Real-time Path Planning and Navigation for Multi-Agent and Heterogeneous Crowd Simulation

Size: px
Start display at page:

Download "Real-time Path Planning and Navigation for Multi-Agent and Heterogeneous Crowd Simulation"

Transcription

1 Real-time Path Planning and Navigation for Multi-Agent and Heterogeneous Crowd Simulation Ming C. Lin Department of Computer Science University of North Carolina at Chapel Hill Joint work with Avneesh Sud, Russell Gayle, Jur Van den Berg, Sean Curtis, Stephen Guy, Erik Andersen, and Dinesh Manocha Problem Definition Navigating to goal - important behavior in multiple agents (robots or virtual agents) simulation Navigation requires path planning Compute collision-free paths Satisfy constraints on the path

2 Applications Training and Mission Rehearsal Disaster Response Urban Warfare Multi-robot planning Human-Robot Interaction Demining Scenario Evaluation Evacuation Planning New Territory Exploration Challenges Path planning for multiple (thousands of) independent agents simultaneously Each agent is a dynamic obstacle Exact path planning for each agent in dynamic environments difficult

3 Goal Real-time path planning for heterogeneous crowds Non uniform distribution Independent goals Indoor Environment: Tradeshow Goal Real-time path planning for heterogeneous crowds Non uniform distribution Independent goals Large urban environments

4 Goal Real-time path planning for heterogeneous crowds in dynamic environments Moving obstacles Evolving navigable regions Weapons effects Safety zones Real-time Path Planning for Virtual Agents in Dynamic Environments [Sud et al.; IEEE VR 2007]

5 Multi-Agent Navigation Graph Unified data structure for path planning of multiple agents Computed using 1 st and 2 nd order Voronoi diagrams Multi-Agent Navigation Graph Unified data structure for path planning of multiple agents Computed using 1 st and 2 nd order Voronoi diagrams Advantage: Provides pairwise proximity information for all agents simultaneously Compute collision free paths of all agents from single MaNG

6 1 st Order Voronoi Diagram (VD 1 ) Agents Static Obstacle 1 st Order Voronoi Diagram (VD 1 ) Agents Static Obstacle

7 2 nd Order Voronoi Diagram (VD 2 ) VD 1 and VD 2 VD 1 VD 2

8 Voronoi Graphs VG 1 U VG 2 2 nd nearest nbr graph 2 nd order Voronoi graph 1 st order Voronoi graph

9 MaNG Subset of the 2 nd nearest neighbor graph Static Obstacle Multi-Agent Navigation Graph Unified data structure for path planning of multiple agents Computed using 1 st and 2 nd order Voronoi diagrams Advantage: Reduce omputation of many 1 st order Voronoi graphs to computation of a single MaNG

10 MaNG: Planner For each agent: 1. Connect agent (source) to VG 2 edges Agent MaNG: Planner For each agent: 1. Connect agent (source) to VG 2 edges 2. Connect destination to VG 1 edges

11 MaNG: Planner For each agent: 1. Connect agent (source) to VG 2 edges 2. Connect destination to VG 1 edges 3. Assign edge weights MaNG: Planner For each agent: 1. Connect agent (source) to VG 2 edges 2. Connect destination to VG 1 edges 3. Assign edge weights 4. Graph search

12 MaNG: Planner For each time step: Compute MaNG once Compute paths for all agents from same MaNG MaNG: Planner 2 nd order Voronoi diagram gives proximity to closest obstacle [Sud et al.06] Compute force fields at each step Repulsive forces from closest obstacle

13 MaNG Computation Computing exact Voronoi diagram difficult Non-linear boundaries High complexity MaNG Computation Computing exact Voronoi diagram difficult Compute Discrete Voronoi Diagram (DVD) Interactive computation using GPU [Sud et al. 06] Culling techniques for fast 2D computation (paper)

14 MaNG Computation Computing exact Voronoi diagram difficult Compute Discrete Voronoi Diagram (DVD) Compute closest site at finite set of points Undersampling Fixed grid resolution on GPU

15 Undersampling Disconnected Voronoi regions Complex graph Solution: Local tests to reduce graph complexity without changing connectivity (paper) Demos Fruit stealing Crowds in urban environment

16 Demos Fruit stealing Dynamic goal update Swarming behavior observed Crowds in urban environment Demo: Stealing Fruit 100-Agent simulation at 9 fps

17 Demos Fruit stealing Crowds in small urban environment Dynamic obstacles Demos: Crowd 100-Agent simulation at 10 fps

18 Main Approaches Adaptive Elastic Roadmaps (AERO): Connectivity graph structure that adapts to environment updates Pedestrian Levels of Detail (PLOD): Hierarchical data structure to accelerate large-scale crowd simulations Preliminary Results Interactive global path planning and local collision avoidance among virtual agents Capture independent behavior Individual goals, states

19 Preliminary Results Interactive global path planning and local collision avoidance among virtual agents Capture independent and collective behavior Individual goals, states Lane formation, oscillations Preliminary Results: Crowd Simulation

20 Adaptive Elastic ROadmaps Global connectivity graph for simultaneous path planning Continuously adapts to dynamic environment Deforms using local force models and global constraints Coherent agent motion Adaptive Elastic ROadmaps

21 Pedestrian Levels of Detail Hierarchical data structure to accelerate large-scale simulation of heterogeneous crowds Agents adaptively clustered based on pedestrian state = dynamic state, spatial proximity, behavior Efficient selective updates Empirically observed in real pedestrian flows Pedestrian Levels of Detail

22 Overview Adaptive Elastic Roadmap Environment (Static Obstacles, Dynamic Obstacles, and Agents) Scripted Behaviors PLOD Tree Event Queue Local Dynamics Collision Detection Demo: Maze agents navigating a maze 8 entry and exit points Closeup demonstrating lane formation

23 Demo: Maze Demo: Tradeshow Tradeshow attendees navigating an indoor environment of an exhibit hall 511 Booths agents visit multiple booths, stop at certain booths

24 Demo: Tradeshow Demo: City Environment Multiple city blocks, 924 buildings 2000 pedestrians 50 moving vehicles

25 Demo: City Environment Advantages Generality No assumption on motion Efficiency Selective hierarchical updates Computation using GPUs Global path planning with independent and collective effects

26 Summary Interactive global path planning and collision avoidance among thousands of virtual agents Application to heterogeneous crowd simulation Questions?

