robots navigation LUKAS HFLIGER SUPERVISED BY MARIAN GEORGE 2 - - PowerPoint PPT Presentation

▶
robots navigation
SMART_READER_LITE
LIVE PREVIEW

robots navigation LUKAS HFLIGER SUPERVISED BY MARIAN GEORGE 2 - - PowerPoint PPT Presentation

Jul 31, 2023 306 likes •765 views

Vision-based systems for autonomous driving and mobile robots navigation LUKAS HFLIGER SUPERVISED BY MARIAN GEORGE 2 LUKAS HFLIGER 3 4 LUKAS HFLIGER 5 Google Chauffeur 6 LUKAS HFLIGER Motivation Environments where humans

slide-1
SLIDE 1

Vision-based systems for autonomous driving and mobile robots navigation

LUKAS HÄFLIGER – SUPERVISED BY MARIAN GEORGE

slide-2
SLIDE 2

LUKAS HÄFLIGER

2

slide-3
SLIDE 3

3

slide-4
SLIDE 4

LUKAS HÄFLIGER

4

slide-5
SLIDE 5

5

slide-6
SLIDE 6

Google Chauffeur

LUKAS HÄFLIGER

6

slide-7
SLIDE 7

Motivation

  • Environments where humans can not operate
  • Great distances where manual control is not feasible
  • Regular tasks
  • Time saving
  • Improving safety
  • …

LUKAS HÄFLIGER

7

slide-8
SLIDE 8

Introduction

  • AGV – Autonomous Ground Vehicle
  • AUV – Autonomous Underwater Vehicle
  • UAV – Unmanned Aerial Vehicle

LUKAS HÄFLIGER

8

slide-9
SLIDE 9

Mobile robot navigation

LUKAS HÄFLIGER

9

Mobile robot navigation Autonomous driving Indoor Outdoor Map-based Map- building Mapless Structured Unstructured Approches Goals

slide-10
SLIDE 10

Indoor – Map-based systems

  • The robot is provided with a map
  • Needs to localize itself within the map

LUKAS HÄFLIGER

10

slide-11
SLIDE 11

Indoor – Map-based systems

  • Robot needs to correct its trajectory if it does not match the

calculated trajectory

http://www.cs.cmu.edu/

LUKAS HÄFLIGER

11

slide-12
SLIDE 12

Indoor – Map-based systems

  • The robot is provided with a map
  • Needs to localize itself within the map
  • Robot needs to correct its trajectory if it does not match the

calculated trajectory

  • Different approaches
  • Force fields
  • Occupancy grids
  • Landmark tracking

LUKAS HÄFLIGER

12

slide-13
SLIDE 13

Prominent robot: FUZZY-NAV

LUKAS HÄFLIGER

13

[PAN1995]

slide-14
SLIDE 14

LUKAS HÄFLIGER

14

Force field

slide-15
SLIDE 15

LUKAS HÄFLIGER

15

Occupancy grid

slide-16
SLIDE 16

Indoor – Map-building systems

  • In a first step the robot explores the map until enough information is

gathered

  • In a second step the navigation is started using the autonomously

generated map

  • Different approaches:
  • Stereo 3D reconstruction
  • Occupancy grid
  • Topological representation (feasible alternative to occupancy grids)

LUKAS HÄFLIGER

16

slide-17
SLIDE 17

Stereo 3D reconstruction

LUKAS HÄFLIGER

17

slide-18
SLIDE 18

Topological representation

LUKAS HÄFLIGER

18

[THRUN1996]

slide-19
SLIDE 19

Indoor – Mapless systems

  • The robot is not provided with a map
  • Needs to detect and drive around obstacles
  • Needs to localize itself within the envirnonment
  • Different approaches:
  • Optical Flow
  • Appearance-based

LUKAS HÄFLIGER

19

slide-20
SLIDE 20

Optical Flow

LUKAS HÄFLIGER

20

[GUZEL2010]

slide-21
SLIDE 21

Appearance based

  • Based on stored image templates of a previous recording phase
  • Robot selflocates and navigates using these templates

LUKAS HÄFLIGER

21

slide-22
SLIDE 22

Mobile robot navigation

LUKAS HÄFLIGER

22

Mobile robot navigation Autonomous driving Indoor Outdoor Map-based Map- building Mapless Structured Unstructured Approches Goals

slide-23
SLIDE 23

Outdoor – structured environments

  • Represents road following
  • Detect lines of the road and navigate robot accordingly
  • Different approaches
  • Laser range finders
  • Machine learning
  • GPS
  • Obstacle maps

LUKAS HÄFLIGER

23

slide-24
SLIDE 24

Meet STANLEY

LUKAS HÄFLIGER

24

slide-25
SLIDE 25

LUKAS HÄFLIGER

25

[THRUN2006]

slide-26
SLIDE 26

LUKAS HÄFLIGER

26

[THRUN2006]

slide-27
SLIDE 27

LUKAS HÄFLIGER

27

slide-28
SLIDE 28

Outdoor – unstructured environments

  • Random exploration
  • Only needs reactive obstacle detection
  • Mission-based exploration
  • The robot has a goal position
  • Robot needs to map the environment
  • Robot needs to localize itself in the map
  • Different approaches
  • Stereo vision
  • Ladar
  • Visual odometry

