A Universal Semantic-Geometric Representation for Robotic ManipulationDownload PDF

Published: 30 Aug 2023, Last Modified: 03 Jul 2024CoRL 2023 PosterReaders: Everyone
Keywords: Representation Learning, Robotic Manipulation
TL;DR: A representation that integrates both semantic understanding and 3D spatial reasoning.
Abstract: Robots rely heavily on sensors, especially RGB and depth cameras, to perceive and interact with the world. RGB cameras record 2D images with rich semantic information while missing precise spatial information. On the other side, depth cameras offer critical 3D geometry data but capture limited semantics. Therefore, integrating both modalities is crucial for learning representations for robotic perception and control. However, current research predominantly focuses on only one of these modalities, neglecting the benefits of incorporating both. To this end, we present $\textbf{Semantic-Geometric Representation} (\textbf{SGR})$, a universal perception module for robotics that leverages the rich semantic information of large-scale pre-trained 2D models and inherits the merits of 3D spatial reasoning. Our experiments demonstrate that SGR empowers the agent to successfully complete a diverse range of simulated and real-world robotic manipulation tasks, outperforming state-of-the-art methods significantly in both single-task and multi-task settings. Furthermore, SGR possesses the capability to generalize to novel semantic attributes, setting it apart from the other methods. Project website: https://semantic-geometric-representation.github.io.
Student First Author: yes
Supplementary Material: zip
Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)
Website: https://semantic-geometric-representation.github.io
Publication Agreement: pdf
Poster Spotlight Video: mp4
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 7 code implementations](https://www.catalyzex.com/paper/a-universal-semantic-geometric-representation/code)
14 Replies