Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Particle Filter Localization for Autonomous AUVs
Search
Ed Kelley
April 30, 2013
Research
0
36
Particle Filter Localization for Autonomous AUVs
Senior Thesis Presentation 2013
Ed Kelley
April 30, 2013
Tweet
Share
Other Decks in Research
See All in Research
3D Human Mesh Estimationについていくつかまとめてみた / Survey about 3D Human Mesh Estimation
nttcom
0
230
媒介分析と疫学
kingqwert
0
120
AIを前提とした体験の実現に向けて/toward_ai_based_experiences
monochromegane
1
260
Julia Tokyo #11 トーク: 「Juliaで歩く自動微分」
abap34
2
1.3k
Ground Metric Learning with applications in genomics
gpeyre
0
380
[Human-AI Decision Making勉強会] 説明の更新はユーザにどのような影響をもたらすか
okoso
1
220
10-ot-generic-bio.pdf
gpeyre
0
140
2024-01-23-az
sofievl
1
800
Threat Intelligence and Beyond
rishikadesai_7
0
190
Cross-Media Information Spaces and Architectures
signer
PRO
0
120
サウナでのプロジェクションマッピングの可能性の検討 / EC71koizumi
yumulab
0
220
VRChat と cluster ワールドの違い-その1-
hidetobara
0
110
Featured
See All Featured
The MySQL Ecosystem @ GitHub 2015
samlambert
244
12k
Web development in the modern age
philhawksworth
203
10k
The Pragmatic Product Professional
lauravandoore
26
5.8k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
12
1k
Testing 201, or: Great Expectations
jmmastey
30
6.4k
Writing Fast Ruby
sferik
622
60k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
501
140k
Into the Great Unknown - MozCon
thekraken
15
1k
Building Adaptive Systems
keathley
32
1.9k
Being A Developer After 40
akosma
67
580k
Infographics Made Easy
chrislema
238
18k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
352
28k
Transcript
Particle Filter Localization for Autonomous AUVs Using Augmented Reality Tags
Ed Kelley, 2013 Szymon Rusinkiewicz
aka
Where is the Quadcopter?
Motivation
This statue is cool http://www.asergeev.com/pictures/archives/2007/572/jpeg/05.jpg
I want a 3d model http://www.asergeev.com/pictures/archives/2007/572/jpeg/05.jpg
Video Games Virtual Reality Movies Archeology Architecture Maps Crash Scenes
Manual Modeling? Laser Scanner? Multi-View Stereo? Microsoft Kinect?
Manual Modeling? Laser Scanner? Multi-View Stereo? Microsoft Kinect?
Irschara et al. 2010
Easy Cheap Complete High Quality
Quadcopters!
Related Work
Irschara et al.
Engel et al.
Bills et al.
System Design
AR.Drone 2.0 http://ardrone2.parrot.com/photos/photo-album/
None
Localization + Controller = Autonomy
Localization
Local drift. tend to measurements
No GPS No rangefinders
None
Kalman Filter? Grid Based Markov? Particle Filter?
Kalman Filter? Grid Based Markov? Particle Filter?
. This is a particle
. It represents a possible pose
. x y z heading weight
Prediction Step Update the position of each particle using noisy
velocity and gyroscope readings.
Correction Step 1. Check for an augmented reality tag. 2.
Calculate transformation from camera to tag. 3. Use known coordinates of the tag to calculate the position of the quadcopter.
Correction Step 4. Weight the particles using their similarity to
this calculated position. 5. Perform weighted resampling of the particles. 6. With some probability, replace particles with this calculated position.
Estimate Use a linear combination of the particle values to
create an estimated pose.
Testing
Gyroscope
Ultrasound
AR Tag
AR Tag
AR Tag
AR Tag
Manual Flight Test
None
None
None
None
None
Conclusion
Particle filter localization using augmented reality tags performs substantially better
than integrated velocity alone.
AR Tags are highly dependent on lighting.
Its called Hardware for a reason.
Next steps... Full integration with controller. Modeling objects.
Thanks!