1 / 37

Evaluating and re-evaluating agent modeling: simulation and design

Evaluating and re-evaluating agent modeling: simulation and design. Daniel Belcher. ?. January 11 th , 2007 Arch 484: Design Computing Seminar. Simulations and Models…Visual Models. Ballard Library & Neighborhood Service Center. Bohlin Cywinski Jackson, Architects.

rafal
Télécharger la présentation

Evaluating and re-evaluating agent modeling: simulation and design

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Evaluating and re-evaluating agent modeling: simulation and design Daniel Belcher ? January 11th, 2007 Arch 484: Design Computing Seminar

  2. Simulations and Models…Visual Models Ballard Library & Neighborhood Service Center. Bohlin Cywinski Jackson, Architects

  3. UW project: http://www.urbansim.org/

  4. ECOTECT.com Physical simulation

  5. Old-school Mechanisms “For seeing life is but a motion of limbs, the beginning whereof is in some principal part within, why may we not say that all automata (engines that move themselves by springs and wheels as doth a watch) have an artificial life?" -Thomas Hobbes, Leviathan, 1660. “L’homme est une machine.” Man is a machine. -Julien Offray de La Mettrie, L’homme machine, 1748. “Verum et factum convertuntur.” The true and the made are convertible. -Giambattista Vico, De nostri temporis studiorum ratione, 1709.

  6. MASSIVE Software Agents on film… “Fellowship of the Ring” battle scenes by Weta digital.

  7. “It’s all soooooo pedestrian…” • Much of agent modeling is focused on navigation, locomotion, and movement through space. • Why? Humans are extremely complex…and even walking around is difficult to model. However… • The dynamics of pedestrian crowds are surprisingly predictable …

  8. Pedestrian activity can be modeled as a self-organizing system (Helbing et al, 2001). Time-lapse photography: standing crowd outside a movie theater showing crossing pedestrians forming a river-like flow. Agent models of pedestrian flows.

  9. EVAS Pedestrian Modeling Software http://www.vr.ucl.ac.uk/research/evas/evas.html

  10. “What behavior should the agent simulate?” “Does the agent exhibit this behavior?” “Do humans behave in the same way?” “How do groups of humans behave?” “Do models exhibit these group behaviors?” “Can models capture something beyond simply behavior?” “Can they capture emotion? Mood? Cognitive process?” “Just how predictable are people?” “Should we model agents at all?” “What assumptions does agent modeling make?”

  11. Two types of control… Information-based control information Environment Agent control Model-based control Planned path Emergent path

  12. Sense-Model-Plan-Act Sense Act Plan Plan Sense Model environment agent Adapted from (Russell & Norvig, “Artificial Intelligence,”1995)

  13. The “Ecological” approach…S(P)A ??? AKA: Gibson’s direct perception: (Gibson, “The Ecological Approach to Visual Perception,” 1979) AKA: Active Perception in robotics (Brooks, “Intelligence without representation”, 1991) Subsumption architecture AKA: Situated, reactive agents

  14. Behaviors as rules… (Reynolds, “Flocks, herds, and schools: A distributed behavioral model,” 1987) a) Separation. Steer to avoid local flock-mates. b) Cohesion. Steer to move toward the average position of local flock-mates. c) Alignment. Steer toward the average heading of local flock-mates. d) Avoidance. Steer to avoid running into local obstacles or non-flock-mates. 1) Pedestrians are motivated to move as efficiently as possible to a destination. 2) Pedestrians wish to maintain a comfortable distance from other pedestrians. 3) Pedestrians wish to maintain a comfortable distance from obstacles. 4) Pedestrians may be attracted to other pedestrians or objects.

  15. Evaluating agent modeling…

  16. Why does all this matter? Answer: Agent-based simulation allows designers to evaluate the behavior of individuals and groups inhabiting a space. • Learn more about the agent-environment dynamic • Validate new designs against known behavior from old designs • Better understand and improve upon existing buildings • Help train building operators to better manage their buildings • Generate building visualizations showing life-like usage patterns • Illustrate the consequences of changes to building structure

  17. (Therakomen, 2000; 2001). MouseHaus + Pros: Seeks to model reflexive, reactive and motivated behaviors. Computationally efficient. - Cons: Agent steering dynamics are simplistic. Linear behavior…no learning.

