1 7 8 ARL Robot Sense Plan Move Goal 9 10 Sense Plan Move - - PDF document

▶
1
SMART_READER_LITE
LIVE PREVIEW

1 7 8 ARL Robot Sense Plan Move Goal 9 10 Sense Plan Move - - PDF document

Sep 23, 2023 352 likes •445 views

Motion planning is the ability for an agent to CS26N: Motion Planning compute its own motions in order to achieve for Robots, Digital Actors, and certain goals. All autonomous robots and digital Other Moving Objects actors should eventually

slide-1
SLIDE 1

1 CS26N: Motion Planning for Robots, Digital Actors, and Other Moving Objects

http://ai.stanford.edu/~latombe/cs26n/2012/home.htm

1

Jean-Claude Latombe latombe@cs.stanford.edu ai.stanford.edu/~latombe/ Winter 2012

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

2

Piano Mover’s Problem

3

What is a path? a trajectory? What are the constraints? What are

4

What are the motion constraints? Why is this example difficult?

5 6

slide-2
SLIDE 2

2

7 8

Plan Move Sense

9

ARL Robot

10

Goal

11

Plan Move Sense Learn

Motion library

12

slide-3
SLIDE 3

3

Plan Move Sense Learn

Motion library

13

Goal of Motion Planning

  • Compute motion strategies, e.g.:

– geometric paths – time-parameterized trajectories sequence of sensor based motion commands

14

– 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

Fundamental Question

Are two given points connected by a path?

15

Valid region Forbidden region

Fundamental Question

Are two given points connected by a path?

16

Valid region Forbidden region E.g.: ▪Collision with obstacle ▪Lack of visibility of an object ▪Lack of stability

Is It Easy?

17

Tool: Configuration Space

18

Problems:

  • Geometric complexity
  • Space dimensionality
slide-4
SLIDE 4

4

Continuous space Discretization

C-space

19

Search

Sampling-based Criticality-based

Many Variants

  • Moving obstacles
  • Multiple robots
  • Movable objects
  • Assembly planning
  • Goal is to acquire

i f ti b i

  • Optimal planning
  • Uncertainty in model,

control and sensing

  • Exploiting task

mechanics (sensorless motions under-

20

information by sensing

– Model building – Object finding/tracking – Inspection

  • Nonholonomic

constraints

  • Dynamic constraints
  • Stability constraints

motions, under actualted systems)

  • Physical models and

deformable objects

  • Integration of planning

and control

  • Integration with higher-

level planning

Some Applications

21

Humanoid Robots

22

HRP-2, AIST, Japan

Lunar Vehicle (ATHLETE, NASA/JPL)

23

Climbing Robot

24

slide-5
SLIDE 5

5 Modular Reconfigurable Robots

25 26

Dexterous Manipulation

27

Manipulation of Deformable Objects

28

Topologically defined goals

Digital Characters

29

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)

Digital Characters

30

slide-6
SLIDE 6

6 Animation of Crowds

31 32

Design for Manufacturing and Servicing

33

Design for Manufacturing and Servicing

34

Design for Manufacturing and Servicing

35

Cable Harness/ Pipe design

36

slide-7
SLIDE 7

7 Map Building

Where to move next?

37

Navigation Through Virtual Environments

38

Virtual Angiography / Bronchoscopy / Colonoscopy

39

Radiosurgical Planning

40

CyberKnife (Accuray)

Building Code Verification

41

9-inch turning radius 24-inch turning radius

Egress Simulation

Primary escape route

Potential congesting areas

42

Secondary escape route

slide-8
SLIDE 8

8 Transportation of A380 Fuselage through Small Villages

43

Kineo

Study of Motion of Bio-Molecules

44

Study of Motion of Bio-Molecules

45 Inhibitor binding to HIV protease

http://ai.stanford.edu/~latombe/cs26n/2012/home.htm

46