CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context

03/26/2020
by   Wenyu Zhang, et al.
0

Learning accurate models of the physical world is required for a lot of robotic manipulation tasks. However, during manipulation, robots are expected to interact with unknown workpieces so that building predictive models which can generalize over a number of these objects is highly desirable. In this paper, we study the problem of designing learning agents which can generalize their models of the physical world by building context-aware learning models. The purpose of these agents is to quickly adapt and/or generalize their notion of physics of interaction in the real world based on certain features about the interacting objects that provide different contexts to the predictive models. With this motivation, we present context-aware zero shot learning (CAZSL, pronounced as 'casual') models, an approach utilizing a Siamese network architecture, embedding space masking and regularization based on context variables which allows us to learn a model that can generalize to different parameters or features of the interacting objects. We test our proposed learning algorithm on the recently released Omnipush datatset that allows testing of meta-learning capabilities using low-dimensional data.

READ FULL TEXT

page 1

page 5

research
04/19/2019

Context-Aware Zero-Shot Recognition

We present a novel problem setting in zero-shot learning, zero-shot obje...
research
03/18/2017

Towards Context-aware Interaction Recognition

Recognizing how objects interact with each other is a crucial task in vi...
research
04/24/2019

Context-Aware Zero-Shot Learning for Object Recognition

Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by levera...
research
04/11/2019

TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning

Learning good feature embeddings for images often requires substantial t...
research
11/18/2021

Visual Goal-Directed Meta-Learning with Contextual Planning Networks

The goal of meta-learning is to generalize to new tasks and goals as qui...
research
01/31/2022

Compositional Multi-Object Reinforcement Learning with Linear Relation Networks

Although reinforcement learning has seen remarkable progress over the la...
research
05/26/2019

Unsupervised Intuitive Physics from Past Experiences

We are interested in learning models of intuitive physics similar to the...

Please sign up or login with your details

Forgot password? Click here to reset