CS686: CS686: Motion Planning and Applications Sung-Eui Yoon ( ) - - PowerPoint PPT Presentation

▶
cs686 cs686 motion planning and applications
SMART_READER_LITE
LIVE PREVIEW

CS686: CS686: Motion Planning and Applications Sung-Eui Yoon ( ) - - PowerPoint PPT Presentation

Jan 19, 2023 431 likes •934 views

CS686: CS686: Motion Planning and Applications Sung-Eui Yoon ( ) ( ) C Course URL: URL http://sglab.kaist.ac.kr/~sungeui/MPA About the Instructor About the Instructor Joined KAI ST at 2007 Joined KAI ST at 2007

slide-1
SLIDE 1

CS686: CS686: Motion Planning and Applications

Sung-Eui Yoon (윤성의) (윤성의)

C URL Course URL: http://sglab.kaist.ac.kr/~sungeui/MPA

slide-2
SLIDE 2

About the Instructor About the Instructor

Joined KAI ST at 2007

  • Joined KAI ST at 2007
  • B.S., M.S. at Seoul National Univ.
  • Ph.D. at Univ. of North Carolina-Chapel Hill
  • Post. doc at Lawrence Livermore Nat’l Lab
  • Main research focus
  • Handling of massive data for various computer

g p graphics and geometric problems

2

slide-3
SLIDE 3

My Recent Work My Recent Work

3

slide-4
SLIDE 4

Welcome to CS780 Welcome to CS780

I nstructor: Sung-eui Yoon Email: sungeui@gmail.com Office: 3432 at CS building Class time: 4:00pm – 5:15pm on T/ Th Class location: 3444 in the CS building Class location: 3444 in the CS building Office hours: 3:00–4:00 MWF (or by appt.) Course webpage: Course webpage: http:/ / sglab.kaist.ac.kr/ ~ sungeui/ MPA TA: Duksu Kim (XXX)

4

TA: Duksu Kim (XXX)

slide-5
SLIDE 5

Real World Robots Real World Robots

Sony Aibo Sony Aibo ASIMO ASIMO

5

Courtesy of Prof. Dinesh Manocha Da Vinci

slide-6
SLIDE 6

Motion of Real Robots Motion of Real Robots

Humanoid Robot:

6

Humanoid Robot: http://youtube.com/watch?v=NYoY4p0_yaI&mode=related&search=

slide-7
SLIDE 7

Motion of Real Robots Motion of Real Robots

Humanoid Robot:

7

Humanoid Robot: http://www.youtube.com/watch?v=ZkYQWBXpk_0

slide-8
SLIDE 8

Motion of Real Robots Motion of Real Robots

Autonomous robot

8

Autonomous robot http://www.youtube.com/watch?v=3SQiow-X3ko

slide-9
SLIDE 9

Motion of Real Robots Motion of Real Robots

Medical robot:

9

Medical robot: http://www.youtube.com/watch?v=XfH8phFm2VY

slide-10
SLIDE 10

Open Platform Humanoid Project: DARwIn OP Project: DARwIn-OP

Just USD 8K!

10

http://www.youtube.com/watch?v=0FFBZ6M0nKw

slide-11
SLIDE 11

Motion of Virtual Worlds Motion of Virtual Worlds

11

slide-12
SLIDE 12

Motion of Virtual Worlds Motion of Virtual Worlds

Computer generated simulations:

12

Computer generated simulations: http://www.youtube.com/watch?v=5-UQmVjFdqs

slide-13
SLIDE 13

Motion of Virtual Worlds Motion of Virtual Worlds

Computer generated simulations games virtual prototyping:

13

Computer generated simulations, games, virtual prototyping: http://www.massivesoftware.com/

slide-14
SLIDE 14

Smart Robots or Agents Smart Robots or Agents

Autonomous agents that sense plan and

  • Autonomous agents that sense, plan, and

act in real and/ or virtual worlds

  • Algorithms and systems for representing
  • Algorithms and systems for representing,

capturing, planning, controlling, and rendering motions of physical objects g p y j