LUKAS HÄFLIGER

28

slide-29
SLIDE 29

Prominent example: Curiosity

LUKAS HÄFLIGER

29

slide-30
SLIDE 30

Visual odometry

  • Incremental motion estimation by visual feature tracking
  • Select features
  • Match in 3D with stereo vision to get 3D coordinates
  • Solve for the motion between successive 3D coordinates

LUKAS HÄFLIGER

30

slide-31
SLIDE 31

Ladar – Laser detection and ranging

LUKAS HÄFLIGER

31

slide-32
SLIDE 32

Autonomous driving

LUKAS HÄFLIGER

32

Mobile robot navigation Autonomous driving Indoor Outdoor Map-based Map- building Mapless Structured Unstructured Approches Goals

slide-33
SLIDE 33

LUKAS HÄFLIGER

33

slide-34
SLIDE 34

Autonomous driving - goals

  • Reliable pedestrian detection
  • Detect and interpret road signs
  • Detect obstacles (other cars, trees on the street,…)
  • Follow the road in given borders
  • React to street signals like red lights
  • …

LUKAS HÄFLIGER

34

slide-35
SLIDE 35

Approaches – Reliable pedestrian detection

  • Stereo vision [CHOI2012]
  • Predict pedestrian motions [BERGER2012]
  • Shape recognition [FRANKE1998]

LUKAS HÄFLIGER

35

slide-36
SLIDE 36

Approaches – Detect road signs

  • Stereo vision [FRANKE1998]
  • Detection based on shape, color and motion [FRANKE1998]
  • MSRC [GALLEGUILLOS2010]

LUKAS HÄFLIGER

36

slide-37
SLIDE 37

Approaches – Obstacle detection

  • Obstacle maps [CHOI2012]

LUKAS HÄFLIGER

37

[CHOI2012]

slide-38
SLIDE 38

Approaches – Road following

  • Follow the road in given borders
  • Dark-light-dark transitions [CHOI2012]

LUKAS HÄFLIGER

38

[CHOI2012]

slide-39
SLIDE 39

Approaches – Street signals

  • React to street signals like red lights
  • Camera-based [LEVINSON2011]

LUKAS HÄFLIGER

39

[LEVINSON2011]

slide-40
SLIDE 40

Thank you for your attention

LUKAS HÄFLIGER

40

slide-41
SLIDE 41

Image Reference

Slide 2: http://farm7.staticflickr.com/6087/6145774669_b855d4a0fa_o.jpg Slide 3: http://persistentautonomy.com/wp-content/uploads/2013/12/DSC_1053.jpg Slide 4: http://25.media.tumblr.com/0c2b1a9479dc09971df4d15f05cc77d5/tumblr_mpqtp1BtTa1rdiu71o2_1280.jpg Slide 5: http://electronicdesign.com/site-files/electronicdesign.com/files/archive/electronicdesign.com/content/content/74282/74282_fig1-nasa-curiosity-landing.jpg Slide 10: http://www.cs.cmu.edu/~maxim/img/mobplatforminautonav_2.PNG Slide 11: http://www.cs.cmu.edu/ Slide 14: https://eris.liralab.it/wiki/D4C_Framework Slide 15: http://www.emeraldinsight.com/content_images/fig/0490390507007.png Slide 17: http://www.vis.uni-stuttgart.de/uploads/tx_visteaching/cv_teaser3_01.png Slide 21: http://www.extremetech.com/extreme/115131-learn-how-to-program-a-self-driving-car-stanfords-ai-guru-says-he-can-teach-you-in-seven-weeks

LUKAS HÄFLIGER

41

slide-42
SLIDE 42

Slide 29: http://f.blick.ch/img/incoming/origs2243351/4650486351-w980-h640/Curiosity.jpg Slide 30: http://www.inrim.it/ar2006/ar/va_quattro1581.png Slide 31: http://www.hizook.com/files/users/3/Velodyne_LaserRangeFinder_Lidar_Visualization.jpg Slide 33: http://mindcater.com/wp-content/uploads/2013/08/bosch-dubai-Autonomous-Driving.jpg Slide 35: http://opticalengineering.spiedigitallibrary.org/article.aspx?articleid=1158526 Slide 36: http://www.cse.buffalo.edu/~jcorso/r/semlabel/files/msrc-montage.png

LUKAS HÄFLIGER

42

slide-43
SLIDE 43

STANLEY details

  • VW Tuareg
  • Drive-by-wire system by VW
  • 7 Pentium M processors
  • 4 Ladars
  • Radar system
  • Stereo vision camera pair
  • Monocular vision system
  • Data rates between 10Hz and 100Hz

LUKAS HÄFLIGER

43

slide-44
SLIDE 44

Curiosity details

  • 900kg
  • 2.90m x 2.70m x 2.20m
  • Plutonium battery
  • RAD750 CPU up to 400MIPS
  • Multiple scientific instruments
  • Stereo 3D navigation with 8 cameras (4 as backup)
  • $2.5 billion

LUKAS HÄFLIGER

44

slide-45
SLIDE 45

Google Chauffeur details

  • 150’000$ Equipment
  • LIDAR

LUKAS HÄFLIGER

45