A Universal Semantic-Geometric Representation for Robotic Manipulation

Tong Zhang, Yingdong Hu, Hanchen Cui, Hang Zhao, Yang Gao
Proceedings of The 7th Conference on Robot Learning, PMLR 229:3342-3363, 2023.

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 Semantic-Geometric Representation (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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-zhang23j, title = {A Universal Semantic-Geometric Representation for Robotic Manipulation}, author = {Zhang, Tong and Hu, Yingdong and Cui, Hanchen and Zhao, Hang and Gao, Yang}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {3342--3363}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/zhang23j/zhang23j.pdf}, url = {https://proceedings.mlr.press/v229/zhang23j.html}, 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 Semantic-Geometric Representation (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.} }
Endnote
%0 Conference Paper %T A Universal Semantic-Geometric Representation for Robotic Manipulation %A Tong Zhang %A Yingdong Hu %A Hanchen Cui %A Hang Zhao %A Yang Gao %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-zhang23j %I PMLR %P 3342--3363 %U https://proceedings.mlr.press/v229/zhang23j.html %V 229 %X 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 Semantic-Geometric Representation (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.
APA
Zhang, T., Hu, Y., Cui, H., Zhao, H. & Gao, Y.. (2023). A Universal Semantic-Geometric Representation for Robotic Manipulation. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:3342-3363 Available from https://proceedings.mlr.press/v229/zhang23j.html.

Related Material