ABSTRACT
Crowd simulations facilitate the study of how an environment layout impacts the movement and behavior of its inhabitants. However, simulations are computationally expensive, which make them infeasible when used as part of interactive systems (e.g., Computer-Assisted Design software). Machine learning models, such as neural networks (NN), can learn observed behaviors from examples, and can potentially offer a rational prediction of a crowd's behavior efficiently. To this end, we propose a method to predict the aggregate characteristics of crowd dynamics using regression neural networks (NN). We parametrize the environment, the crowd distribution and the steering method to serve as inputs to the NN models, while a number of common performance measures serve as the output. Our preliminary experiments show that our approach can help users evaluate a large number of environments efficiently.
- Aniket Bera, Sujeong Kim, and Dinesh Manocha. 2016a. Interactive Crowd-Behavior Learning for Surveillance and Training. IEEE Computer Graphics and Applications 36, 6 (2016), 37--45. Google ScholarDigital Library
- Aniket Bera, Sujeong Kim, and Dinesh Manocha. 2016b. Online parameter learning for data-driven crowd simulation and content generation. Computers & Graphics 55 (2016), 68--79. Google ScholarDigital Library
- FM Garcia, M Kapadia, and NI Badler. 2014. GPU-based dynamic search on adaptive resolution grids. IEEE International Conference on Robotics and Automation, ICRA (2014), 1631--1638.Google ScholarCross Ref
- S. J. Guy, J. Chhugani, C. Kim, N. Satish, M. Lin, D. Manocha, and P. Dubey. 2009. Clearpath: highly parallel collision avoidance for multi-agent simulation. ACM SIGGRAPH/Eurographics SCA (2009), 177--187.Google Scholar
- D. Helbing and P. Molnar. 1995. Social force model for pedestrian dynamics. Physical review 51, 5 (1995), 4282.Google Scholar
- T Huang, M Kapadia, NI Badler, and M Kallmann. 2014. Path planning for coherent and persistent groups. IEEE International Conference on Robotics and Automation, ICRA (2014), 1652--1659.Google ScholarCross Ref
- Guy S.J., Chhugani J., Curtis S., Dubey P., Lin M., and Manocha D. 2010. PLEdestrians: a least-effort approach to crowd simulation. ACM SIGGRAPH/Eurographics SCA (2010), 1--24.Google Scholar
- M Kallmann and M Kapadia. 2014. Navigation meshes and real-time dynamic planning for virtual worlds. Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH (2014), 3:1--3:81.Google ScholarDigital Library
- M. Kallmann and M. Kapadia. 2016. Geometric and discrete path planning for interactive virtual worlds. ACM SIGGRAPH (2016), 1--29.Google Scholar
- M Kapadia, A Beacco, FM Garcia, V Reddy, N Pelechano, and NI Badler. 2013a. Multidomain real-time planning in dynamic environments. The ACM SIGGRAPH / Eurographics Symposium on Computer Animation, SCA (2013), 115--124.Google Scholar
- M Kapadia, FM Garcia, CD Boatright, and NI Badler. 2013b. Dynamic search on the GPU. IEEE/RSJ International Conference on Intelligent Robots and Systems (2013), 3332--3337.Google ScholarCross Ref
- M. Kapadia, N. Pelechano, J. Allbeck, and N. Badler. 2015. Virtual crowds: steps toward behavioral realism. Vol. 7. Synthesis Lectures on Visual Computing. 1--270 pages.Google Scholar
- M. Kapadia, S. Singh, W. Hewlett, and P. Faloutsos. 2009. Egocentric affordance fields in pedestrian steering. ACM SIGGRAPH I3D (2009), 215--223.Google Scholar
- Mubbasir Kapadia, Matthew Wang, Glenn Reinman, and Petros Faloutsos. 2011a. Improved Benchmarking for Steering Algorithms. 4th International Conference on Motion in Games (2011). Google ScholarDigital Library
- Mubbasir Kapadia, Matthew Wang, Shawn Singh, Glenn Reinman, and Petros Faloutsos. 2011b. Scenario Space: Characterizing Coverage, Quality, and Failure of Steering Algorithms. ACM SIGGRAPH Symposium on Computer Animation (2011).Google ScholarDigital Library
- Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. CoRR abs/1412.6980 (2014). http://arxiv.org/abs/1412.6980Google Scholar