27 April 18, 2007 Reciprocal Velocity Obstacles for Mutli-Agent Navigation Independent Navigation Continuous cycle of sensing and acting (small time step Δt) Each cycle: each agent observes other agents (position, velocity) And select a new velocity for itself for the next cycle Problem: It does not know what the other agents are going to do How to act? (i.e. what velocity to select) Global planning vs. Local navigation Basic Idea Use position information of other agent, as well as velocity Assume other agents are moving obstacles (that maintain their current velocity for a while) Feurtey 00 Lamarche, Donikian 04 Reynolds 99 Velocity Obstacles [Fiorini, Shiller, 98] Case Study 3 - Part II - Ming Lin

28 April 18, 2007 Velocity Obstacle γ(p, v) = {p + tv t > 0} VO A B(v B ) = {v A γ(p A, v A v B ) B A } Using Velocity Obstacles In each cycle, select velocity outside velocity obstacle of any moving obstacle For multi-agent navigation? Agents are not passively moving, but react on each other Result: oscillations Case Study 3 - Part II - Ming Lin

29 April 18, 2007 New Approach Prevent oscillations No communication among agents or global coordination Simple idea: instead of choosing a new velocity outside the velocity obstacle, take the average of a velocity outside the velocity obstacle and the current velocity Formalized into Reciprocal Velocity Obstacle (RVO) Reciprocal Velocity Obstacle RVO A B(v B, v A ) = {v A 2v A v A VO A B(v B )} Case Study 3 - Part II - Ming Lin

30 April 18, 2007 Using RVO In each cycle, select velocity outside reciprocal velocity obstacle of any other agent Guaranteed to give safe navigation Guaranteed to prevent oscillations We use RVO as core operator of our navigation system Multi-Agent Navigation System n agents A 1,, A n with positions p 1,, p n, velocities v 1,, v n, preferred speeds v pref 1,, v pref n and goals g 1,, g n Each time step: for each agent: Compute preferred velocity Select new velocity (RVO) Update position of agent according to new velocity Case Study 3 - Part II - Ming Lin

31 April 18, 2007 Global Path Planning Global Path Planning Preprocessing Take only static obstacles into account Visibility graph (or other roadmap) Case Study 3 - Part II - Ming Lin

32 April 18, 2007 Select Preferred Velocity During simulation For each agent: Compute shortest path using roadmap Use direction along path as preferred velocity No local minima Select New Velocity Case Study 3 - Part II - Ming Lin

33 April 18, 2007 Select New Velocity Outside the union of the reciprocal velocity obstacles, closest to preferred velocity Select New Velocity Environment may become crowded: no valid velocity Solution: select velocity inside RVO but penalize Expected time to collision Distance to preferred velocity Select velocity with minimal penalty Case Study 3 - Part II - Ming Lin

34 April 18, 2007 Adding Realism Orientation and Kinodynamics Inferring Orientation Orientation in direction of motion Side-steps? Backsteps? Kinodynamic constraints Maximum velocity Maximum acceleration More complicated based on orientation Case Study 3 - Part II - Ming Lin

35 April 18, 2007 Selecting Neighbors Neighbor region More region (based on orientation) Results - Stadium scenario 250 agents entering a stadium four narrow entrances forming the word I3D2008 on the field 97 fps (without visualization) on an 8-core Intel Xeon 2.66 GHz Case Study 3 - Part II - Ming Lin

36 April 18, 2007 Results - Stadium scenario Results - Office scenario 1000 agents evacuating an office building two narrow exits densely crowded scenario 46 fps (without visualization) on an 8-core Intel Xeon 2.66 GHz Case Study 3 - Part II - Ming Lin

37 April 18, 2007 Results - Office scenario Results - Crosswalk scenario 100 agents in each corner of the crossroads move to other side of street opposite flow of agents: automatic lane formation 57 fps (without visualization) on an 8-core Intel Xeon 2.66 GHz Case Study 3 - Part II - Ming Lin

38 April 18, 2007 Results - Crosswalk scenario System Demonstrations Real-time Capture Case Study 3 - Part II - Ming Lin

39 April 18, 2007 Extension to 3D 500 agents on a sphere moving to the other side Composite Agents Case Study 3 - Part II - Ming Lin

40 April 18, 2007 Results - Scalability Performance (16 cores, Sitterson scene) Performance (5000 agents, Sitterson scene) Running time (sec/frame) Number of Agents Frame rate (frame/sec) Number of Cores Summary Powerful and simple (easy to implement) local collision avoidance technique for multi-agent navigation Allows for easy integration with global planning, kinodynamic constraints, visibility constraints, etc. Scalable with number of agents and number of processors used Application to Crowd Simulation & Games Case Study 3 - Part II - Ming Lin

41 April 18, 2007 Research Sponsors Army Research Office Defense Advanced Research Projects Agency Department of Energy (Fellowship) Intel Corporation National Science Foundation RDECOM Case Study 3 - Part II - Ming Lin

Collaborators. Multiple Agents & Crowd Simulation: training sytems 5/15/2010. Interactive Multi-Robot Planning and Multi-Agent Simulation

Collaborators. Multiple Agents & Crowd Simulation: training sytems 5/15/2010. Interactive Multi-Robot Planning and Multi-Agent Simulation Interactive Multi-Robot Planning and Multi-Agent Simulation Dinesh Manocha UNC Chapel Hill dm@cs.unc.edu http://gamma.cs.unc.edu Collaborators Ming C. Lin Jur van der Berg Sean Curtis Russell Gayle Stephen

More information

Multi Agent Navigation on GPU. Avi Bleiweiss

Multi Agent Navigation on GPU. Avi Bleiweiss Multi Agent Navigation on GPU Avi Bleiweiss Reasoning Explicit Implicit Script, storytelling State machine, serial Compute intensive Fits SIMT architecture well Navigation planning Collision avoidance

More information

Crowd simulation. Taku Komura

Crowd simulation. Taku Komura Crowd simulation Taku Komura Animating Crowds We have been going through methods to simulate individual characters What if we want to simulate the movement of crowds? Pedestrians in the streets Flock of

