2016
220 views
TRANSCRIPT
![Page 1: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/1.jpg)
A Multi-Agent System for Visualization Simulated
User Behaviour
B. de Vries, J. Dijkstra
![Page 2: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/2.jpg)
Agenda
VR-DIS research programme:
B. de Vries
AI for visualization of human behavior:
J. Dijkstra
![Page 3: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/3.jpg)
VR Technology in (Architectural) Design
• Traditional process and use
• Envisioned process and use
![Page 4: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/4.jpg)
Traditional process: Sketch
• Paper & Pencil• Reflection on
Thoughts• Vague
![Page 5: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/5.jpg)
Traditional process: Design
• 2D/3D Modeling• Material use• Consultancy:
Installation, Construction, etc.
![Page 6: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/6.jpg)
Traditional process: Presentation
• Convey design• Impression of
building
![Page 7: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/7.jpg)
Envisioned process: 3D Modeling
• Direct manipulation
• Implicit relations• Sculpturing
![Page 8: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/8.jpg)
Envisioned process: Scene Painting
• Realistic images• No construction
material
![Page 9: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/9.jpg)
Envisioned process: Evaluation
• Indoor climate• Lighting• Structural
behavior• Acoustics• User behavior
![Page 10: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/10.jpg)
Example: Urban plan
![Page 11: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/11.jpg)
Towards a Multi-Agent System for Visualizing Simulated User Behavior
![Page 12: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/12.jpg)
Introduction of the Model
![Page 13: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/13.jpg)
• Architects and urban planners are often faced with the problem to assess how their design or planning decisions will affect the behavior of individuals.
• One way of addressing this problem is the use of models simulating the navigation of users in buildings and urban environments.
A Multi-Agent System based on Cellular Automata
![Page 14: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/14.jpg)
Essentials of Cellular Automata
![Page 15: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/15.jpg)
Cellular automata are discrete dynamical Cellular automata are discrete dynamical systems whose behavior is completely systems whose behavior is completely specified in terms of a local relationspecified in terms of a local relation
• Cell
Cellular automata are characterized by the following features:
• Grid • State • Time
![Page 16: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/16.jpg)
Cellular Automata Model of Cellular Automata Model of Traffic FlowTraffic Flow
![Page 17: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/17.jpg)
Agent Characteristics
![Page 18: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/18.jpg)
Agent DefinitionsAgent Definitions
Agents are computational systems that inhibit some complex dynamic environment, sense and act autonomously in this environment, and by doing so realize a set of goals or tasks for which they are designed (Maes).
An autonomous agent is a system situated within and part of an environment that senses that environment and acts on it, over time, in pursuit of its own agenda (Franklin & Graesser).
![Page 19: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/19.jpg)
Agent PropertiesAgent Properties• Autonomy
- agents have some control over their actions and internal state
• Social ability- agents interact with other agents
• Reactivity- agents perceive their environment and respond to
changes in it
• Pro-activeness- agents exhibit goal-directed behavior by acting on
their own initiative
• ? Mentalistic capabilities- knowledge, belief, intention, emotion
![Page 20: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/20.jpg)
Agent ArchitectureAgent Architecture
State
ProductionSystem
ActionPerception
Sen
sors
Eff
ecto
rs
![Page 21: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/21.jpg)
Multi Agent Simulation Models
![Page 22: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/22.jpg)
Offers the promise of simulatingsimulating autonomous agents and the interaction between them.
behaviors evolve dynamically during the simulation
Evolution capabilities:
• evolution of the agent’s environment
• evolution of the agent’s behavior during the simulation
• anticipated behavior
• unplanned behavior
![Page 23: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/23.jpg)
Towards the Framework
![Page 24: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/24.jpg)
CellularAutomata
Artificial Intelligence
DistributedArtificial
Intelligence
Multi Agent Simulation Models
![Page 25: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/25.jpg)
MotivationMotivation
• Develop a system how people move in a particular environment.• People are represented by agents.• The cellular automata model is used to simulate
their behavior across the network.
• A simulation system would allow the designer to assess how its design decisions influence user movement and hence performance indicators.
![Page 26: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/26.jpg)
Network ModelNetwork Model
The network is the three-dimensional cellular automata model representation of a state at a certain time.
![Page 27: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/27.jpg)
different neighborhoodsdifferent neighborhoods
von Neum ann
r = 1 r = 2
Moore
r = 1 r = 2
![Page 28: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/28.jpg)
transition of a state of a celltransition of a state of a cell
![Page 29: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/29.jpg)
Agent ModelAgent Model
ConjointMeasurement
Agent
DecisionSupportAgent
ActorAgent 1
ActorAgent n
SubjectAgent
Virtual EnvironmentSimulation Model
VirtualInteraction
Interface AgencyTechnical
Communication IntuitiveCommunication
![Page 30: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/30.jpg)
User AgentUser Agent
Define an user-agent as: U = < R | S >, where:
• R is finite set of role identifiers; {actor, subject}
• S scenario , defined by: S = <B, I, A, F, T>, where:• B represents the behavior of user-agent i • I represents the intentions of a user-agent i • A represents the activity agenda user user-agent i • F represents the knowledge of information about
the environment, called Facets• T represents the time-budget each user-agent
possesses
![Page 31: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/31.jpg)
The Integration of Cellular Automata The Integration of Cellular Automata and Multi Agent Technologyand Multi Agent Technology
• an actor-based view
Initially, we will realize different graphic representations of our simulation:
• a network-based view
• a main node-based view
![Page 32: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/32.jpg)
network grid and decision pointsnetwork grid and decision points
main decision point
remaining walkway section decision point
section bound
E1 E2
E3
°
°
° ° °
°
° °
° S6
S7
S8S10 S9
°
°
°
S11
S12
S13
° ° ° S14S15S16
° ° ° ° ° S1 S2 S3 S4 S5
S18S17
S19 S20
![Page 33: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/33.jpg)
main node-based viewmain node-based view
links
actual path
actual decision point
![Page 34: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/34.jpg)
actor-based view / network-based viewactor-based view / network-based view
![Page 35: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/35.jpg)
Simulation ExperimentSimulation Experiment
Design of a simulation experiment of pedestrian movement.
Considering a T-junction walkway where pedestrians will be randomly created at one of the entrances.
Some impressions ...
![Page 36: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/36.jpg)
![Page 37: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/37.jpg)
![Page 38: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/38.jpg)
![Page 39: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/39.jpg)
Demo
![Page 40: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/40.jpg)
Conclusions
![Page 41: A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra](https://reader036.vdocuments.net/reader036/viewer/2022062804/56649d545503460f94a301e0/html5/thumbnails/41.jpg)
Complex behavior can be simulated by using the concept of cellular automata in the context of multi-agent technology.
The development of multi-agent models offers the promise of simulating autonomous individuals.
A multi-agent model can be used for visualizing simulated user behavior to support the assignment of design performance.
The proposed concept potentially has a lot to offer in architecture and urban planning when visual and active environments may impact user behavior and decision-making processes.