reciprocal al c collision avoidan ance an and n
play

RECIPROCAL AL C COLLISION AVOIDAN ANCE AN AND N NAVIGATION F - PowerPoint PPT Presentation

Feb 01, 2024 •403 likes •1.12k views

RECIPROCAL AL C COLLISION AVOIDAN ANCE AN AND N NAVIGATION F FOR VIDEO G GAM AMES Jamie Snape 1 Stephen J. Guy 1 Jur van den Berg 2 Ming C. Lin Di Dine nesh M h Mano nocha ha 1 1 University of North Carolina at Chapel Hill 2

  1. RECIPROCAL AL C COLLISION AVOIDAN ANCE AN AND N NAVIGATION F FOR VIDEO G GAM AMES Jamie Snape 1 Stephen J. Guy 1 Jur van den Berg 2 Ming C. Lin Di Dine nesh M h Mano nocha ha 1 1 University of North Carolina at Chapel Hill 2 University of Utah

  2. Out Outline line • Introduction • Hybrid Reciprocal Velocity Obstacles (HRVO) • Goal Velocity Obstacles (GVO) • Optimal Reciprocal Collision Avoidance (ORCA) • Comparison • Conclusion Reciprocal Collision Avoidance and 2 Navigation for Video Games

  3. INT INTRODUC ODUCTION ION Reciprocal Collision Avoidance and 3 Navigation for Video Games

  4. Int Introduct oduction ion • Techniques for multi-agent navigation from robotics and cybernetics are increasingly applicable to AI in video games • Multicore architectures in current-generation computers and consoles allow increasing numbers of characters to be simulated Introduction 4

  5. Hitman: Ab Absolution ( (1,200 A Agents) Square Enix / IO Interactive / UBM TechWeb, 2012 Reyno ynold ld’s ’s S Steering ng M Metho hod [ [1999] a and nd 3 3 mo mont nths hs o of ma manu nual t l tweaki king ng 5

  6. Global P Path P h Planners CENTRAL ALIZED DECOUPLED DECOUPLED • Treat system of multiple • Compute paths for each agents as a single agent separately and then combined agent and use adjust speed along path to single-agent planner avoid collisions • e.g. Brooks & Lozano- • e.g. Kant & Zucker, 1986 Perez, 1983 (cell (decoupled) decompositions), Khatib, 1986 (potential fields), Canny, 1988 (roadmaps) Introduction 6

  7. Local C Collision A Avoidance FORCE / P / POTENTIAL AL F FIELD VELOCITY S SPACE • Model agents as particle • Use current velocity of systems, each particle each agent to extrapolate applies a force on nearby its position for some short particles to maintain time interval separation • e.g. Fiorini & Shiller, 1998 • e.g. Reynolds, 1987 (velocity obstacles) (steering behaviors) • Social Forces (Helbing et al.) Introduction 7

  8. Multi-Agent N Navigation: G Global + + L Local Snape, 2012 Hybrid Reciprocal Velocity Obstacles 8 (HRVO)

  9. Collisions a and O Oscillations CO COLLISI SIONS NS OSCILLA OS ILLATIONS IONS • Pairs of agents touch or • Direction of successive intersect velocities alternates between left and right of agent • Implausible for video game characters • Causes noticeable artifacts in video games Introduction 9

  10. HYBRID R RECIPROCAL AL V VELOCITY OBSTACLES ( (HRVO) Reciprocal Collision Avoidance and 10 Navigation for Video Games

  11. Int Introduct oduction ion • Can we navigate multiple agents to goal points in 2D with no oscillations? Hybrid Reciprocal Velocity Obstacles 11 (HRVO)

  12. Forbidden R Regions f for C Collision A Avoidance Velocity-based R Reasoning • Maritime navigation : “course indicator” (Battenberg, 1902) • Missile guidance (Guelman, 1976) • Artificial intelligence : “maneuvering board” (Tychonievich et al., 1989) • Robotics : “velocity obstacle” (Fiorini & Shiller, 1993, 1998) • Cybernetics : “collision cone” (Chakravarthy & Ghose, 1998) Hybrid Reciprocal Velocity Obstacles 12 (HRVO)

  13. Velocity O Obstacles ( (VO) – – Fiorini Fiorini & & Shi hiller, 1 1998 WO WORKSPACE VELOCITY S SPACE Hybrid Reciprocal Velocity Obstacles 13 (HRVO)