More information

Reciprocal Collision Avoidance and Navigation for Video Games

Reciprocal Collision Avoidance and Navigation for Video Games Reciprocal Collision Avoidance and Navigation for Video Games Jamie Snape, 1 Stephen J. Guy, 1 Deepak Vembar, 2 Adam Lake, 2 Ming C. Lin, 1 and Dinesh Manocha 11 1. Introduction COLLISION AVOIDANCE AND

More information

Scalable Multi Agent Simulation on the GPU. Avi Bleiweiss NVIDIA Corporation San Jose, 2009

Scalable Multi Agent Simulation on the GPU. Avi Bleiweiss NVIDIA Corporation San Jose, 2009 Scalable Multi Agent Simulation on the GPU Avi Bleiweiss NVIDIA Corporation San Jose, 2009 Reasoning Explicit State machine, serial Implicit Compute intensive Fits SIMT well Collision avoidance Motivation

More information

Interactive Modeling, Simulation and Control of Large-Scale Crowds and Traffic

Interactive Modeling, Simulation and Control of Large-Scale Crowds and Traffic Interactive Modeling, Simulation and Control of Large-Scale Crowds and Traffic Ming C. Lin 1, Stephen Guy 1,RahulNarain 1, Jason Sewall 1, Sachin Patil 1, Jatin Chhugani 2, Abhinav Golas 1,JurvandenBerg

More information

Simulating Group Formations Using RVO

Simulating Group Formations Using RVO Simulating Group Formations Using RVO Martin Funkquist martinfu@kth.se Supervisor: Christopher Peters Staffan Sandberg stsand@kth.se May 25, 2016 Figure 1: From left to right. First figure displays a real

More information

Deformable Distance Fields for Simulation of Non- Penetrating Flexible Bodies

Deformable Distance Fields for Simulation of Non- Penetrating Flexible Bodies Deformable Distance Fields for Simulation of Non- Penetrating Flexible Bodies Susan Fisher and Ming C. Lin {sfisher, lin}@cs.unc.edu http://gamma.cs.unc.edu/ddf/ Department of Computer Science University

More information

Goal Velocity Obstacles for Spatial Navigation of Multiple Autonomous Robots or Virtual Agents

Goal Velocity Obstacles for Spatial Navigation of Multiple Autonomous Robots or Virtual Agents Goal Velocity Obstacles for Spatial Navigation of Multiple utonomous Robots or Virtual gents Jamie Snape and Dinesh Manocha University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 {snape,dm}@cs.unc.edu

More information

DiFi: Distance Fields - Fast Computation Using Graphics Hardware

DiFi: Distance Fields - Fast Computation Using Graphics Hardware DiFi: Distance Fields - Fast Computation Using Graphics Hardware Avneesh Sud Dinesh Manocha UNC-Chapel Hill http://gamma.cs.unc.edu/difi Distance Fields Distance Function For a site a scalar function f:r

More information

Robot Motion Planning

Robot Motion Planning Robot Motion Planning James Bruce Computer Science Department Carnegie Mellon University April 7, 2004 Agent Planning An agent is a situated entity which can choose and execute actions within in an environment.

More information

Real-time Simulation of Heterogeneous Crowds

Real-time Simulation of Heterogeneous Crowds Real-time Simulation of Heterogeneous Crowds Avneesh Sud Russell Gayle Stephen Guy Erik Andersen Ming Lin Dinesh Manocha Dept of Computer Science, University of North Carolina at Chapel Hill Figure 1:

More information

A Predictive Collision Avoidance Model for Pedestrian Simulation

A Predictive Collision Avoidance Model for Pedestrian Simulation A Predictive Collision Avoidance Model for Pedestrian Simulation Ioannis Karamouzas, Peter Heil, Pascal van Beek, and Mark H. Overmars Center for Advanced Gaming and Simulation, Utrecht University, The

More information

ACCELERATING ROUTE PLANNING AND COLLISION DETECTION FOR COMPUTER GENERATED FORCES USING GPUS

ACCELERATING ROUTE PLANNING AND COLLISION DETECTION FOR COMPUTER GENERATED FORCES USING GPUS ACCELERATING ROUTE PLANNING AND COLLISION DETECTION FOR COMPUTER GENERATED FORCES USING GPUS David Tuft, Russell Gayle, Brian Salomon, Naga Govindaraju, Ming Lin, and Dinesh Manocha University of North

More information

Collision Avoidance with Unity3d

Collision Avoidance with Unity3d Collision Avoidance with Unity3d Jassiem Ifill September 12, 2013 Abstract The primary goal of the research presented in this paper is to achieve natural crowd simulation and collision avoidance within

More information

Modeling Collision Avoidance Behavior for Virtual Humans

Modeling Collision Avoidance Behavior for Virtual Humans Modeling Collision voidance Behavior for Virtual Humans Stephen J. Guy Dept. of Computer Science UNC - Chapel Hill, NC sjguy@cs.unc.edu Ming C. Lin Dept. of Computer Science UNC - Chapel Hill, NC lin@cs.unc.edu

More information

Goal. Interactive Walkthroughs using Multiple GPUs. Boeing 777. DoubleEagle Tanker Model

Goal. Interactive Walkthroughs using Multiple GPUs. Boeing 777. DoubleEagle Tanker Model Goal Interactive Walkthroughs using Multiple GPUs Dinesh Manocha University of North Carolina- Chapel Hill http://www.cs.unc.edu/~walk SIGGRAPH COURSE #11, 2003 Interactive Walkthrough of complex 3D environments

More information

Probabilistic Methods for Kinodynamic Path Planning

Probabilistic Methods for Kinodynamic Path Planning 16.412/6.834J Cognitive Robotics February 7 th, 2005 Probabilistic Methods for Kinodynamic Path Planning Based on Past Student Lectures by: Paul Elliott, Aisha Walcott, Nathan Ickes and Stanislav Funiak

More information

Robot Motion Planning

Robot Motion Planning Robot Motion Planning slides by Jan Faigl Department of Computer Science and Engineering Faculty of Electrical Engineering, Czech Technical University in Prague lecture A4M36PAH - Planning and Games Dpt.

