Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Xinyu, Luo, Shengcheng, Yang, Yanchao, Li, Yong-Lu, Lu, Cewu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2407.14758
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910536627650560
author Xu, Xinyu
Luo, Shengcheng
Yang, Yanchao
Li, Yong-Lu
Lu, Cewu
author_facet Xu, Xinyu
Luo, Shengcheng
Yang, Yanchao
Li, Yong-Lu
Lu, Cewu
contents Building a general-purpose intelligent home-assistant agent skilled in diverse tasks by human commands is a long-term blueprint of embodied AI research, which poses requirements on task planning, environment modeling, and object interaction. In this work, we study primitive mobile manipulations for embodied agents, i.e. how to navigate and interact based on an instructed verb-noun pair. We propose DISCO, which features non-trivial advancements in contextualized scene modeling and efficient controls. In particular, DISCO incorporates differentiable scene representations of rich semantics in object and affordance, which is dynamically learned on the fly and facilitates navigation planning. Besides, we propose dual-level coarse-to-fine action controls leveraging both global and local cues to accomplish mobile manipulation tasks efficiently. DISCO easily integrates into embodied tasks such as embodied instruction following. To validate our approach, we take the ALFRED benchmark of large-scale long-horizon vision-language navigation and interaction tasks as a test bed. In extensive experiments, we make comprehensive evaluations and demonstrate that DISCO outperforms the art by a sizable +8.6% success rate margin in unseen scenes, even without step-by-step instructions. Our code is publicly released at https://github.com/AllenXuuu/DISCO.
format Preprint
id arxiv_https___arxiv_org_abs_2407_14758
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control
Xu, Xinyu
Luo, Shengcheng
Yang, Yanchao
Li, Yong-Lu
Lu, Cewu
Computer Vision and Pattern Recognition
Building a general-purpose intelligent home-assistant agent skilled in diverse tasks by human commands is a long-term blueprint of embodied AI research, which poses requirements on task planning, environment modeling, and object interaction. In this work, we study primitive mobile manipulations for embodied agents, i.e. how to navigate and interact based on an instructed verb-noun pair. We propose DISCO, which features non-trivial advancements in contextualized scene modeling and efficient controls. In particular, DISCO incorporates differentiable scene representations of rich semantics in object and affordance, which is dynamically learned on the fly and facilitates navigation planning. Besides, we propose dual-level coarse-to-fine action controls leveraging both global and local cues to accomplish mobile manipulation tasks efficiently. DISCO easily integrates into embodied tasks such as embodied instruction following. To validate our approach, we take the ALFRED benchmark of large-scale long-horizon vision-language navigation and interaction tasks as a test bed. In extensive experiments, we make comprehensive evaluations and demonstrate that DISCO outperforms the art by a sizable +8.6% success rate margin in unseen scenes, even without step-by-step instructions. Our code is publicly released at https://github.com/AllenXuuu/DISCO.
title DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.14758