Push Proposal Network Andreas Eitel, Nico Hauff, Wolfram Burgard - - PowerPoint PPT Presentation

push proposal network
SMART_READER_LITE
LIVE PREVIEW

Push Proposal Network Andreas Eitel, Nico Hauff, Wolfram Burgard - - PowerPoint PPT Presentation

Learning to Singulate Objects using a Push Proposal Network Andreas Eitel, Nico Hauff, Wolfram Burgard Removing Clutter is Hard Manipulation of objects in unstructured scenes is challenging due to uncertainty from perception Motivation


slide-1
SLIDE 1

Learning to Singulate Objects using a Push Proposal Network

Andreas Eitel, Nico Hauff, Wolfram Burgard

slide-2
SLIDE 2

Removing Clutter is Hard

Manipulation of objects in unstructured scenes is challenging due to uncertainty from perception

slide-3
SLIDE 3

Motivation

physical interaction Input Output Object singulation = physically separating objects in cluttered tabletop scenes

slide-4
SLIDE 4

Singulation and Interactive Object Perception

How many objects are in the image?

slide-5
SLIDE 5

Singulation and Interactive Object Perception

Singulation facilitates perception

slide-6
SLIDE 6

Contributions

  • We train a CNN to detect favourable push actions

from over-segmented images in order to clear clutter

  • In comparison to previous work

1. Model-free approach, no physics simulator, no object knowledge 2. Learn features automatically

slide-7
SLIDE 7

Approach

slide-8
SLIDE 8

Approach

  • 1. Sample push proposals from over-segmented

RGB-D image

slide-9
SLIDE 9

Over-segmentation

Objects get segmented into multiple facets using RGB-D Segmenter [1] [1] Richtsfeld et al. 2012

slide-10
SLIDE 10

Approach

  • 2. Classify set of sampled push proposals with push

proposal network

slide-11
SLIDE 11

Approach

  • 3. Perform motion planning
slide-12
SLIDE 12

Approach

  • 4. Execute first successful motion plan
slide-13
SLIDE 13

Definitions

  • Neural network with parameters
  • Input is an over-segmented image and a push

proposal action

  • The push proposal consists of a start position pixel

and a push angle both defined in the image plane

slide-14
SLIDE 14

Supervised Learning

Training data is labeled by an expert user who gives a binary label for successful or unsuccessful push action

slide-15
SLIDE 15

Iterative Training

slide-16
SLIDE 16

How to Fuse Image and Push Proposal Action

  • Key idea: only need to capture local context

between objects, not global

  • Fuse image and push proposal action using rigid

image transformations

  • Result is a local push-centric image

translation rotation

slide-17
SLIDE 17

Push Proposal CNN

Gets push-centric image as input

Predicts probability of singulation success for

  • ne proposal
slide-18
SLIDE 18

Experimental Setup

  • PR2 robot with Kinect 2
  • All experiments with unknown objects in cluttered

initial configurations

  • Increasing difficulty level 4-8 objects
  • Singulation trial is successful if all objects are

separated by at least 3cm

slide-19
SLIDE 19

Results with 6 and 8 Objects

success fail, two objects at top still touching success fail, no motion plan found

  • bjects too close to robot
slide-20
SLIDE 20

Quantitative Results

  • Success rate of our best network
  • 6 objects 70%, 25 trials
  • 8 objects 40%, 10 trials
  • Improvement with respect to manual baseline

method is 30%

slide-21
SLIDE 21

Video

slide-22
SLIDE 22

Conclusions

  • Novel learning-based approach for clearing object

clutter based on CNN

  • Neural network generalizes well to novel objects

and cluttered object configurations

  • Novel method for fusing image and action

representation into network

  • Successful singulation experiments with up to 8

cluttered objects

slide-23
SLIDE 23

Future Work

  • Move from supervised to semi- and self-supervised

learning

  • Extension of network with multi-class output for

prediction of varying push lengths

slide-24
SLIDE 24

Thank you for your attention!

Learning to Singulate Objects using a Push Proposal Network http://robotpush.cs.uni-freiburg.de