More information

Introduction to State-of-the-art Motion Planning Algorithms. Presented by Konstantinos Tsianos

Introduction to State-of-the-art Motion Planning Algorithms. Presented by Konstantinos Tsianos Introduction to State-of-the-art Motion Planning Algorithms Presented by Konstantinos Tsianos Robots need to move! Motion Robot motion must be continuous Geometric constraints Dynamic constraints Safety

More information

Path Planning. Marcello Restelli. Dipartimento di Elettronica e Informazione Politecnico di Milano tel:

Path Planning. Marcello Restelli. Dipartimento di Elettronica e Informazione Politecnico di Milano   tel: Marcello Restelli Dipartimento di Elettronica e Informazione Politecnico di Milano email: restelli@elet.polimi.it tel: 02 2399 3470 Path Planning Robotica for Computer Engineering students A.A. 2006/2007

More information

Fast Proximity Computation among Deformable Models Using Discrete Voronoi Diagrams

Fast Proximity Computation among Deformable Models Using Discrete Voronoi Diagrams Fast Proximity Computation among Deformable Models Using Discrete Voronoi Diagrams Avneesh Sud Naga Govindaraju Russell Gayle Ilknur Kabul Dinesh Manocha Dept of Computer Science, University of North Carolina

More information

Efficient Multi-Agent Global Navigation Using Interpolating Bridges

Efficient Multi-Agent Global Navigation Using Interpolating Bridges Efficient Multi-Agent Global Navigation Using Interpolating Bridges Liang He 1 and Jia Pan 2 and Dinesh Manocha 1 Abstract We present a novel approach for collision-free global navigation for continuous-time

More information

Collision Detection. These slides are mainly from Ming Lin s course notes at UNC Chapel Hill

Collision Detection. These slides are mainly from Ming Lin s course notes at UNC Chapel Hill Collision Detection These slides are mainly from Ming Lin s course notes at UNC Chapel Hill http://www.cs.unc.edu/~lin/comp259-s06/ Computer Animation ILE5030 Computer Animation and Special Effects 2 Haptic

More information

Collision Detection II. These slides are mainly from Ming Lin s course notes at UNC Chapel Hill

Collision Detection II. These slides are mainly from Ming Lin s course notes at UNC Chapel Hill Collision Detection II These slides are mainly from Ming Lin s course notes at UNC Chapel Hill http://www.cs.unc.edu/~lin/comp259-s06/ Some Possible Approaches Geometric methods Algebraic techniques Hierarchical

More information

Autonomous Mobile Robots, Chapter 6 Planning and Navigation Where am I going? How do I get there? Localization. Cognition. Real World Environment

Autonomous Mobile Robots, Chapter 6 Planning and Navigation Where am I going? How do I get there? Localization. Cognition. Real World Environment Planning and Navigation Where am I going? How do I get there?? Localization "Position" Global Map Cognition Environment Model Local Map Perception Real World Environment Path Motion Control Competencies

More information

Geometric Path Planning McGill COMP 765 Oct 12 th, 2017

Geometric Path Planning McGill COMP 765 Oct 12 th, 2017 Geometric Path Planning McGill COMP 765 Oct 12 th, 2017 The Motion Planning Problem Intuition: Find a safe path/trajectory from start to goal More precisely: A path is a series of robot configurations

More information

Collision Detection. Motivation - Dynamic Simulation ETH Zurich. Motivation - Path Planning ETH Zurich. Motivation - Biomedical Simulation ETH Zurich

Collision Detection. Motivation - Dynamic Simulation ETH Zurich. Motivation - Path Planning ETH Zurich. Motivation - Biomedical Simulation ETH Zurich Collision Detection Motivation - Dynamic Simulation Collision detection is an essential part of physically realistic dynamic simulations. For each time step: compute dynamics detect collisions resolve

More information

Motion Planning. Howie CHoset

Motion Planning. Howie CHoset Motion Planning Howie CHoset Questions Where are we? Where do we go? Which is more important? Encoders Encoders Incremental Photodetector Encoder disk LED Photoemitter Encoders - Incremental Encoders -

More information

Agent Based Intersection Traffic Simulation

Agent Based Intersection Traffic Simulation Agent Based Intersection Traffic Simulation David Wilkie May 7, 2009 Abstract This project focuses on simulating the traffic at an intersection using agent-based planning and behavioral methods. The motivation

More information

arxiv: v1 [cs.cv] 27 Sep 2018

arxiv: v1 [cs.cv] 27 Sep 2018 Interactive Surveillance Technologies for Dense Crowds Aniket Bera Department of Computer Science University of North Carolina at Chapel Hill Chapel Hill, NC Dinesh Manocha Department of Computer Science

More information

Space-time Group Motion Planning

Space-time Group Motion Planning Space-time Group Motion Planning Ioannis Karamouzas, Roland Geraerts, A. Frank van der Stappen Abstract We present a novel approach for planning and directing heterogeneous groups of virtual agents based

More information

Robotics Tasks. CS 188: Artificial Intelligence Spring Manipulator Robots. Mobile Robots. Degrees of Freedom. Sensors and Effectors

Robotics Tasks. CS 188: Artificial Intelligence Spring Manipulator Robots. Mobile Robots. Degrees of Freedom. Sensors and Effectors CS 188: Artificial Intelligence Spring 2006 Lecture 5: Robot Motion Planning 1/31/2006 Dan Klein UC Berkeley Many slides from either Stuart Russell or Andrew Moore Motion planning (today) How to move from

More information

GPU-based Distributed Behavior Models with CUDA

GPU-based Distributed Behavior Models with CUDA GPU-based Distributed Behavior Models with CUDA Courtesy: YouTube, ISIS Lab, Universita degli Studi di Salerno Bradly Alicea Introduction Flocking: Reynolds boids algorithm. * models simple local behaviors

More information

Reactive Deformation Roadmaps: Motion Planning of Multiple Robots in Dynamic Environments

Reactive Deformation Roadmaps: Motion Planning of Multiple Robots in Dynamic Environments Reactive Deformation Roadmaps: Motion Planning of Multiple Robots in Dynamic Environments Russell Gayle Avneesh Sud Ming C. Lin Dinesh Manocha Department of Computer Science University of North Carolina

