Precise Object Placement with Pose Distance Estimations for Different Objects and Grippers

TL;DR

This paper presents a neural network-based method for grasping and precise placement of objects in cluttered scenes, achieving higher success and placement accuracy by estimating object poses, class, and pose distances from a single depth image.

Contribution

It introduces a unified neural network approach that estimates object poses, classes, and placement distances simultaneously for improved grasping and placement accuracy.

Findings

Higher grasp success rates than state-of-the-art model-free methods.

More precise object placement compared to prior model-based approaches.

Effective in cluttered scenes with multiple objects.

Abstract

This paper introduces a novel approach for the grasping and precise placement of various known rigid objects using multiple grippers within highly cluttered scenes. Using a single depth image of the scene, our method estimates multiple 6D object poses together with an object class, a pose distance for object pose estimation, and a pose distance from a target pose for object placement for each automatically obtained grasp pose with a single forward pass of a neural network. By incorporating model knowledge into the system, our approach has higher success rates for grasping than state-of-the-art model-free approaches. Furthermore, our method chooses grasps that result in significantly more precise object placements than prior model-based work.