  14. Truncated ( (Reciprocal) V Velocity Obs Obstacle acles – G Guy e et a al., 2 2009 WO WORKSPACE VELOCITY S SPACE Hybrid Reciprocal Velocity Obstacles 14 (HRVO)

  15. Os Oscillat cillations ions • Oscillations may occur since agents are decision-making entities • Each selects a velocity outside the VO of the other, but then old velocities are valid with respect to new VO • Agents will oscillate between these velocities Hybrid Reciprocal Velocity Obstacles 15 (HRVO)

  16. Reciprocal V Velocity O Obstacles ( (RVO) - V Van d den B Berg e et a al., 2 2008 • Set of all velocities in VO averaged with current velocity of agent • One agent takes half responsibility for avoiding collision and other agent takes other half • Collision-free if each agent selects velocity outside RVO of other Hybrid Reciprocal Velocity Obstacles 16 (HRVO)

  17. Reciprocal D Dances • Reciprocal dance oscillations may occur when agents do not select free velocity closest to current velocity • May be due to desire to choose velocity towards its goal point or due to the presence of a third agent Hybrid Reciprocal Velocity Obstacles 17 (HRVO)

  18. Hybrid R Reciprocal V Velocity O Obstacles (HR (HRVO) ) – S Snape e et a al., 2 2009, 2 2011 • Enlarge RVO on the side we do not wish the agent to pass • Replace RVO edge on that side with VO edge Hybrid Reciprocal Velocity Obstacles 18 (HRVO)

  19. No O Oscillations o or R Reciprocal D Dances • If A attempts pass on wrong side of B, must give full priority to B, as with VO • If A chooses correct side, may assume cooperation of B and retain equal priority, as with RVO • Reduces reciprocal dance oscillations without over- constraining motion Hybrid Reciprocal Velocity Obstacles 19 (HRVO)

  20. Circle S Scenario ( (75 A Agents) Snape, 2012 Hybrid Reciprocal Velocity Obstacles 20 (HRVO)

  21. Multi-Agent N Navigation Hybrid Reciprocal Velocity Obstacles 21 (HRVO)

  22. Game L Loop Hybrid Reciprocal Velocity Obstacles 22 (HRVO)

  23. Game L Loop Hybrid Reciprocal Velocity Obstacles 23 (HRVO)

  24. Game L Loop Hybrid Reciprocal Velocity Obstacles 24 (HRVO)

  25. Union o of H Hybrid R Reciprocal V Velocity Obs Obstacle acles Hybrid Reciprocal Velocity Obstacles 25 (HRVO)

  26. New V Velocity O Optimization – G Guy e et a al., 2 2009 Hybrid Reciprocal Velocity Obstacles 26 (HRVO)

  27. Experimental R Results Hybrid Reciprocal Velocity Obstacles 27 (HRVO)

  28. Im Imple plement ntat ation ion • HRVO Library (C++) • http://gamma.cs.unc.edu/HRVO/ • 1,500 downloads since October 2009 Hybrid Reciprocal Velocity Obstacles 28 (HRVO)

  29. Rectangle S Scenario ( (4 A Agents) Hybrid Reciprocal Velocity Obstacles 29 (HRVO)

  30. Circle S Scenario ( (75 A Agents) Snape, 2012 Hybrid Reciprocal Velocity Obstacles 30 (HRVO)

  31. Su Summa mmary y • HRVO for agents in 2D • Motion of agents is free of oscillations and reciprocal dances in practice • Each agent acts independently and does not explicitly communicate with other agents Hybrid Reciprocal Velocity Obstacles 31 (HRVO)

  32. GOAL AL V VELOCITY O OBSTACLES ( (GVO) Reciprocal Collision Avoidance and 32 Navigation for Video Games

  33. Int Introduct oduction ion • HRVO or RVO navigates multiple agents to static goal points with no oscillations in practice • Can we accommodate goal regions, e.g. line segment or area goals, and moving goals? Goal Velocity Obstacles (GVO) 33

  34. Wa Wayportals: L Line G Goals O Optimization [Curtis et al. 2012] University of North Carolina at Chapel Hill 34

  35. Wa Wayportals: L Line G Goals O Optimization Dungeon – 97 agents [Mononen 2009] [Curtis et al. 2012] University of North Carolina at Chapel Hill 35

