A pattern-based modeling framework for simulating human-like pedestrian steering behaviors

Hu, Nan; Lees, Michael; Zhou, Suiping

doi:10.1145/2503713.2503723

Cited by 8 publications

(8 citation statements)

References 27 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these applications, one of the goals is to generate realistic group movements or emerging behaviors in the background, while the user is immersed in the scene and performing certain tasks. The realism of group movement and the ability to interact with the virtual crowds enhances the presence in the virtual environment and steering strategies [4].…”

Section: Introductionmentioning

confidence: 99%

Data-driven modeling of group entitativity in virtual environments

Bera¹,

Randhavane²,

Kubin

et al. 2018

Proceedings of the 24th ACM Symposium on Virtual Reality Software and Technology

View full text Add to dashboard Cite

Figure 1: Interactive Crowd Simulation: Our adaptive data-driven group emotion algorithm is based on a statistical scheme that dynamically learns pedestrian behavior. Our method can generate realistic trajectory-level pedestrian behaviors with varying perceptual entitativity features like friendliness, creepiness, comfort, and unnervingness. We can simulate a large number of agent groups at interactive rates. ABSTRACTWe present a data-driven algorithm to model and predict the socioemotional impact of groups on observers. Psychological research finds that highly entitative i.e. cohesive and uniform groups induce threat and unease in observers. Our algorithm models realistic trajectory-level behaviors to classify and map the motion-based entitativity of crowds. This mapping is based on a statistical scheme that dynamically learns pedestrian behavior and computes the resultant entitativity induced emotion through group motion characteristics. We also present a novel interactive multi-agent simulation algorithm to model entitative groups and conduct a VR user study to validate the socio-emotional predictive power of our algorithm. We further show that model-generated high-entitativity groups do induce more negative emotions than low-entitative groups.

show abstract

Section: Introductionmentioning

confidence: 99%

Data-driven modeling of group entitativity in virtual environments

Bera¹,

Randhavane²,

Kubin

et al. 2018

Proceedings of the 24th ACM Symposium on Virtual Reality Software and Technology

View full text Add to dashboard Cite

show abstract

“…One promising approach is agent-based modelling (ABM), which treats individuals as agents that can perceive, decide and act independently based on some rules [4]. From the ABM perspective, crowd dynamics emerge from the motions of individuals, and the motions can be generated through a simplified two-layer movement model [5].…”

Section: Introductionmentioning

confidence: 99%

Guide them through: An automatic crowd control framework using multi-objective genetic programming

Zhong

Zhou

et al. 2018

Applied Soft Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…least biomechanical energy spent [GCC*10], collision‐free velocities which are closest to the preferred velocities [VDBGLM11] and a set of rules that employed by all agents in crowd [Rey99]. In order to reproduce complex crowd behaviours, some researchers include personal attributes such as personality, emotion, group interactions and cultural difference [MT97, ALL*11, SJCO06, LZC*08] in their models, or define more finely tuned situation‐specific rules and strategies [ST05, LMM03, SGC04, HLZ13]. However, identifying the correct rules that influence pedestrian's motions requires a great amount of domain knowledge and besides, the wide variety of steering behaviours are difficult to generate by considering only a limited number of factors.…”

Section: Introductionmentioning

confidence: 99%

CLUST: Simulating Realistic Crowd Behaviour by Mining Pattern from Crowd Videos

Zhao

Cai

Turner

2017

Computer Graphics Forum

View full text Add to dashboard Cite

In this paper, we present a data‐driven approach to simulate realistic locomotion of virtual pedestrians. We focus on simulating low‐level pedestrians' motion, where a pedestrian's motion is mainly affected by other pedestrians and static obstacles nearby, and the preferred velocities of agents (direction and speed) are obtained from higher level path planning models. Before the simulation, collision avoidance processes (i.e. examples) are extracted from videos to describe how pedestrians avoid collisions, which are then clustered using hierarchical clustering algorithm with a novel distance function to find similar patterns of pedestrians' collision avoidance behaviours. During the simulation, at each time step, the perceived state of each agent is classified into one cluster using a neural network trained before the simulation. A sequence of velocity vectors, representing the agent's future motion, is selected among the examples corresponding to the chosen cluster. The proposed CLUST model is trained and applied to different real‐world datasets to evaluate its generality and effectiveness both qualitatively and quantitatively. The simulation results demonstrate that the proposed model can generate realistic crowd behaviours with comparable computational cost.

show abstract

A pattern-based modeling framework for simulating human-like pedestrian steering behaviors

Cited by 8 publications

References 27 publications

Data-driven modeling of group entitativity in virtual environments

Data-driven modeling of group entitativity in virtual environments

Guide them through: An automatic crowd control framework using multi-objective genetic programming

CLUST: Simulating Realistic Crowd Behaviour by Mining Pattern from Crowd Videos

Contact Info

Product

Resources

About