Login / Signup
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:
Robotics: Science and Systems (2020)
Keyphrases
</>
motion planning
action sequences
input image
visual scene
complex scenes
low level
image classification
image representation
image features
visual features
spatial relations
image retrieval
image content
degrees of freedom
video sequences
multiscale
three dimensional
knowledge base
path planning
initial state