  36. Preferred V Velocity POINT G GOAL AL MOVING G GOAL AL Goal Velocity Obstacles (GVO) 36

  37. Goal V Velocity O Obstacles ( (GVO) – [ [Sn Snape e et a al., 2 2012] • Use VO not only to avoid collisions, but also to direct agent to a goal region • Choose velocities inside GVO to cause a “collision” with the goal region • Optimize on closest velocity to current velocity inside GVO rather than preferred velocity Goal Velocity Obstacles (GVO) 37

  38. Line G Goal WO WORKSPACE VELOCITY S SPACE Goal Velocity Obstacles (GVO) 38

  39. Moving G Goal WO WORKSPACE VELOCITY S SPACE Goal Velocity Obstacles (GVO) 39

  40. Experimental R Results Goal Velocity Obstacles (GVO) 40

  41. Line G Goal S Scenario ( (25 A Agents) Snape, 2012 Goal Velocity Obstacles (GVO) 41

  42. Moving G Goal S Scenario ( (25 A Agents) Snape, 2012 Goal Velocity Obstacles (GVO) 42

  43. Su Summa mmary y • GVO for specifying goal regions using VO • Choose velocities inside GVO to eventually “collide” with the goal • Goals may be regions with nonzero area and may be moving Goal Velocity Obstacles (GVO) 43

  44. OPTIMAL AL R RECIPROCAL AL C COLLISION AVOIDAN ANCE Reciprocal Collision Avoidance and 44 Navigation for Video Games

  45. Int Introduct oduction ion • HRVO eliminates almost all oscillations in practice, but makes no theoretical guarantees of smoothness • Can we guarantee trajectories in velocity space are continuous, so that trajectories of agents in workspace are continuously differentiable, i.e. smooth? Optimal Reciprocal Collision Avoidance 45 (ORCA)

  46. Optimal R Reciprocal C Collision Avoidance ( (ORCA) A) – V Van d den B Berg e et a al., 2 2011 • Augment VO with an additional linear ORCA constraint • Provides a half-plane of velocities that are locally free of collisions, oscillations, and reciprocal dances • Choose a velocity from the intersection of all ORCA constraints of other agents Optimal Reciprocal Collision Avoidance 46 (ORCA)

Recommend

Reciprocal Collision Avoidance for Quadrotor Helicopters using LQR- Obstacles Daman F. Bareiss

Reciprocal Collision Avoidance for Quadrotor Helicopters using LQR- Obstacles Daman F. Bareiss

Reciprocal Collision Avoidance for Quadrotor Helicopters using LQR- Obstacles Daman F. Bareiss Jur Van Den Berg Algorithmic Robotics Laboratory (ARL) Problem Statement n Multiple robots with linear dynamics in a common workspace n

400 views • 23 slides
10-Collision Response Collision Response Collision Response [Moore and Wilhelms 88]:

10-Collision Response Collision Response Collision Response [Moore and Wilhelms 88]:

10-Collision Response Collision Response Collision Response [Moore and Wilhelms 88]: automatic suggestions about the motions of objects immediately following a collision; animation systems using dynamical simulation inherently must respond

767 views • 53 slides
Collision Detection Part 2. Narrow Phase Collision Detection The Narrow Phase Exact collision

Collision Detection Part 2. Narrow Phase Collision Detection The Narrow Phase Exact collision

Collision Detection Part 2. Narrow Phase Collision Detection The Narrow Phase Exact collision detection: Where precisely have objects touched, where to apply forces, torques? Collision Response The following is an equation for Rigid Body

1.06k views • 79 slides
Q44.2 Consider the collision p + p -> p + p + 0 p + p + Consider the collision p + p

Q44.2 Consider the collision p + p -> p + p + 0 p + p + Consider the collision p + p

Q44.2 Consider the collision p + p -> p + p + 0 p + p + Consider the collision p + p A. It is exoergic. g B. It is endoergic C These terms dont apply to this type of collision C. These terms don t apply to this type of collision

596 views • 20 slides
Collision Detection Collision detection weaknesses Naive collision detection suffers from 3 known

Collision Detection Collision detection weaknesses Naive collision detection suffers from 3 known

07 Tutorial: Broadphase Collision Detection Collision detection weaknesses Naive collision detection suffers from 3 known weaknesses Fixed-timestep weakness All-pairs weakness Pair-processing weakness Two-phase collision detection

833 views • 20 slides
I. Introduction II. Collision of Domain Walls in 5D Minkowski Space III. Reheating by Collision

I. Introduction II. Collision of Domain Walls in 5D Minkowski Space III. Reheating by Collision

I. Introduction II. Collision of Domain Walls in 5D Minkowski Space III. Reheating by Collision of Branes IV. Fermion Localization at Collision V. Collision of Domain Walls in Asymptotically AdS Space VI. Summary Kei-ichi Maeda Waseda Univ.