More information

Strategies for simulating pedestrian navigation with multiple reinforcement learning agents

Strategies for simulating pedestrian navigation with multiple reinforcement learning agents Strategies for simulating pedestrian navigation with multiple reinforcement learning agents Francisco Martinez-Gil, Miguel Lozano, Fernando Ferna ndez Presented by: Daniel Geschwender 9/29/2016 1 Overview

More information

Navigation Queries from Triangular Meshes

Navigation Queries from Triangular Meshes In Proceedings of the Third International Conference on Motion in Games (MIG), 2010 Navigation Queries from Triangular Meshes Marcelo Kallmann University of California, Merced Abstract. Navigation meshes

More information

CS 4649/7649 Robot Intelligence: Planning

CS 4649/7649 Robot Intelligence: Planning CS 4649/7649 Robot Intelligence: Planning Probabilistic Roadmaps Sungmoon Joo School of Interactive Computing College of Computing Georgia Institute of Technology S. Joo (sungmoon.joo@cc.gatech.edu) 1

More information

Collision and Proximity Queries

Collision and Proximity Queries Collision and Proximity Queries Dinesh Manocha (based on slides from Ming Lin) COMP790-058 Fall 2013 Geometric Proximity Queries l Given two object, how would you check: If they intersect with each other

More information

Graphs, Search, Pathfinding (behavior involving where to go) Steering, Flocking, Formations (behavior involving how to go)

Graphs, Search, Pathfinding (behavior involving where to go) Steering, Flocking, Formations (behavior involving how to go) Graphs, Search, Pathfinding (behavior involving where to go) Steering, Flocking, Formations (behavior involving how to go) Class N-2 1. What are some benefits of path networks? 2. Cons of path networks?

More information

Real-Time Multi-Agent Path Planning on Arbitrary Surfaces

Real-Time Multi-Agent Path Planning on Arbitrary Surfaces Real-Time Multi-Agent Path Planning on Arbitrary Surfaces Rafael P. Torchelsen1 Luiz F. Scheidegger1 Guilherme N. Oliveira1 Rui Bastos2 Joa o L. D. Comba1 1 Instituto de Informa tica - PPGC, UFRGS - Brazil

More information

Aggregate Dynamics for Dense Crowd Simulation

Aggregate Dynamics for Dense Crowd Simulation Aggregate Dynamics for Dense Crowd Simulation Rahul Narain Abhinav Golas Sean Curtis Ming C. Lin University of North Carolina at Chapel Hill (a) (b) (c) Figure 1: Some examples of large, dense crowds simulated

More information

Crowd simulation. Summerschool Utrecht: Multidisciplinary Game Research. Dr. Roland Geraerts 23 August 2017

Crowd simulation. Summerschool Utrecht: Multidisciplinary Game Research. Dr. Roland Geraerts 23 August 2017 Crowd simulation Summerschool Utrecht: Multidisciplinary Game Research Dr. Roland Geraerts 23 August 2017 1 Societal relevance of crowd simulation The number of environments with big crowds are growing

More information

Collision Avoidance for Preplanned Locomotion

Collision Avoidance for Preplanned Locomotion 22 Collision Avoidance for Preplanned Locomotion Bobby Anguelov 22.1 Introduction 22.2 Collision Avoidance for Preplanned Locomotion 22.3 Collision Detection and Trivial Collision Resolution 22.4 Nontrivial

More information

Multi Agent Navigation on the GPU

Multi Agent Navigation on the GPU Multi Agent Navigation on the GPU Avi Bleiweiss NVIDIA Corporation ableiweiss@nvidia.com Abstract We present a unique and elegant graphics hardware realization of multi agent simulation. Specifically,

More information

Chapter 12. Path Planning. Beard & McLain, Small Unmanned Aircraft, Princeton University Press, 2012,

Chapter 12. Path Planning. Beard & McLain, Small Unmanned Aircraft, Princeton University Press, 2012, Chapter 12 Path Planning Beard & McLain, Small Unmanned Aircraft, Princeton University Press, 212, Chapter 12: Slide 1 Control Architecture destination, obstacles map path planner waypoints status path

More information

Algorithms for Sensor-Based Robotics: Sampling-Based Motion Planning

Algorithms for Sensor-Based Robotics: Sampling-Based Motion Planning Algorithms for Sensor-Based Robotics: Sampling-Based Motion Planning Computer Science 336 http://www.cs.jhu.edu/~hager/teaching/cs336 Professor Hager http://www.cs.jhu.edu/~hager Recall Earlier Methods

More information

Robot Motion Control Matteo Matteucci

Robot Motion Control Matteo Matteucci Robot Motion Control Open loop control A mobile robot is meant to move from one place to another Pre-compute a smooth trajectory based on motion segments (e.g., line and circle segments) from start to

More information

CAB: Fast Update of OBB Trees for Collision Detection between Articulated Bodies

CAB: Fast Update of OBB Trees for Collision Detection between Articulated Bodies CAB: Fast Update of OBB Trees for Collision Detection between Articulated Bodies Harald Schmidl Nolan Walker Ming C. Lin {schmidl walkern lin}@cs.unc.edu Department of Computer Science Sitterson Hall,

More information

Sung-Eui Yoon ( 윤성의 )

Sung-Eui Yoon ( 윤성의 ) Path Planning for Point Robots Sung-Eui Yoon ( 윤성의 ) Course URL: http://sglab.kaist.ac.kr/~sungeui/mpa Class Objectives Motion planning framework Classic motion planning approaches 2 3 Configuration Space:

More information

Announcements. CS 188: Artificial Intelligence Fall Robot motion planning! Today. Robotics Tasks. Mobile Robots

Announcements. CS 188: Artificial Intelligence Fall Robot motion planning! Today. Robotics Tasks. Mobile Robots CS 188: Artificial Intelligence Fall 2007 Lecture 6: Robot Motion Planning 9/13/2007 Announcements Project 1 due (yesterday)! Project 2 (Pacman with ghosts) up in a few days Reminder: you are allowed to

