0

DMotion: Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos

DMotion trains a forward model using unsupervised video data to represent agent motion with spatial transformation matrices, achieving superior performance in model predictive control for robotic tasks.

Year
2021
Venue
arXiv 2021
Authors
6
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2103.04301ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Learning an accurate model of the environment is essential for model-based control tasks. Existing methods in robotic visuomotor control usually learn from data with heavily labelled actions, object entities or locations, which can be demanding in many cases. To cope with this limitation, we propose a method, dubbed DMotion, that trains a forward model from video data only, via disentangling the motion of controllable agent to model the transition dynamics. An object extractor and an interaction learner are trained in an end-to-end manner without supervision. The agent's motions are explicitly represented using spatial transformation matrices containing physical meanings. In the experiments, DMotion achieves superior performance on learning an accurate forward model in a Grid World environment, as well as a more realistic robot control environment in simulation. With the accurate learned forward models, we further demonstrate their usage in model predictive control as an effective approach for robotic manipulations.

Authors

6