DeepAI AI Chat
Log In Sign Up

Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learning

by   Philipp Jund, et al.
University of Freiburg

To operate intelligently in domestic environments, robots require the ability to understand arbitrary spatial relations between objects and to generalize them to objects of varying sizes and shapes. In this work, we present a novel end-to-end approach to generalize spatial relations based on distance metric learning. We train a neural network to transform 3D point clouds of objects to a metric space that captures the similarity of the depicted spatial relations, using only geometric models of the objects. Our approach employs gradient-based optimization to compute object poses in order to imitate an arbitrary target relation by reducing the distance to it under the learned metric. Our results based on simulated and real-world experiments show that the proposed method is able to generalize to unknown objects over a continuous spectrum of spatial relations.


page 1

page 3

page 4


Positive semidefinite support vector regression metric learning

Most existing metric learning methods focus on learning a similarity or ...

Relational Learning for Skill Preconditions

To determine if a skill can be executed in any given environment, a robo...

Learning Object Placements For Relational Instructions by Hallucinating Scene Representations

Robots coexisting with humans in their environment and performing servic...

Deep Metric Learning Beyond Binary Supervision

Metric Learning for visual similarity has mostly adopted binary supervis...

Approximation of dilation-based spatial relations to add structural constraints in neural networks

Spatial relations between objects in an image have proved useful for str...

A New Similarity Space Tailored for Supervised Deep Metric Learning

We propose a novel deep metric learning method. Differently from many wo...

Invariant Feature Mappings for Generalizing Affordance Understanding Using Regularized Metric Learning

This paper presents an approach for learning invariant features for obje...