An Object-based World Model and its Uses Mac Mason Bhaskara Marthi - - PowerPoint PPT Presentation

an object based world model and its uses
SMART_READER_LITE
LIVE PREVIEW

An Object-based World Model and its Uses Mac Mason Bhaskara Marthi - - PowerPoint PPT Presentation

An Object-based World Model and its Uses Mac Mason Bhaskara Marthi I just want a robot that keeps track of my stuff - Aditi Nabar (spouse) Pipeline Point Planes in Plane Data Clouds frame Set of Kinect Plane Finder Association


slide-1
SLIDE 1

An Object-based World Model and its Uses

Mac Mason Bhaskara Marthi

slide-2
SLIDE 2

“I just want a robot that keeps track of my stuff”

  • Aditi Nabar (spouse)
slide-3
SLIDE 3
slide-4
SLIDE 4

Pipeline

Kinect Plane Finder Plane Data Association Clustering Object Data Association DB

Point Clouds Planes in frame Points above planes Object clusters Set of planes Set of objects + metadata

slide-5
SLIDE 5

Implementation

  • PR2 + Kinect
  • ROS, PCL, Nav stack
  • MongoDB for storing info
  • Binary blobs + metadata (color, shape, ...)
  • Partition by run
  • Efficient queries over location, attributes
slide-6
SLIDE 6
slide-7
SLIDE 7
slide-8
SLIDE 8
slide-9
SLIDE 9
slide-10
SLIDE 10
slide-11
SLIDE 11
slide-12
SLIDE 12

Data Association

  • Match within runs based on spatial overlap
  • Don’t commit to matches across runs
  • Discover likely matches at query time
slide-13
SLIDE 13

Attribute perception

  • No object categories or instances
  • Instead, extract descriptive features

Color: Red Shape: Cylinder Diameter: 0.1m

slide-14
SLIDE 14

Sensors to symbols

  • Sensor level
  • Point clouds, images,
  • Normals, SIFT features, ...
  • Symbolic level: objects, categories, relations
  • How to connect?
slide-15
SLIDE 15

Bridging the gap

[Galindo et al, 2008]

slide-16
SLIDE 16

Reify Geometry

  • Surfaces, clusters, cluttered regions, ...
  • Color, shape, topology, ...
  • A lot can be done at this level!
slide-17
SLIDE 17

Conclusions

  • Object-based world model
  • Allows
  • Change detection
  • Semantic querying
  • Robust to noisy perception
slide-18
SLIDE 18

Conclusions

  • Object-based world model
  • Allows
  • Change detection
  • Semantic querying
  • Robust to noisy perception

Thank you!