- K. H. Lee, M. G. Choi, Q. Hong, and J. Lee. 2007. Group behavior from video: a data-driven approach to crowd simulation. ACM SIGGRAPH/Eurographics SCA 1 (2007), 109--118.Google ScholarDigital Library
- A. Lerner, Y. Chrysanthou, and D. Lischinski. 2007. Crowds by Example. CGF 26, 3 (2007), 655--664. Google ScholarCross Ref
- L. Magee. 1990. R2 measures based on Wald and likelihood ratio joint significance tests. The American Statistician (1990), 250.Google Scholar
- R. A. Metoyer and J. K. Hodgins. 2003. Reactive pedestrian path following from examples. CASA 20 (2003), 149--156. Google ScholarCross Ref
- K Ninomiya, M Kapadia, A Shoulson, FM Garcia, and NI Badler. 2015. Planning approaches to constraint-aware navigation in dynamic environments. Journal of Visualization and Computer Animation (2015), 119--139. Google ScholarDigital Library
- N. Pelechano, J. M. Allbeck, and N. I. Badler. 2007. Controlling individual agents in high-density crowd simulation. ACM SIGGRAPH/Eurographics SCA 1 (2007), 108.Google Scholar
- C. W. Reynolds. 1987. A distributed behavioral model. ACM SIGGRAPH 21, 4 (1987), 25--34. Google ScholarDigital Library
- C. W. Reynolds. 1999. Steering behaviors for autonomous characters. GDC, Citeseer (1999), 763--782.Google Scholar
- P. Scovanner and M. F. Tappen. 2009. Learning pedestrian dynamics from the real world. In 2009 IEEE 12th International Conference on Computer Vision. 381--388. Google ScholarCross Ref
- Shawn Singh, Mubbasir Kapadia, Glenn Reinman, and Petros Faloutsos. 2009a. Steer-Bench: A Benchmark Suite for Evaluating Steering Behaviors. Computer Animation and Virtual Worlds (2009).Google Scholar
- Shawn Singh, Mubbasir Kapadia, Glenn Reinman, and Petros Faloutsos. 2009b. Steer-Suite: An Open Framework For Developing, Evaluating and Sharing Steering Algorithms. International Conference on Motion in Games (2009).Google Scholar
- S. Singh, M. Kapadia, G. Reinman, and P. Faloutsos. 2011. Footstep navigation for dynamic crowds. CAVW 22, 2-3 (2011), 151--158.Google Scholar
- J. Snape, S. J. Guy, D. Vembar, A. Lake, and M. C. Lin. 2012. Reciprocal collision avoidance and navigation for video games. Game Developers Conf. (2012).Google Scholar
- P. Torrens, X. Li, and W. A. Griffin. 2011. Building Agent-Based Walking Models by Machine-Learning on Diverse Databases of Space-Time Trajectory Samples. Transactions in GIS 15 (2011), 67--94. Google ScholarCross Ref
- Jur van den Berg, Ming C. Lin, and Dinesh Manocha. 2008. Reciprocal velocity obstacles for real-time multi-agent navigation. Proc. IEEE Int. Conf. Robotics and Automation (2008), 1928--1935.Google ScholarCross Ref
- M. Whittle. 2014. Gait analysis: an introduction. Butterworth-Heinemann.Google Scholar
Index Terms
- Characterizing the relationship between environment layout and crowd movement using machine learning
Recommendations
Physics-infused Machine Learning for Crowd Simulation
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningCrowd simulation acts as the basic component in traffic management, urban planning, and emergency management. Most existing approaches use physics-based models due to their robustness and strong generalizability, yet they fall short in fidelity since ...
The hierarchical behavior model for crowd simulation
VRCAI '09: Proceedings of the 8th International Conference on Virtual Reality Continuum and its Applications in IndustryWe present a hierarchical behavior model to simulate realistic crowd behaviors. This model is composed of two parts. One is the low density behavior module, emphasizing the autonomy and diversity of the behaviors. The other is high density behavior ...
A Role-dependent Data-driven Approach for High Density Crowd Behavior Modeling
SIGSIM-PADS '16: Proceedings of the 2016 ACM SIGSIM Conference on Principles of Advanced Discrete SimulationIn this paper, we propose a role-dependent data-driven modeling approach to simulate pedestrians' motion in high density scenes. It is commonly observed that pedestrians behave quite differently when walking in dense crowd. Some people explore routes ...
Comments