SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.06933 · 2019

Self-Supervised Correspondence in Visuomotor Policy Learning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper we explore using self-supervised correspondence for improving the generalization performance and sample efficiency of visuomotor policy learning. Prior work has primarily used approaches such as autoencoding, pose-based losses, and end-to-end policy optimization in order to train the visual portion of visuomotor policies. We instead propose an approach using self-supervised dense visual correspondence training, and show this enables visuomotor policy learning with surprisingly high generalization performance with modest amounts of data: using imitation learning, we demonstrate extensive hardware validation on challenging manipulation tasks with as few as 50 demonstrations. Our learned policies can generalize across classes of objects, react to deformable object configurations, and manipulate textureless symmetrical objects in a variety of backgrounds, all with closed-loop, real-time vision-based policies. Simulated imitation learning experiments suggest that correspondence training offers sample complexity and generalization benefits compared to autoencoding and end-to-end training.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1909.06933")
get_code_for_paper("1909.06933")
have("1909.06933")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1909.06933.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1909.06933.svg)](https://syntology.ai/paper/1909.06933)

Connect an agent — have() is free.