451 views • 26 slides
Middle School Highlights Reciprocal Teaching Reciprocal Teaching Think like a teacher.

Middle School Highlights Reciprocal Teaching Reciprocal Teaching Think like a teacher.

Middle School Highlights Reciprocal Teaching Reciprocal Teaching Think like a teacher. Sense of community - Gr. 8: Planned and presented - Gr. 6: Pre-teaching Middle School Highlights Interdisciplinary Experiences Middle School

1.11k views • 52 slides
Class 29: More collisions Simple collision problem in 1D Before collision: m 1 m 2 #2 v 2i v 1i

Class 29: More collisions Simple collision problem in 1D Before collision: m 1 m 2 #2 v 2i v 1i

Class 29: More collisions Simple collision problem in 1D Before collision: m 1 m 2 #2 v 2i v 1i #1 After collision: m 2 m 1 #1 v 1f v 2f #2 Equation of motion: m 1 v 1i + m 2 v 2i = m 1 v 1f + m 2 v 2f Can solve for any one unknown from v 1i , v

452 views • 9 slides
Collision Detection http://www.cse.iitd.ac.in/ Collision Detection IIT Delhi Collision handling

Collision Detection http://www.cse.iitd.ac.in/ Collision Detection IIT Delhi Collision handling

IIT Delhi Collision Detection http://www.cse.iitd.ac.in/ Collision Detection IIT Delhi Collision handling is fundamental to animation or dynamic scenes in virtual environments. http://www.cse.iitd.ac.in/ Applications IIT Delhi Games

519 views • 23 slides
Collision Detection Based on Collision Series On XNA Creators Club Collision Detection Circular

Collision Detection Based on Collision Series On XNA Creators Club Collision Detection Circular

Collision Detection Based on Collision Series On XNA Creators Club Collision Detection Circular Rectangular Pixel based Rotated rectangles Pixel based with rotations Minimize work (to do) Circular Collision Detection

486 views • 19 slides
CS 1666 www.cs.pitt.edu/~nlf4/cs1666/ Collision detection Collision detection We already had to

CS 1666 www.cs.pitt.edu/~nlf4/cs1666/ Collision detection Collision detection We already had to

CS 1666 www.cs.pitt.edu/~nlf4/cs1666/ Collision detection Collision detection We already had to implement some basic collision detection in the motion example I.e., to keep our square from moving out of the window Checking for

679 views • 14 slides
Collision Detection I Motivation F d X S, X Collision Force detection response F d F r

Collision Detection I Motivation F d X S, X Collision Force detection response F d F r

CPSC 599.86 / 601.86 Sonny Chan - University of Calgary Collision Detection I Motivation F d X S, X Collision Force detection response F d F r Control algorithms Haptic rendering Problem Definition We seek efficient algorithms to

822 views • 42 slides
Notes Rigid Collision Algorithms Use the same collision response algorithm as Assignment 2

Notes Rigid Collision Algorithms Use the same collision response algorithm as Assignment 2

Notes Rigid Collision Algorithms Use the same collision response algorithm as Assignment 2 instability - dont worry with particles about it right now Identify colliding points as perhaps the deepest Please read penetrating

499 views • 5 slides
Computational Complexity of the Reciprocal Lifts and Strong Meaning Hypothesis Computational

Computational Complexity of the Reciprocal Lifts and Strong Meaning Hypothesis Computational

Motivations Preliminaries Reciprocity in language Reciprocals as lifts over GQs Complexity of reciprocal lifts Speculations on SMH Computational Complexity of the Reciprocal Lifts and Strong Meaning Hypothesis Computational dichotomy

481 views • 32 slides
Object Collision Various types of collision for an object: Sphere Bounding box

Object Collision Various types of collision for an object: Sphere Bounding box

Integrating Physics into a Modern Game Engine Object Collision Various types of collision for an object: Sphere Bounding box Convex hull based on rendered model List of convex hull(s) based on special collision model

