24
Autonomous Localization & Navigation using 2D Laser Scanners Animesh Garg & Manohar Paluri

Autonomous Localization & Navigation using 2D Laser Scanners

  • Upload
    tave

  • View
    36

  • Download
    0

Embed Size (px)

DESCRIPTION

Autonomous Localization & Navigation using 2D Laser Scanners. Animesh Garg & Manohar Paluri. Outline. Problem Description Motivation Previous research Proposed approach Details of our approach Testing Results Conclusion. Why an autonomous painting system is required?. Introduction. - PowerPoint PPT Presentation

Citation preview

Page 1: Autonomous Localization & Navigation using 2D Laser Scanners

Autonomous Localization & Navigation using 2D Laser

Scanners

Animesh Garg & Manohar Paluri

Page 2: Autonomous Localization & Navigation using 2D Laser Scanners

22

Outline

• Problem Description• Motivation• Previous research• Proposed approach• Details of our approach• Testing • Results• Conclusion

Page 3: Autonomous Localization & Navigation using 2D Laser Scanners

33

Why an autonomous painting system is required?

Page 4: Autonomous Localization & Navigation using 2D Laser Scanners

44

Introduction

During spray painting process, the environment has a very large concentration of paint particles decreasing visibility. And the paint settles on surfaces, it rules out markers based solution.

The Omnimove is a huge platform for moving very heavy weights around. Herein it would hold the robotic arm which will be used to carry out the painting job.

Page 5: Autonomous Localization & Navigation using 2D Laser Scanners

55

Potential Solutions

• Cameras• GPS• INS• Sonar• Laser• Northstar• Vicon• And more…

Page 6: Autonomous Localization & Navigation using 2D Laser Scanners

66

Our solution

Sample Mount

• Laser Scanners– Cost effective, Reliable,

Accurate, known solutions!

– Paint Hangar constraints

Page 7: Autonomous Localization & Navigation using 2D Laser Scanners

77

Past Work

• Fast RANSAC based registration algorithm for accurate navigation using only Lidar. RANSAC in combination with Huber's kernel to overcome the LIDAR input noise.

• Hough transform for robot localization.The self localiza-tion technique in the paper is based on matching a geometric reference map with range information

• RRT-Connect, bi-directional decision trees.• RRT* - Combines advantages of RRGs optimal solution

with a tree structure.

Page 8: Autonomous Localization & Navigation using 2D Laser Scanners

88

Block Diagram

Page 9: Autonomous Localization & Navigation using 2D Laser Scanners

99

Rigid Transformation

• Scan1 Scan2

• Combined Scan

Page 10: Autonomous Localization & Navigation using 2D Laser Scanners

1010

Line Extraction Techniques

• Split-and-Merge• Line-Regression• Incremental• RANSAC• Hough-Transform• EM

Page 11: Autonomous Localization & Navigation using 2D Laser Scanners

1111

Split & Merge• Initial: set s1 consists of N points. Put s1 in a list L 1• Fit a line to the next set s in L 2• Detect point P with maximum distance d to the line 3• If d is less than a threshold, continue (go to 2) 4• Otherwise, split s at P into s 1 and s 2, replace s in 5• L by s 1 and s 2, continue (go to 2)• When all sets (segments) in L have been checked, 6• merge collinear segments.

Page 12: Autonomous Localization & Navigation using 2D Laser Scanners

1212

Hough Transform

• Initial: A set of N points• Initialize the accumulator array (model space)• Construct values for the array• Choose the element with max. votes Vmax• If Vmax is less than a threshold, terminate• Otherwise, determine the inliers• Fit a line through the inliers and store the line• Remove the inliers from the set, goto 2

Page 13: Autonomous Localization & Navigation using 2D Laser Scanners

1313

Non-Uniform Density

Page 14: Autonomous Localization & Navigation using 2D Laser Scanners

1414

Weighted Hough Transform

Page 15: Autonomous Localization & Navigation using 2D Laser Scanners

1515

Find Maximas – 5 constraints

1. They appear in pairs: the first one is formed by peaks H1 and H2; the second one is formed by peaks H3 and H4.

2. Two peaks belonging to the same pair are symmetric with respect to the x-axis(angle).3. The two pairs are separated by 90o4. The heights of the two peaks within the same pair are exactly the same, and represent

the length of the respective line segment.5. The vertical distances between peaks within the pair are exactly the sides of the

rectangle.

In case of other obstacles in the scene, constraints 4 & 5 are not robust. So we only use 1, 2 & 3.

Page 16: Autonomous Localization & Navigation using 2D Laser Scanners

1616

Line Fitting

Page 17: Autonomous Localization & Navigation using 2D Laser Scanners

1717

Line Fitting - Example

Page 18: Autonomous Localization & Navigation using 2D Laser Scanners

1818

Localization

Page 19: Autonomous Localization & Navigation using 2D Laser Scanners

1919

Obstacle Map

Page 20: Autonomous Localization & Navigation using 2D Laser Scanners

2020

Obstacle Detection

Page 21: Autonomous Localization & Navigation using 2D Laser Scanners

2121

Planning - RRT

Page 22: Autonomous Localization & Navigation using 2D Laser Scanners

2222

Navigation

Page 23: Autonomous Localization & Navigation using 2D Laser Scanners

2323

Future Scope

Page 24: Autonomous Localization & Navigation using 2D Laser Scanners

2424

Thank You