More information

CS 188: Artificial Intelligence Fall Announcements

CS 188: Artificial Intelligence Fall Announcements CS 188: Artificial Intelligence Fall 2007 Lecture 6: Robot Motion Planning 9/13/2007 Dan Klein UC Berkeley Many slides over the course adapted from either Stuart Russell or Andrew Moore Announcements Project

More information

A comparative study of k-nearest neighbour techniques in crowd simulation

A comparative study of k-nearest neighbour techniques in crowd simulation A comparative study of k-nearest neighbour techniques in crowd simulation Jordi Vermeulen Arne Hillebrand Roland Geraerts Department of Information and Computing Sciences Utrecht University, The Netherlands

More information

Realtime Anomaly Detection using Trajectory-level Crowd Behavior Learning

Realtime Anomaly Detection using Trajectory-level Crowd Behavior Learning Realtime Anomaly Detection using Trajectory-level Crowd Behavior Learning Aniket Bera University of North Carolina Chapel Hill, NC, USA ab@cs.unc.edu Sujeong Kim SRI International Princeton, NJ, USA sujeong.kim@sri.com

More information

Deformable and Fracturing Objects

Deformable and Fracturing Objects Interactive ti Collision i Detection ti for Deformable and Fracturing Objects Sung-Eui Yoon ( 윤성의 ) IWON associate professor KAIST http://sglab.kaist.ac.kr/~sungeui/ Acknowledgements Research collaborators

More information

DenseSense: Interactive Crowd Simulation using Density-Dependent Filters

DenseSense: Interactive Crowd Simulation using Density-Dependent Filters Eurographics/ ACM SIGGRAPH Symposium on Computer Animation (2014) Vladlen Koltun and Eftychios Sifakis (Editors) DenseSense: Interactive Crowd Simulation using Density-Dependent Filters A. Best and S.

More information

Planning in Mobile Robotics

Planning in Mobile Robotics Planning in Mobile Robotics Part I. Miroslav Kulich Intelligent and Mobile Robotics Group Gerstner Laboratory for Intelligent Decision Making and Control Czech Technical University in Prague Tuesday 26/07/2011

More information

CS 378: Computer Game Technology

CS 378: Computer Game Technology CS 378: Computer Game Technology Dynamic Path Planning, Flocking Spring 2012 University of Texas at Austin CS 378 Game Technology Don Fussell Dynamic Path Planning! What happens when the environment changes

More information

ECE276B: Planning & Learning in Robotics Lecture 5: Configuration Space

ECE276B: Planning & Learning in Robotics Lecture 5: Configuration Space ECE276B: Planning & Learning in Robotics Lecture 5: Configuration Space Lecturer: Nikolay Atanasov: natanasov@ucsd.edu Teaching Assistants: Tianyu Wang: tiw161@eng.ucsd.edu Yongxi Lu: yol070@eng.ucsd.edu

More information

Collision Detection based on Spatial Partitioning

Collision Detection based on Spatial Partitioning Simulation in Computer Graphics Collision Detection based on Spatial Partitioning Matthias Teschner Computer Science Department University of Freiburg Outline introduction uniform grid Octree and k-d tree

More information

Fast Line-of-Sight Computations in Complex Environments

Fast Line-of-Sight Computations in Complex Environments Fast Line-of-Sight Computations in Complex Environments David Tuft Brian Salomon Sean Hanlon Dinesh Manocha Dept. of Computer Science Univ. of North Carolina at Chapel Hill Chapel Hill, NC 27599-3175 USA

More information

Automatic Construction of High Quality Roadmaps for Path Planning

Automatic Construction of High Quality Roadmaps for Path Planning Automatic Construction of High Quality Roadmaps for Path Planning D.Nieuwenhuisen A.Kamphuis M.Mooijekind M.H.Overmars institute of information and computing sciences, utrecht university technical report

More information

CS 231. Crowd Simulation. Outline. Introduction to Crowd Simulation. Flocking Social Forces 2D Cellular Automaton Continuum Crowds

CS 231. Crowd Simulation. Outline. Introduction to Crowd Simulation. Flocking Social Forces 2D Cellular Automaton Continuum Crowds CS 231 Crowd Simulation Outline Introduction to Crowd Simulation Fields of Study & Applications Visualization vs. Realism Microscopic vs. Macroscopic Flocking Social Forces 2D Cellular Automaton Continuum

More information

Real-time Continuous Collision Detection and Penetration Depth Computation

Real-time Continuous Collision Detection and Penetration Depth Computation Real-time Continuous Collision Detection and Penetration Depth Computation Young J. Kim http://graphics.ewha.ac.kr Ewha Womans University Non-penetration Constraint No overlap between geometric objects

More information

Local Search Methods. CS 188: Artificial Intelligence Fall Announcements. Hill Climbing. Hill Climbing Diagram. Today

Local Search Methods. CS 188: Artificial Intelligence Fall Announcements. Hill Climbing. Hill Climbing Diagram. Today CS 188: Artificial Intelligence Fall 2006 Lecture 5: Robot Motion Planning 9/14/2006 Local Search Methods Queue-based algorithms keep fallback options (backtracking) Local search: improve what you have

More information

Large Scale Crowd Simulation Using A Hybrid Agent Model

Large Scale Crowd Simulation Using A Hybrid Agent Model Large Scale Crowd Simulation Using A Hybrid Agent Model Seung In Park 1, Yong Cao 1, Francis Quek 1 1 Department of Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, Virginia,

More information

Robotic Motion Planning: Review C-Space and Start Potential Functions

Robotic Motion Planning: Review C-Space and Start Potential Functions Robotic Motion Planning: Review C-Space and Start Potential Functions Robotics Institute 16-735 http://www.cs.cmu.edu/~motionplanning Howie Choset http://www.cs.cmu.edu/~choset What if the robot is not

More information

Particle Systems. Typical Time Step. Particle Generation. Controlling Groups of Objects: Particle Systems. Flocks and Schools

Particle Systems. Typical Time Step. Particle Generation. Controlling Groups of Objects: Particle Systems. Flocks and Schools Particle Systems Controlling Groups of Objects: Particle Systems Flocks and Schools A complex, fuzzy system represented by a large collection of individual elements. Each element has simple behavior and

