NeRFuser: Diffusion Guided Multi-Task 3D Policy Learning

Ge Yan, Yueh-Hua Wu, Xiaolong Wang

Primary Area: applications to robotics, autonomy, planning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Robotic Manipulation, Neural Radiance Field, Pre-Training, Diffusion

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: This paper presents NeRFuser, a language-conditioned multi-task policy framework that integrates neural rendering pre-training and diffusion training to enforce multi-modality learning in action sequence spaces. To learn a generalizable multi-task policy with few demonstrations, the pre-training phase of NeRFuser leverages neural rendering to distill 2D semantic features from foundation models such as Stable Diffusion to a 3D space, which provides a comprehensive semantic understanding regarding the scene. Consequently, it allows various applications to challenging robotic tasks requiring rich 3D semantics and accurate geometry. Furthermore, we introduce a novel approach utilizing diffusion training to learn a vision and language feature that encapsulates the inherent multi-modality in the multi-task demonstrations. By reconstructing the action sequences from different tasks via the diffusion process, the model is capable of distinguishing different modalities and thus improving the robustness and the generalizability of the learned representation. NeRFuser significantly surpasses SOTA NeRF-based multi-task manipulation approaches with over 30\% improvement in success rate. Videos: https://nerfuser.github.io/.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1182