PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation

Abstract

The ability for robots to comprehend and execute manipulation tasks based on natural language instructions is a long-term goal in robotics. The dominant approaches for language-guided manipulation use 2D image representations, which face difficulties in combining multi-view cameras and inferring precise 3D positions and relationships. To address these limitations, we propose a 3D point cloud based policy called PolarNet for language-guided manipulation. It leverages carefully designed point cloud inputs, efficient point cloud encoders, and multimodal transformers to learn 3D point cloud representations and integrate them with language instructions for action prediction. PolarNet is shown to be effective and data efficient in a variety of experiments conducted on the RLBench benchmark. It outperforms state-of-the-art 2D and 3D approaches in both single-task and multi-task learning. It also achieves promising results on a real robot.
Fichier principal
Vignette du fichier
2309.15596.pdf (14.87 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04221153 , version 1 (28-09-2023)

Licence

Identifiers

Cite

Shizhe Chen, Ricardo Garcia, Cordelia Schmid, Ivan Laptev. PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation. 7th Conference on Robot Learning (CoRL 2023), Nov 2023, Atlanta, GA, United States. ⟨hal-04221153⟩
45 View
62 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More