Crowd and Multi-agent Simulation


Overview

Crowd and multi-agent simulation is the process of simulating large numbers of people, creatures, or other characters, each interacting in one environment. These actors are expected to move to their goals, interact with their environment, and respond to each other. Crowd simulations have many uses, including improving architectural planning, enhancing training environments and virtual realities, and driving artificially-intelligent (AI) characters in games and movies. Our group has worked on many problems in crowd simulation, including fast, guaranteed, collision avoidance, real-time path and motion planning, crowd flows, and directed behaviors. See also our related work in Motion and Path Planning for single and multiple robots or agents.

Software

  • d-ORCA: Distributed Optimal Reciprocal Collision Avoidance, the first decentralized collision avoidance simulation package for quadrotor swarms. Users of the package can simulate a swarm of up to 50 quadrotors which can avoid collisions with each other and with static obstacles in a known environment, and easily add and test their own perception or global path planning code with the package.

  • Menge: A Modular Framework for Crowd Movement Simulation.

  • RVO2: Reciprocal Collision Avoidance for Real-Time Multi-Agent Simulation.

  • HRVO: Hybrid Reciprocal Velocity Obstacle.


Publications

Project Conference/Journal Year
d-ORCA: Distributed Optimal Reciprocal Collision Avoidance ROS Package 2019
LSwarm: Efficient Collision Avoidance for Large Swarms with Coverage Constraints in Complex Urban Scenes RA-L IROS 2019
Monitoring Access to User Defined Areas with Multi-Agent Team in Urban Environments MRS 2019
DensePeds: Pedestrian Tracking in Dense Crowds Using Front-RVO and Sparse Features IROS 2019
Stable information transfer network facilitates the emergence of collective behavior in bird flocks PRE 2018
AutoRVO: Local Navigation with Dynamic Constraints in Dense Heterogeneous Traffic ACM CSCS 2018
Efficient Reciprocal Collision Avoidance between Heterogeneous Agents Using CTMAT AAMAS 2018
PORCA: Modeling and Planning for Autonomous Driving among Many Pedestrians RA-L 2018
Pedestrian Detection in Unannotated Videos using Synthetically Generated Human-agents for Training AAAI 2018
ACMICS: an agent communication model for interacting crowd simulation AAMAS 2017
PRVO: Probabilistic Reciprocal Velocity Obstacle for Multi Robot Navigation under Uncertainty IROS 2017
Efficient Multi-Agent Global Navigation Using Interpolating Bridges ICRA 2017
LCrowdV: Procedural framework for generating crowd videos ECCVW 2016
WarpDriver: context-aware probabilistic motion prediction for crowd simulation SIGGRAPH Asia 2016
Interactive Crowd Simulation Using Elliptical Agents ICRA 2016
PedVR: Simulating Gaze-Based Interactions between a Real User and Virtual Crowds ACM VRST 2016
Procedural framework for generating crowd videos ECCV Workshop 2016
Realtime Crowd Tracking and Data-Driven Simulation ICRA, IEEE VR, ISM, Computers & Graphics 2016
GLMP – Realtime Pedestrian Path Prediction using Global and Local Movement Patterns ICRA 2016
Interactive and Adaptive Data-Driven Crowd Simulation IEEE VR 2016
Online parameter learning for data-driven crowd simulation and content generation Computers & Graphics 2016
Menge: A Modular Framework for Crowd Movement Simulation Software Package/Collective Dynamics 2016
BSwarm: Biologically-Plausible Dynamics Model of Insect Swarms SCA 2015
Biologically-Inspired Visual Simulation of Insect Swarms EUROGRAPHICS 2015
Efficient Trajectory Extraction and Parameter Learning for Data-Driven Crowd Simulation GI 2015
Generating Pedestrian Trajectories Consistent with the Fundamental Diagram Based on Physiological and Psychological Factors PLOS ONE 2015
Interactive Crowd Content Generation and Analysis using Trajectory-level Behavior Learning ISM 2015
REACH – Realtime Crowd tracking using a Hybrid motion model ICRA 2015
Predicting Pedestrian Trajectories using Velocity-Space Reasoning IJRR 2015
Ped-Air: a Simulator for Loading, Unloading, and Evacuating Aircraft Pedestrian and Evacuation Dynamics 2014
DenseSense: Interactive Crowd Simulation using Density-Dependent Filters SCA 2014
Realtime Multilevel Crowd Tracking ICPR 2014
Parameter Estimation and Comparative Evaluation of Crowd Simulations EUROGRAPHICS 2014
Hybrid Long-Range Collision Avoidance for Crowd Simulation I3D 2013/IEEE TVCG 2014
Crowd Simulation for Games Software Package -
Velocity-Based Modeling of Physical Interactions in Multi-Agent Simulations SCA/Visual Computer 2013
A Statistical Similarity Measure for Aggregate Crowd Dynamics SIGGRAPH Asia 2012
Interactive Simulation of Dynamic Crowd Behaviors using General Adaptation Syndrome Theory I3D 2012
Optimal Reciprocal Collision Avoidance ISRR 2011
Pedestrian Velocity Obstacles: Pedestrian Simulation through Reasoning in Velocity Space PED 2012
Simulation and Analysis of Large Crowds (e.g. Crowd Modeling in Mataf, Mecca) Visual Analysis of Large Crowds 2011
Simulating Heterogeneous Crowd Behaviors Using Personality Trait Theory SCA 2011
Directing Crowd Simulations Using Navigation Fields IEEE TVCG 2011
A Least-effort Approach to Crowd Simulation SCA 2010
Synthesizing Human Motion in Constrained Environments Humanoids, CASA 2010
Modeling Collision Avoidance Behavior for Virtual Humans AAMAS 2010
Aggregate Dynamics for Dense Crowd Simulation SIGGRAPH Asia 2009
Highly Parallel Collision Avoidance for Multi-agent Simulation SCA 2009
Composite Agents SCA 2008
Interactive Navigation of Individual Agents in Crowded Environments I3D 2008
Navigating Virtual Agents in Online Virtual Worlds Web3D Symposium 2008
Real-time Navigation of Independent Agents Using Adaptive Roadmaps VRST 2007
Real-time Path Planning for Virtual Agents in Dynamic Environments IEEE VR/TVCG 2007