S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency

09/30/2020
by   Mel Večerík, et al.
5

A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria, e.g. image reconstruction, smoothness in latent space, or usefulness for control, or else make use of large datasets annotated with specific features (bounding boxes, segmentations, etc.). However, both approaches often struggle to capture the fine-detail required for precision tasks on specific objects, e.g. grasping and mating a plug and socket. We argue that these difficulties arise from a lack of geometric structure in these models. In this work we advocate semantic 3D keypoints as a visual representation, and present a semi-supervised training objective that can allow instance or category-level keypoints to be trained to 1-5 millimeter-accuracy with minimal supervision. Furthermore, unlike local texture-based approaches, our model integrates contextual information from a large area and is therefore robust to occlusion, noise, and lack of discernible texture. We demonstrate that this ability to locate semantic keypoints enables high level scripting of human understandable behaviours. Finally we show that these keypoints provide a good way to define reward functions for reinforcement learning and are a good representation for training agents.

READ FULL TEXT

page 1

page 2

page 3

page 7

page 11

research
03/13/2020

Self-supervised Single-view 3D Reconstruction via Semantic Consistency

We learn a self-supervised, single-view 3D reconstruction model that pre...
research
11/16/2018

Grasp2Vec: Learning Object Representations from Self-Supervised Grasping

Well structured visual representations can make robot learning faster an...
research
02/27/2020

Semantically-Guided Representation Learning for Self-Supervised Monocular Depth

Self-supervised learning is showing great promise for monocular depth es...
research
01/23/2020

Semi-supervised Grasp Detection by Representation Learning in a Vector Quantized Latent Space

Determining quality grasps from an image is an important area of researc...
research
12/03/2021

Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks

Self-supervised learning aims to learn image feature representations wit...

Please sign up or login with your details

Forgot password? Click here to reset