  • Applications:
  • Applications:
  • Manufacturing
  • Mobile robots
  • Computational biology
  • Computer-assisted surgery

14

  • Digital actors
slide-15
SLIDE 15

Goal of Motion Planning Goal of Motion Planning

Compute motion strategies e g :

  • Compute motion strategies, e.g.:
  • Geometric paths
  • Time parameterized trajectories
  • Time-parameterized trajectories
  • Sequence of sensor-based motion commands
  • Aesthetic constraints
  • Aesthetic constraints
  • Achieve high-level goals, e.g.:
  • Achieve high level goals, e.g.:
  • Go to A without colliding with obstacles
  • Assemble product P

p

  • Build map of environment E
  • Find object O

15

slide-16
SLIDE 16

Basic Motion Planning Problem Basic Motion Planning Problem

Statement:

  • Statement:
  • Compute a collision-free path for an object (the

robot) among obstacles subject to robot) among obstacles subject to CONSTRAI NTS

  • I nputs:

I nputs:

  • Geometry of robot and obstacles
  • Kinematics of robot (degrees of freedom)

( g )

  • I nitial and goal robot configurations

(placements)

  • Outputs:
  • Continuous sequence of collision-free robot

fi ti ti th i iti l d l

16

configurations connecting the initial and goal configurations

slide-17
SLIDE 17

Examples with Rigid Object Examples with Rigid Object

 Ladder problem

17

Piano-mover problem 

slide-18
SLIDE 18

Is It Easy? Is It Easy?

18

slide-19
SLIDE 19

Example with Articulated Object Example with Articulated Object

19

slide-20
SLIDE 20

Some Extensions of Basic Problem Problem

M lti l b t O ti l l i

  • Multiple robots
  • Assembly planning

A i i f ti b

  • Optimal planning
  • Uncertainty in model,

control and sensing

  • Acquire information by

sensing

  • Model building

control and sensing

  • Exploiting task

mechanics (sensorless

Model building

  • Object finding/ tracking
  • I nspection

( motions, under- actualted systems) Ph i l d l d

  • Nonholonomic

constraints

  • Physical models and

deformable objects

  • I ntegration of planning
  • Dynamic constraints
  • Stability constraints
  • I ntegration of planning

and control

  • I ntegration with

20

I ntegration with higher-level planning

slide-21
SLIDE 21

Examples of Applications Examples of Applications

M f t i G hi i ti f

  • Manufacturing:
  • Robot programming
  • Robot placement
  • Graphic animation of

“digital actors” for video games, movies,

  • Robot placement
  • Design of part feeders
  • Design for

g , , and webpages

  • Virtual walkthrough

Design for manufacturing and servicing i f i l

  • Medical surgery

planning G ti f l ibl

  • Design of pipe layouts

and cable harnesses

  • Autonomous mobile
  • Generation of plausible

molecule motions, e.g., docking and folding

  • Autonomous mobile

robots planetary exploration, ill ili g g motions

  • Building code

ifi ti

21

surveillance, military scouting verification

slide-22
SLIDE 22

Assembly Planning and Design of Assembly Planning and Design of y Manufacturing Systems Manufacturing Systems

slide-23
SLIDE 23

Application: Checking Building Code Application: Checking Building Code Application: Checking Building Code Application: Checking Building Code

slide-24
SLIDE 24

Cable Harness/ Pipe design Cable Harness/ Pipe design Cable Harness/ Pipe design Cable Harness/ Pipe design

slide-25
SLIDE 25

Humanoid Robot Humanoid Robot Humanoid Robot Humanoid Robot

[Kuffner and Inoue, 2000] (U. Tokyo)

slide-26
SLIDE 26

Digital Actors Digital Actors g

A Bug’s Life (Pixar/Disney) Toy Story (Pixar/Disney) Antz (Dreamworks) Tomb Raider 3 (Eidos Interactive) Final Fantasy VIII (SquareOne) The Legend of Zelda (Nintendo)

slide-27
SLIDE 27

Motion Planning for Digital Actors Motion Planning for Digital Actors Motion Planning for Digital Actors Motion Planning for Digital Actors