More information

Collision Detection with Bounding Volume Hierarchies

Collision Detection with Bounding Volume Hierarchies Simulation in Computer Graphics Collision Detection with Bounding Volume Hierarchies Matthias Teschner Computer Science Department University of Freiburg Outline introduction bounding volumes BV hierarchies

More information

CMU-Q Lecture 4: Path Planning. Teacher: Gianni A. Di Caro

CMU-Q Lecture 4: Path Planning. Teacher: Gianni A. Di Caro CMU-Q 15-381 Lecture 4: Path Planning Teacher: Gianni A. Di Caro APPLICATION: MOTION PLANNING Path planning: computing a continuous sequence ( a path ) of configurations (states) between an initial configuration

More information

video 1 video 2 Motion Planning (It s all in the discretization) Digital Actors Basic problem Basic problem Two Possible Discretizations

video 1 video 2 Motion Planning (It s all in the discretization) Digital Actors Basic problem Basic problem Two Possible Discretizations Motion Planning (It s all in the discretization) Motion planning is the ability for an agent to compute its own motions in order to achieve certain goals. ll autonomous robots and digital actors should

More information

Advanced Robotics Path Planning & Navigation

Advanced Robotics Path Planning & Navigation Advanced Robotics Path Planning & Navigation 1 Agenda Motivation Basic Definitions Configuration Space Global Planning Local Planning Obstacle Avoidance ROS Navigation Stack 2 Literature Choset, Lynch,

More information

W4. Perception & Situation Awareness & Decision making

W4. Perception & Situation Awareness & Decision making W4. Perception & Situation Awareness & Decision making Robot Perception for Dynamic environments: Outline & DP-Grids concept Dynamic Probabilistic Grids Bayesian Occupancy Filter concept Dynamic Probabilistic

More information

AUTONOMOUS TAWAF CROWD SIMULATION. Ahmad Zakwan Azizul Fata, Mohd Shafry Mohd Rahim, Sarudin Kari

AUTONOMOUS TAWAF CROWD SIMULATION. Ahmad Zakwan Azizul Fata, Mohd Shafry Mohd Rahim, Sarudin Kari BORNEO SCIENCE 36 (2): SEPTEMBER 2015 AUTONOMOUS TAWAF CROWD SIMULATION Ahmad Zakwan Azizul Fata, Mohd Shafry Mohd Rahim, Sarudin Kari MaGIC-X (Media and Games Innonovation Centre of Excellence UTM-IRDA

More information

Real-time Navigation of Independent Agents Using Adaptive Roadmaps

Real-time Navigation of Independent Agents Using Adaptive Roadmaps Real-time Navigation of Independent Agents Using Adaptive Roadmaps AvneeshSud RussellGayle ErikAndersen StephenGuy MingLin DineshManocha Dept of Computer Science, University of North Carolina at Chapel

More information

Simulation in Computer Graphics Space Subdivision. Matthias Teschner

Simulation in Computer Graphics Space Subdivision. Matthias Teschner Simulation in Computer Graphics Space Subdivision Matthias Teschner Outline Introduction Uniform grid Octree and k-d tree BSP tree University of Freiburg Computer Science Department 2 Model Partitioning

More information

Sound in Nature. Collisions lead to surface vibrations Vibrations create pressure waves in air Pressure waves are sensed by ear

Sound in Nature. Collisions lead to surface vibrations Vibrations create pressure waves in air Pressure waves are sensed by ear Sound in Nature Collisions lead to surface vibrations Vibrations create pressure waves in air Pressure waves are sensed by ear Vibration Pressure Wave Perception Physically Based Sound Generate Sounds

More information

A Fast Method for Local Penetration Depth Computation. Stephane Redon and Ming C. Lin

A Fast Method for Local Penetration Depth Computation. Stephane Redon and Ming C. Lin A Fast Method for Local Penetration Depth Computation Stephane Redon and Ming C. Lin Department of Computer Science University of North Carolina at Chapel Hill Abstract This paper presents a fast method

More information

Cognitive Robotics Robot Motion Planning Matteo Matteucci

Cognitive Robotics Robot Motion Planning Matteo Matteucci Cognitive Robotics Robot Motion Planning Robot Motion Planning eminently necessary since, by definition, a robot accomplishes tasks by moving in the real world. J.-C. Latombe (1991) Robot Motion Planning

More information

Configuration Space of a Robot

Configuration Space of a Robot Robot Path Planning Overview: 1. Visibility Graphs 2. Voronoi Graphs 3. Potential Fields 4. Sampling-Based Planners PRM: Probabilistic Roadmap Methods RRTs: Rapidly-exploring Random Trees Configuration

More information

An Open Framework for Developing, Evaluating, and Sharing Steering Algorithms

An Open Framework for Developing, Evaluating, and Sharing Steering Algorithms An Open Framework for Developing, Evaluating, and Sharing Steering Algorithms Shawn Singh, Mubbasir Kapadia, Petros Faloutsos, and Glenn Reinman University of California, Los Angeles Abstract. There are

More information

Adding Virtual Characters to the Virtual Worlds. Yiorgos Chrysanthou Department of Computer Science University of Cyprus

Adding Virtual Characters to the Virtual Worlds. Yiorgos Chrysanthou Department of Computer Science University of Cyprus Adding Virtual Characters to the Virtual Worlds Yiorgos Chrysanthou Department of Computer Science University of Cyprus Cities need people However realistic the model is, without people it does not have

More information

6.141: Robotics systems and science Lecture 10: Implementing Motion Planning

6.141: Robotics systems and science Lecture 10: Implementing Motion Planning 6.141: Robotics systems and science Lecture 10: Implementing Motion Planning Lecture Notes Prepared by N. Roy and D. Rus EECS/MIT Spring 2011 Reading: Chapter 3, and Craig: Robotics http://courses.csail.mit.edu/6.141/!

