Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter

Georgios Tziafas, Yucheng Xu, Arushi Goel, Mohammadreza Kasaei, Alex Li, Hamidreza Kasaei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Robots operating in human-centric environments require the integration of visual grounding and grasping capabilities to effectively manipulate objects based on user instructions. This work focuses on the task of referring grasp synthesis, which predicts a grasp pose for an object referred through natural language in cluttered scenes. Existing approaches often employ multi-stage pipelines that first segment the referred object and then propose a suitable grasp, and are evaluated in private datasets or simulators that do not capture the complexity of natural indoor scenes. To address these limitations, we develop a challenging benchmark based on cluttered indoor scenes from OCID dataset, for which we generate referring expressions and connect them with 4-DoF grasp poses. Further, we propose a novel end-to-end model (CROG) that leverages the visual grounding capabilities of CLIP to learn grasp synthesis directly from image-text pairs. Our results show that vanilla integration of CLIP with pretrained models transfers poorly in our challenging benchmark, while CROG achieves significant improvements both in terms of grounding and grasping. Extensive robot experiments in both simulation and hardware demonstrate the effectiveness of our approach in challenging interactive object grasping scenarios that include clutter.
Original languageEnglish
Title of host publicationProceedings of The 7th Conference on Robot Learning
PublisherMIT Press
Number of pages17
Publication statusPublished - 2 Dec 2023
EventThe Conference on Robot Learning 2023 - Atlanta, United States
Duration: 6 Nov 20239 Nov 2023
Conference number: 7

Publication series

NameProceedings of Machine Learning Research
ISSN (Electronic)2640-3498


ConferenceThe Conference on Robot Learning 2023
Abbreviated titleCoRL 2023
Country/TerritoryUnited States
Internet address

Keywords / Materials (for Non-textual outputs)

  • language-guided robot grasping
  • referring grasp synthesis
  • visual grounding


Dive into the research topics of 'Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter'. Together they form a unique fingerprint.

Cite this