Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image.

Danny Drieß Jung-Su Ha Marc Toussaint

Published in: CoRR (2020)

Keyphrases

motion planning
action sequences
input image
multiscale
visual scene
low level
complex scenes
image set
image regions
image content
spatial relations
image representation
image classification
image features
mobile robot
reinforcement learning
path planning
human actions
multiple objects
video sequences