CS 326A: Motion Planning Criticality-Based Motion Planning: Target Finding.
CS 326A: Motion Planning
description
Transcript of CS 326A: Motion Planning
![Page 1: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/1.jpg)
CS 326A: Motion Planning
Jean-Claude Latombe
CA: Aditya Mandayam
![Page 2: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/2.jpg)
Motion planning is the ability for an agent to compute its own motions in order to achieve certain goals. All autonomous
robots and digital actors should eventually have this ability
![Page 3: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/3.jpg)
Piano Mover’s Problem
![Page 4: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/4.jpg)
![Page 5: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/5.jpg)
![Page 6: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/6.jpg)
![Page 7: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/7.jpg)
![Page 8: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/8.jpg)
Plan MoveSense
![Page 9: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/9.jpg)
ARL Robot
Goal
![Page 10: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/10.jpg)
![Page 11: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/11.jpg)
Plan MoveSense
LearnMotion library
![Page 12: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/12.jpg)
Goal of Motion Planning
• Compute motion strategies, e.g.:– geometric paths – time-parameterized trajectories– sequence of sensor-based motion commands
• To achieve high-level goals, e.g.:– go to A without colliding with obstacles– assemble product P– build map of environment E– find object O
![Page 13: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/13.jpg)
Fundamental QuestionAre two given points connected by a path?
Valid region
Forbidden region
![Page 14: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/14.jpg)
Fundamental QuestionAre two given points connected by a path?
Valid region
Forbidden region
E.g.:▪Collision with obstacle▪Lack of visibility of an object▪Lack of stability
![Page 15: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/15.jpg)
Basic Problem Statement:
Compute a collision-free path for a rigid or articulated object among static obstacles
Inputs:•Geometry of moving object and obstacles•Kinematics of moving object (degrees of freedom)•Initial and goal configurations (placements)
Output:Continuous sequence of collision-free robot configurations connecting the initial and goal configurations
![Page 16: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/16.jpg)
Is It Easy?
![Page 17: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/17.jpg)
Tool: Configuration Space
Problems:• Geometric complexity• Space dimensionality
![Page 18: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/18.jpg)
Continuous space
Discretization
Search
C-space
Sampling-based Criticality-based
![Page 19: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/19.jpg)
Extensions of Basic Problem
• Moving obstacles• Multiple robots• Movable objects• Assembly planning• Goal is to acquire
information by sensing– Model building– Object finding/tracking– Inspection
• Nonholonomic constraints
• Dynamic constraints• Stability constraints
• Optimal planning• Uncertainty in model,
control and sensing• Exploiting task
mechanics (sensorless motions, under-actualted systems)
• Physical models and deformable objects
• Integration of planning and control
• Integration with higher-level planning
![Page 20: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/20.jpg)
Some Applications
![Page 21: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/21.jpg)
Humanoid Robots
HRP-2, AIST, Japan
![Page 22: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/22.jpg)
Lunar Vehicle (ATHLETE, NASA/JPL)
![Page 23: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/23.jpg)
Climbing Robot
http://www.youtube.com/watch?v=biSx-aKN690
![Page 24: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/24.jpg)
Dexterous Manipulation
![Page 25: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/25.jpg)
Modular Reconfigurable Robots
![Page 26: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/26.jpg)
![Page 27: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/27.jpg)
Manipulation of Deformable Objects
Topologicallydefined goal
![Page 28: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/28.jpg)
Digital Characters
A Bug’s Life (Pixar/Disney) Toy Story (Pixar/Disney)
Tomb Raider 3 (Eidos Interactive) Final Fantasy VIII (SquareOne)The Legend of Zelda (Nintendo)
Antz (Dreamworks)
![Page 29: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/29.jpg)
Digital Characters
![Page 30: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/30.jpg)
Animation of Crowds
![Page 31: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/31.jpg)
![Page 32: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/32.jpg)
Design for Manufacturing and Servicing
![Page 33: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/33.jpg)
Design for Manufacturing and Servicing
![Page 34: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/34.jpg)
Design for Manufacturing and Servicing
![Page 35: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/35.jpg)
Assembly Sequence Planning
![Page 36: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/36.jpg)
![Page 37: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/37.jpg)
Cable Harness/ Pipe design
![Page 38: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/38.jpg)
Map Building
Where to move next?
![Page 39: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/39.jpg)
Navigation Through Virtual Environments
![Page 40: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/40.jpg)
Virtual Angiography / Bronchoscopy /
Colonoscopy
![Page 41: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/41.jpg)
Radiosurgical Planning
CyberKnife (Accuray)
![Page 42: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/42.jpg)
Building Code Verification
9-inch turning radius24-inch turning radius
![Page 43: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/43.jpg)
Egress Simulation
Primary escape route
Secondary escape route
Potential congesting areas
![Page 45: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/45.jpg)
Transportation of A380 Fuselage through Small
Villages
Kineo
![Page 46: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/46.jpg)
Study of Motion of Bio-Molecules
Inhibitor binding to HIV protease
![Page 47: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/47.jpg)
Goals of CS326A
Present a coherent framework for motion planning problems
Emphasis of “practical” algorithms with some guarantees of performance over “theoretical” or purely “heuristic” algorithms
![Page 48: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/48.jpg)
General Framework
Continuous representation(configuration space and related spaces + constraints)
Discretization(probabilistic sampling, criticality-based decomposition)
Graph searching(blind, best-first, A*)
![Page 49: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/49.jpg)
Practical Algorithms (1/2)
A complete motion planner always returns a solution plan when one exists and indicates that no such plan exists otherwise.
Most motion planning problems are hard, meaning that complete planners take exponential time in # of degrees of freedom, objects, etc.
![Page 50: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/50.jpg)
Practical Algorithms (2/2)
Theoretical algorithms strive for completeness and minimal worst-case complexity. Difficult to implement and not robust.
Heuristic algorithms strive for efficiency in commonly encountered situations. Usually no performance guarantee.
Weaker completeness Simplifying assumptions Exponential algorithms that work in practice
![Page 51: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/51.jpg)
Prerequisites for CS326A
Ability and willingness to complete a significant programming project with graphic interface.
Basic knowledge and taste for geometry and algorithms.
Interest in devoting reasonable time each week in reading papers.
![Page 52: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/52.jpg)
CS326A is not a course in …
Differential Geometry and TopologyKinematics and DynamicsGeometric Modeling
… but it makes use of knowledge from all these areas
![Page 53: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/53.jpg)
Work to Do
A. Attend every classB. Prepare/give two presentations with
ppt slides (20 minutes each)C. For each class read the two papers
listed as “required reading” in advance
D. Complete the programming projectE. Complete two homework
assignments
![Page 54: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/54.jpg)
Programming Project• Navigate in virtual environment
• Simulate legged robot
• Inspection of structures
• Search and escape
![Page 55: CS 326A: Motion Planning](https://reader035.fdocuments.in/reader035/viewer/2022062322/56814aa2550346895db7b552/html5/thumbnails/55.jpg)
Website and Schedule
ai.stanford.edu/~latombe/cs326/2009/index.htm