Manipulation Sensory-based locomotion

slide-28
SLIDE 28

Application: Computer Application: Computer Assisted Surgical Planning Assisted Surgical Planning Application: Computer Application: Computer-Assisted Surgical Planning Assisted Surgical Planning

slide-29
SLIDE 29

Radiosurgical Planning Radiosurgical Planning Radiosurgical Planning Radiosurgical Planning

Cyberknife Cyberknife

slide-30
SLIDE 30

Study of the Motion of Bio Study of the Motion of Bio-Molecules Molecules Study of the Motion of Bio Study of the Motion of Bio-Molecules Molecules

  • Protein folding
  • Ligand binding
  • Ligand binding
slide-31
SLIDE 31

DARPA G d Ch ll DARPA Grand Challenge

Planning for a collision free 132 mile path Planning for a collision-free 132 mile path in a desert

The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL

slide-32
SLIDE 32

Prerequisites Prerequisites

B i k l d f b bilit

  • Basic knowledge of probability
  • E.g., events, expected values, etc
  • I f you are not sure, please consult the

instructor at the end of the course instructor at the end of the course

32

slide-33
SLIDE 33

Topics Topics

Unde l ing geomet ic concepts of motion

  • Underlying geometric concepts of motion

planning

  • Configuration space
  • Configuration space
  • Motion planning algorithms:
  • Complete motion planning
  • Complete motion planning
  • Randomized approaches
  • Kinodynamic constraints
  • Kinodynamic constraints
  • Character motion in virtual environments
  • Multi agent and crowd simulation
  • Multi-agent and crowd simulation

The course is about motion planning

33

The course is about motion planning algorithms, not control of real robots!

slide-34
SLIDE 34

Course Overview Course Overview

1/ 2 of lectures and 1/ 2 of student

  • 1/ 2 of lectures and 1/ 2 of student

presentations

  • This is a research-oriented course
  • This is a research-oriented course
  • Paper reading list
  • What you will do:
  • Choose papers that are interesting to you

Choose papers that are interesting to you

  • Present those papers
  • Propose ideas that can improve the state-of-

p p the-art techniques; implementation is not required, but is recommended Quiz and mid term

34

  • Quiz and mid-term
  • and, have fun!
slide-35
SLIDE 35

Presentations and Final Project Presentations and Final Project

For each paper:

  • For each paper:
  • Consider its main idea given its context
  • Look at pros and cons of each method
  • Look at pros and cons of each method
  • Think about how we can efficiently handle

more realistic and complex scene more realistic and complex scene

  • Propose ideas to address those problems
  • Show convincing reasons why your ideas can

Show convincing reasons why your ideas can improve those problems

  • I mplementation is optional

35

slide-36
SLIDE 36

Course Awards Course Awards

Best speaker and best project

  • Best speaker and best project
  • For the best presenter, a small research

related device will be supported

  • For the best project, a high grade will be

given given

36

slide-37
SLIDE 37

Course Overview Course Overview

Grade policy

  • Grade policy
  • Class presentations: 30%
  • Quiz assignment and mid term: 30%
  • Quiz, assignment, and mid-term: 30%
  • Final project: 40%
  • I nstructor (50% ) and students (50% ) will
  • I nstructor (50% ) and students (50% ) will

evaluate presentations and projects

  • Late policy

Late policy

  • No score
  • Submit your work before the deadline!

y

  • Class attendance rule
  • Late two times  count as one absence

37

  • Every two absences lower your grade (e.g.,

A-  B+ )

slide-38
SLIDE 38

Resource Resource

  • Textbook
  • Textbook
  • Planning Algorithms, Steven
  • M. LaValle, 2006

, (http:/ / msl.cs.uiuc.edu/ pla nning/ )

38

slide-39
SLIDE 39

Other Reference Other Reference

Our paper reading list

  • Our paper reading list
  • Technical papers

I EEE I t ti l C f R b ti d

  • I EEE I nternational Conf. on Robotics and

Automation (I CRA)

  • I EEE/ RSJ I nt Conf o nI ntelligent Robots and
  • I EEE/ RSJ I nt. Conf. o nI ntelligent Robots and

