Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation

TL;DR

This paper introduces Dense Object Nets, a self-supervised method for learning dense visual object descriptors that are task-agnostic, applicable to rigid and non-rigid objects, and useful for robotic manipulation tasks.

Contribution

The authors present Dense Object Nets, enabling rapid, self-supervised learning of dense descriptors for various objects, including multi-object and class-level generalization, for robotic manipulation.

Findings

Can be trained in approximately 20 minutes

Effective for both rigid and non-rigid objects

Enables grasping specific points and transferring grasps across objects

Abstract

What is the right object representation for manipulation? We would like robots to visually perceive scenes and learn an understanding of the objects in them that (i) is task-agnostic and can be used as a building block for a variety of manipulation tasks, (ii) is generally applicable to both rigid and non-rigid objects, (iii) takes advantage of the strong priors provided by 3D vision, and (iv) is entirely learned from self-supervision. This is hard to achieve with previous methods: much recent work in grasping does not extend to grasping specific objects or other tasks, whereas task-specific learning may require many trials to generalize well across object configurations or other tasks. In this paper we present Dense Object Nets, which build on recent developments in self-supervised dense descriptor learning, as a consistent object representation for visual understanding and manipulation. We demonstrate they can be trained quickly (approximately 20 minutes) for a wide variety of previously unseen and potentially non-rigid objects. We additionally present novel contributions to enable multi-object descriptor learning, and show that by modifying our training procedure, we can either acquire descriptors which generalize across classes of objects, or descriptors that are distinct for each object instance. Finally, we demonstrate the novel application of learned dense descriptors to robotic manipulation. We demonstrate grasping of specific points on an object across potentially deformed object configurations, and demonstrate using class general descriptors to transfer specific grasps across objects in a class.