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

TL;DR

This paper introduces CAZSL, a context-aware zero-shot learning approach using Siamese networks to enable robots to quickly generalize physical interaction models across different objects based on contextual features.

Contribution

The paper proposes a novel deep learning framework, CAZSL, that generalizes physical models for robotic manipulation through context-aware zero-shot learning with Siamese networks.

Findings

Successfully tested on Omnipush dataset

Demonstrated ability to generalize across object parameters

Achieved rapid adaptation to new object contexts

Abstract

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 deep 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. Codes for CAZSL are available at https://www.merl.com/research/license/CAZSL.