  18. Agent-based Virtual Users (Yan and Kalay, “Simulating Human Behavior in Built Environments,” 2005)

  19. <arch:LowWall archID='FountainSide' x='9' y='39' id='516' usability='sit'/> <use xlink:href='#cell_6' transform='translate(84.0,94.5)'/> Artificial Life Behavior Modeling: primary movement control was flocking (as in Reynolds, 1987). B = f(G,R,E) International standard of human modeling: Humanoid Animation Specification (H-Anim, 1.1)

  20. 3D visual simulation of plaza, with and without fountain. (Yan and Kalay, 2005). • + Pros: • + Interactive simulation. • + Uses standard media (DXF) + “BIM”. • + Conducted study of observed behavior. • Cons: • Artificial life model is extremely simplistic. • Agents explore, but do not learn. • Affordances are explicitly encoded in the environment, and not as emergent behavior.

  21. Curious Agents (Saunders and Gero, “Curious Agents and Situated Design Evaluation,” 2004) • Exploratory agents • Ray-casting perception • Curiosity model (Saunders and Gero, 2001) • Learning model • Exploring an “art gallery”

  22. Agent Evaluations, before and after… • Agent’s Post-Occupancy Evaluation… • Even dispersal of interest • Less crowding • All rooms visited by each agent • Agents learn a random array of “art work” • Uneven dispersal • Crowding around entrance and exit • Stuck in local-minima (NW room empty)

  23. Ecoconfiguration & Generative Design (Turner, Mottram & Penn, “An Ecological Approach to Generative Design,” IJDC, 2004) • Generative Component: • Environments are randomly seeded. • Genetic Algorithm employed to optimize • configurations. • Spatial syntax used as fitness function… • Axial arrangements selected for. • (Penn & Turner, 2002) Simple Agent: Affordances: “walkable” and “seeable” Walk three steps, look around, repeat

  24. Foyer? (from Turner, Mottram and Penn, 2004.)

  25. Re-evaluating agent modeling…

  26. Two types of control…revisited Information-based control information Environment Agent control Model-based control Planned path Emergent path

  27. information Environment Agent Behavioral dynamics control Behavioral Dynamics • Behavioral variables(Schöner, Dose & Engles, 1995) • goals expressed as (sets of) points in space spanned by behavioral variables • behavior corresponds to trajectories through that space • Behavioral Dynamics • (Fajen and Warren, 2001) • trajectories expressed as solutions to system of differential equations • attractors (intended states) and repellors (avoided states) • behavior emerges as a consequence of how information is used to adjust action system

  28. Repellor state (maxima) Attractor State (minima) Behavior corresponds to trajectories through that space?

  29. “Trajectories expressed as solutions to system of differential equations?” Mass-spring-damper Sinusoid oscillation

  30. Direction of goal g attractor of f • Direction of obstacle o repellor of f goal obstacle o g goal angle = ( - g) obstacle angle = ( - o) Dynamics of Steering & Obstacle Avoidance • Behavioral variables • Heading (f) and its rate of change () Fixed exocentric frame of reference . heading f • Behavioral dynamics • Identify factors • Develop an equation of motion • Predict routes • (Fajen & Warren, 2001) Dynamics of Steering

  31. The VENLab InterSense 900 Tracker: sonic beacons (12 x 12 m) microphones inertia cube Kaiser Proview 80 HMD stereo (60˚ x 40˚) • Manipulate goals & obstacles during walking • Record paths: x and z position data

  32. Random Obstacle Fields (Warren & Belcher, 2002) 8 6 4 Z (m) 2 0 - - 4 2 0 2 4 X (m) • 8 random arrays, forward and backward • 15 trials per condition, Number of subject =10 • 8 * 15 = 120 trials per subject…10 subjects = 1200 reps • Our goal: Observe and predict paths

  33. Random Obstacles …Findings Human Model 8 8 S2 6 6 4 4 2 2 S2 S8 0 0 S8 Z (m) Array 1: -2 -1 0 1 2 -2 -1 0 1 Z (m) Array 2: -1 0 1 2 -1 0 1 2 X (m) X (m) individual differences  different set of parameters 65% of all human paths are within 1 obstacle of model

  34. Why does all this matter again? Agent-based simulation allows designers to evaluate the behavior of individuals and groups inhabiting a space. Important to iteratively re-evaluate agent modeling on the basis of emergent models from cognitive science and robotics. Deepens our understanding of the dynamic complexity of human activity and our coupling with the Built Environment.

  35. Thank You

More Related