More information

Path Planning for Point Robots. NUS CS 5247 David Hsu

Path Planning for Point Robots. NUS CS 5247 David Hsu Path Planning for Point Robots NUS CS 5247 David Hsu Problem Input Robot represented as a point in the plane Obstacles represented as polygons Initial and goal positions Output A collision-free path between

More information

Variable-resolution Velocity Roadmap Generation Considering Safety Constraints for Mobile Robots

Variable-resolution Velocity Roadmap Generation Considering Safety Constraints for Mobile Robots Variable-resolution Velocity Roadmap Generation Considering Safety Constraints for Mobile Robots Jingyu Xiang, Yuichi Tazaki, Tatsuya Suzuki and B. Levedahl Abstract This research develops a new roadmap

More information

MEV 442: Introduction to Robotics - Module 3 INTRODUCTION TO ROBOT PATH PLANNING

MEV 442: Introduction to Robotics - Module 3 INTRODUCTION TO ROBOT PATH PLANNING MEV 442: Introduction to Robotics - Module 3 INTRODUCTION TO ROBOT PATH PLANNING THE PATH PLANNING PROBLEM The robot should find out a path enables the continuous motion of a robot from an initial configuration

More information

Smooth and Collision-Free Navigation for Multiple Robots Under Differential-Drive Constraints

Smooth and Collision-Free Navigation for Multiple Robots Under Differential-Drive Constraints Smooth and Collision-Free Navigation for Multiple Robots Under Differential-Drive Constraints Jamie Snape, Student Member, IEEE, Jur van den Berg, Stephen J. Guy, and Dinesh Manocha Abstract We present

More information

URBAN SCALE CROWD DATA ANALYSIS, SIMULATION, AND VISUALIZATION

URBAN SCALE CROWD DATA ANALYSIS, SIMULATION, AND VISUALIZATION www.bsc.es URBAN SCALE CROWD DATA ANALYSIS, SIMULATION, AND VISUALIZATION Isaac Rudomin May 2017 ABSTRACT We'll dive deep into how we use heterogeneous clusters with GPUs for accelerating urban-scale crowd

More information

Introduction to Information Science and Technology (IST) Part IV: Intelligent Machines and Robotics Planning

Introduction to Information Science and Technology (IST) Part IV: Intelligent Machines and Robotics Planning Introduction to Information Science and Technology (IST) Part IV: Intelligent Machines and Robotics Planning Sören Schwertfeger / 师泽仁 ShanghaiTech University ShanghaiTech University - SIST - 10.05.2017

More information

Algorithms for Sensor-Based Robotics: Sampling-Based Motion Planning

Algorithms for Sensor-Based Robotics: Sampling-Based Motion Planning Algorithms for Sensor-Based Robotics: Sampling-Based Motion Planning Computer Science 336 http://www.cs.jhu.edu/~hager/teaching/cs336 Professor Hager http://www.cs.jhu.edu/~hager Recall Earlier Methods

More information

Duksu Kim. Professional Experience Senior researcher, KISTI High performance visualization

Duksu Kim. Professional Experience Senior researcher, KISTI High performance visualization Duksu Kim Assistant professor, KORATEHC Education Ph.D. Computer Science, KAIST Parallel Proximity Computation on Heterogeneous Computing Systems for Graphics Applications Professional Experience Senior

More information

Introduction to Mobile Robotics Path and Motion Planning. Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Diego Tipaldi, Luciano Spinello

Introduction to Mobile Robotics Path and Motion Planning. Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Diego Tipaldi, Luciano Spinello Introduction to Mobile Robotics Path and Motion Planning Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Diego Tipaldi, Luciano Spinello 1 Motion Planning Latombe (1991): eminently necessary since,

More information

Approximate path planning. Computational Geometry csci3250 Laura Toma Bowdoin College

Approximate path planning. Computational Geometry csci3250 Laura Toma Bowdoin College Approximate path planning Computational Geometry csci3250 Laura Toma Bowdoin College Outline Path planning Combinatorial Approximate Combinatorial path planning Idea: Compute free C-space combinatorially

More information

Lecture 3: Motion Planning 2

Lecture 3: Motion Planning 2 CS 294-115 Algorithmic Human-Robot Interaction Fall 2017 Lecture 3: Motion Planning 2 Scribes: David Chan and Liting Sun - Adapted from F2016 Notes by Molly Nicholas and Chelsea Zhang 3.1 Previously Recall

More information

Kinodynamic Motion Planning on Roadmaps in Dynamic Environments

Kinodynamic Motion Planning on Roadmaps in Dynamic Environments Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems San Diego, CA, USA, Oct 29 - Nov 2, 2007 ThD11.1 Kinodynamic Motion Planning on Roadmaps in Dynamic Environments

More information

Way Portals: Efficient Multi-Agent Navigation with Line-Segment Goals

Way Portals: Efficient Multi-Agent Navigation with Line-Segment Goals Way Portals: Efficient Multi-Agent Navigation with Line-Segment Goals Sean Curtis Jamie Snape Dinesh Manocha University of North Carolina at Chapel Hill http://gamma.cs.unc.edu/wayportals Abstract It is

More information

Mobile Robot Path Planning in Static Environments using Particle Swarm Optimization

Mobile Robot Path Planning in Static Environments using Particle Swarm Optimization Mobile Robot Path Planning in Static Environments using Particle Swarm Optimization M. Shahab Alam, M. Usman Rafique, and M. Umer Khan Abstract Motion planning is a key element of robotics since it empowers

More information

Digital Sound Ming C. Lin & Zhimin Ren

Digital Sound Ming C. Lin & Zhimin Ren Digital Sound Ming C. Lin & Zhimin Ren Department of Computer Science University of North Carolina http://gamma.cs.unc.edu/sound How can it be done? Foley artists manually make and record the sound from

More information

CROWD SIMULATION AS A SERVICE

CROWD SIMULATION AS A SERVICE CROWD SIMULATION AS A SERVICE Client dr. Roland Geraerts (r.j.geraerts@uu.nl) Virtual Worlds Dept. of Information and computing sciences Utrecht University (version 13 12 2017) Screenshot of a crowd simulation

More information

11 Behavioural Animation. Chapter 11. Behavioural Animation. Department of Computer Science and Engineering 11-1

11 Behavioural Animation. Chapter 11. Behavioural Animation. Department of Computer Science and Engineering 11-1 Chapter 11 Behavioural Animation 11-1 Behavioral Animation Knowing the environment Aggregate behavior Primitive behavior Intelligent behavior Crowd management 11-2 Behavioral Animation 11-3 Knowing the

More information