Systems (I ROS)

  • Graphics-related conference (SI GGRAPH, etc)

p ( , )

  • http:/ / kesen.huang.googlepages.com/
  • SI GGRAPH course notes and video encore
  • Course homepages

39

  • Course homepages
  • Google or Google scholar
slide-40
SLIDE 40

Our Research Focus Our Research Focus

Design general motion planning algorithms

  • Design general motion planning algorithms

that:

  • Easily adapt to various motion planning
  • Easily adapt to various motion planning

problems

  • Show high performance

g p

  • Provide high scalability for complex and high-

dimensional problems

40

slide-41
SLIDE 41

Ranking of Robotics-Related Conf (among last 10 years)

  • Conf. (among last 10 years)

Based on last 10 years records among 2 3K

  • Based on last 10 years records among 2.3K

conf.

  • Name (rank): publications, citations

I CCV (10) 1K 23K

  • I CCV (10): 1K, 23K
  • CVPR (18): 3.5K, 42K
  • I ROS (59): 0.5K, 6.5K
  • I CRA (75): 7K, 30K
  • I 3D (91): 0.2K, 3K
  • RSS (missed): 0.1K, 1.2K (recent conf.)

41

RSS (missed): 0.1K, 1.2K (recent conf.)

  • I SRR (missed): 0.1K, 1.2K
slide-42
SLIDE 42

Ranking of Robotics-Related Journals Journals

Based on last 10 years records among 0 9K

  • Based on last 10 years records among 0.9K

journals

  • Name (rank): publications citations
  • Name (rank): publications, citations
  • TOG (1): 1.2K, 38K

PAMI (5) 1 9K 40K

  • PAMI (5): 1.9K, 40K
  • I JCV (7): 0.9K, 19K
  • I JRR (65): 0.8K, 7K (I F ’09: 1.993)
  • TVCG(72): 1.2K, 8.6K
  • CGF (83): 1.4K, 9.2K
  • Trob (87): 1.1K, 7.6K (I F ‘09: 2.035)

42

Trob (87): 1.1K, 7.6K (I F 09: 2.035)

  • Autonomous Robot (missed): 2K, 13K

(whole years) (I F ‘09: 1.2)

slide-43
SLIDE 43

Honor Code Honor Code

Collaboration encouraged but assignments

  • Collaboration encouraged, but assignments

must be your own work

  • Cite any other’s work if you use their codes
  • Cite any other s work if you use their codes

43

slide-44
SLIDE 44

Schedule Schedule

Please refer the course homepage:

  • Please refer the course homepage:
  • http:/ / sglab.kaist.ac.kr/ ~ sungeui/ MPA

44

slide-45
SLIDE 45

Official Language in Class Official Language in Class

English

  • English
  • I ’ll give lectures in English
  • I may explain again in Korean if materials are
  • I may explain again in Korean if materials are

unclear to you

  • You are also required to use English, unless

You are also required to use English, unless special cases

45

slide-46
SLIDE 46

About You About You

Name

  • Name
  • Your (non hanmail.net) email address
  • What is your major?
  • Previous experience on motion planning

and robotics

46

slide-47
SLIDE 47

Homework for Every Class Homework for Every Class

Go over the next lecture slides

  • Go over the next lecture slides
  • Come up with one question on what we

have discussed today and submit at the have discussed today and submit at the beginning of the next class

  • 0 for no questions
  • 0 for no questions
  • 2 for typical questions
  • 3 for questions with thoughts

q g

  • 4 for questions that surprised me

47

slide-48
SLIDE 48

Homework Homework

Read Chapter 1 of our textbook

  • Read Chapter 1 of our textbook
  • Optional:
  • Motion planning: A journey of robots,

molecules digital Actors and other artifacts molecules, digital Actors, and other artifacts. J.C. Latombe. I nt. J. Robotics Research, 18(11):1119-1128, 1999. ( ) ,

48

slide-49
SLIDE 49

Next Time Next Time…

Configuration spaces

  • Configuration spaces
  • Motion planning framework
  • Classic motion planning approaches

49