792 views • 21 slides
Collision Detection II Outline Broad phase collision detection: - Problem definition and

Collision Detection II Outline Broad phase collision detection: - Problem definition and

CPSC 599.86 / 601.86 Sonny Chan - University of Calgary Collision Detection II Outline Broad phase collision detection: - Problem definition and motivation - Bounding volume hierarchies - Spatial partitioning approaches Polyhedron

815 views • 42 slides
Physics 1 Overview Collision detection Model representation Dynamic vs. static

Physics 1 Overview Collision detection Model representation Dynamic vs. static

Physics 1 Overview Collision detection Model representation Dynamic vs. static Discrete vs. continuous Efficiency issues Collision resolution Events Solvers Dynamics Rigid bodies Impulse-based collision

433 views • 24 slides
Cumulative Submission Assignment 5: Collision Response Implement collision response of a This

Cumulative Submission Assignment 5: Collision Response Implement collision response of a This

Assignment 5 + Cumulative Submission Assignment 5: Collision Response Implement collision response of a This assignment is worth ~8-12% of single convex object falling onto an the module infinite plane Minimum requirements: Rigid Body state

284 views • 13 slides
Lecture 28 of 41 Collision Handling Part 2 of 2: Dynamic Collision Response, Particle Systems

Lecture 28 of 41 Collision Handling Part 2 of 2: Dynamic Collision Response, Particle Systems

Lecture 28 of 41 Collision Handling Part 2 of 2: Dynamic Collision Response, Particle Systems William H. Hsu Department of Computing and Information Sciences, KSU KSOL course pages: http://bit.ly/hGvXlH / http://bit.ly/eVizrE Public mirror web

483 views • 21 slides
Lecture 28 of 41 Collision Handling Part 2 of 2: Dynamic Collision Response, Particle Systems

Lecture 28 of 41 Collision Handling Part 2 of 2: Dynamic Collision Response, Particle Systems

Lecture 28 of 41 Collision Handling Part 2 of 2: Dynamic Collision Response, Particle Systems William H. Hsu Department of Computing and Information Sciences, KSU KSOL course pages: http://bit.ly/hGvXlH / http://bit.ly/eVizrE Public mirror web

812 views • 42 slides
Reciprocal Learning via Dialogue Interaction: Challenges and Prospects Raquel Fernndez, Staffan

Reciprocal Learning via Dialogue Interaction: Challenges and Prospects Raquel Fernndez, Staffan

Reciprocal Learning via Dialogue Interaction: Challenges and Prospects Raquel Fernndez, Staffan Larsson, Robin Cooper Jonathan Ginzburg, David Schlangen IJCAI ALIHT 2011 IJCAI - ALIHT 2011 Reciprocal Learning via Dialogue Interaction 1

181 views • 16 slides
Behavioral Finance: The Collision of Finance and Psychology Behavioral Finance: The Collision of

Behavioral Finance: The Collision of Finance and Psychology Behavioral Finance: The Collision of

Behavioral Finance: The Collision of Finance and Psychology Behavioral Finance: The Collision of Finance and Psychology Presented by: Dr. Joel M. DiCicco, CPA Florida Atlantic University Order of Presentation Behavioral Finance 1)

304 views • 28 slides
k -Reciprocal Nearest Neighbors Algorithm for One-Class Collaborative Filtering Wei Cai a , b , c

k -Reciprocal Nearest Neighbors Algorithm for One-Class Collaborative Filtering Wei Cai a , b , c

k -Reciprocal Nearest Neighbors Algorithm for One-Class Collaborative Filtering Wei Cai a , b , c , Weike Pan a , b , c , Jixiong Liu a , b , c , Zixiang Chen a , b , c , Zhong Ming a , b , c { caiwei2016, liujixiong, chenzixiang2016 }

678 views • 35 slides
February Fourier talks, 2011 Zeros of some self-reciprocal polynomials D. Joyner, USNA FFT 2011

February Fourier talks, 2011 Zeros of some self-reciprocal polynomials D. Joyner, USNA FFT 2011

February Fourier talks, 2011 Zeros of some self-reciprocal polynomials D. Joyner, USNA FFT 2011 at the Norbert Wiener Center, UMCP February 15, 2011 D. Joyner, USNA Zeros of some self-reciprocal polynomials 1/42 Outline 1 Introduction 2

922 views • 48 slides

More recommend