Deep Visual Foresight for Planning Robot Motion

10/03/2016
by   Chelsea Finn, et al.
0

A key challenge in scaling up robot learning to many skills and environments is removing the need for human supervision, so that robots can collect their own data and improve their own performance without being limited by the cost of requesting human feedback. Model-based reinforcement learning holds the promise of enabling an agent to learn to predict the effects of its actions, which could provide flexible predictive models for a wide range of tasks and environments, without detailed human supervision. We develop a method for combining deep action-conditioned video prediction models with model-predictive control that uses entirely unlabeled training data. Our approach does not require a calibrated camera, an instrumented training set-up, nor precise sensing and actuation. Our results show that our method enables a real robot to perform nonprehensile manipulation -- pushing objects -- and can handle novel objects not seen during training.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

research
10/15/2017

Self-Supervised Visual Planning with Temporal Skip Connections

In order to autonomously learn wide repertoires of complex skills, robot...
research
10/24/2019

RoboNet: Large-Scale Multi-Robot Learning

Robot learning has emerged as a promising tool for taming the complexity...
research
04/28/2022

Human Motion Control of Quadrupedal Robots using Deep Reinforcement Learning

A motion-based control interface promises flexible robot operations in d...
research
12/03/2018

Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control

Deep reinforcement learning (RL) algorithms can learn complex robotic sk...
research
10/02/2022

An optimal open-loop strategy for handling a flexible beam with a robot manipulator

Fast and safe manipulation of flexible objects with a robot manipulator ...
research
10/02/2018

Time Reversal as Self-Supervision

A longstanding challenge in robot learning for manipulation tasks has be...
research
12/30/2019

Learning Predictive Models From Observation and Interaction

Learning predictive models from interaction with the world allows an age...

Please sign up or login with your details

Forgot password? Click here to reset