Image source: octomap.github.io Image source: - - PowerPoint PPT Presentation

image source octomap github io image source pirobot org
SMART_READER_LITE
LIVE PREVIEW

Image source: octomap.github.io Image source: - - PowerPoint PPT Presentation

Image source: octomap.github.io Image source: pirobot.org/blog/0015/ Map from first-person images to actions Need to learn how to reason about changing observations Add explicit Camera Projection and


slide-1
SLIDE 1
slide-2
SLIDE 2
slide-3
SLIDE 3

Image source: octomap.github.io Image source: pirobot.org/blog/0015/

slide-4
SLIDE 4
  • Map from first-person images to actions
  • Need to learn how to reason about changing observations
slide-5
SLIDE 5
  • Add explicit Camera Projection and Differentiable Mapping
  • Reason about the instruction on a static map
  • Automatically handle changing first-person observations
slide-6
SLIDE 6

Each pixel in the feature encodes an image neighbourhood

Input Image Feature Map

slide-7
SLIDE 7

Feature Map Projected Features

(Map Frame) (Image Plane in Camera Frame)

slide-8
SLIDE 8

Projected features (time )

Semantic Map (time )

Semantic Map (time )

slide-9
SLIDE 9

Semantic Map Grounding Map Goal Map

1x1 Filter 9x9 Filter

LSTM go to the left side of plane

Inferred goal location Recognized airplane

slide-10
SLIDE 10

Grounding Map Goal Map Perceptron Forward velocity

  • Output the velocity

command, given Grounding and Goal maps

  • Sent to quadcopter’s flight-

controller

Yaw rate

slide-11
SLIDE 11

Agent

Action Image Instruction

Oracle

Ground truth action Ground truth trajectory Modified variant of DAgger Trade convergence guarantees for speed and memory efficiency

slide-12
SLIDE 12

3500 Instructions + Environments Ground-truth trajectories 63 Landmarks 252 Possible Tasks Go to right side of mushroom

T

  • tal number of rollouts:

3500 oracle 2000 policy

slide-13
SLIDE 13

83.47 28.67 87.87

20 40 60 80 100 GSMN (Ours) NN with no Mapping Oracle

Outperform standard NN with no mapping Very close to oracle performance

slide-14
SLIDE 14

Feature Extraction Mapping 1x1 Filter 9x9 Filter

MLP

LSTM

Go

  • to

to th the e left left sid side e of

  • f

plan plane

Action

Image Features

Instruction Embedding

Grounding Map Semantic Map Goal Map