Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds

TL;DR

This paper presents Spot-Compose, a comprehensive framework that integrates open-vocabulary 3D instance segmentation and grasp pose estimation for robotic manipulation tasks like object retrieval and drawer opening in human environments.

Contribution

The work introduces a novel integrated framework combining recent 3D segmentation and grasping methods for real-world robotic manipulation tasks.

Findings

Achieved 51% success in dynamic object retrieval.

Achieved 82% success in drawer opening.

Demonstrated robustness in real-world experiments.

Abstract

In recent years, modern techniques in deep learning and large-scale datasets have led to impressive progress in 3D instance segmentation, grasp pose estimation, and robotics. This allows for accurate detection directly in 3D scenes, object- and environment-aware grasp prediction, as well as robust and repeatable robotic manipulation. This work aims to integrate these recent methods into a comprehensive framework for robotic interaction and manipulation in human-centric environments. Specifically, we leverage 3D reconstructions from a commodity 3D scanner for open-vocabulary instance segmentation, alongside grasp pose estimation, to demonstrate dynamic picking of objects, and opening of drawers. We show the performance and robustness of our model in two sets of real-world experiments including dynamic object retrieval and drawer opening, reporting a 51% and 82% success rate respectively. Code of our framework as well as videos are available on: https://spot-compose.github.io/.