A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Rongtao, Zhang, Jian, Guo, Minghao, Wen, Youpeng, Yang, Haoting, Lin, Min, Huang, Jianzheng, Li, Zhe, Zhang, Kaidong, Wang, Liqiong, Kuang, Yuxuan, Cao, Meng, Zheng, Feng, Liang, Xiaodan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917210573766656
author Xu, Rongtao
Zhang, Jian
Guo, Minghao
Wen, Youpeng
Yang, Haoting
Lin, Min
Huang, Jianzheng
Li, Zhe
Zhang, Kaidong
Wang, Liqiong
Kuang, Yuxuan
Cao, Meng
Zheng, Feng
Liang, Xiaodan
author_facet Xu, Rongtao
Zhang, Jian
Guo, Minghao
Wen, Youpeng
Yang, Haoting
Lin, Min
Huang, Jianzheng
Li, Zhe
Zhang, Kaidong
Wang, Liqiong
Kuang, Yuxuan
Cao, Meng
Zheng, Feng
Liang, Xiaodan
contents Robotic manipulation faces critical challenges in understanding spatial affordances--the "where" and "how" of object interactions--essential for complex manipulation tasks like wiping a board or stacking objects. Existing methods, including modular-based and end-to-end approaches, often lack robust spatial reasoning capabilities. Unlike recent point-based and flow-based affordance methods that focus on dense spatial representations or trajectory modeling, we propose A0, a hierarchical affordance-aware diffusion model that decomposes manipulation tasks into high-level spatial affordance understanding and low-level action execution. A0 leverages the Embodiment-Agnostic Affordance Representation, which captures object-centric spatial affordances by predicting contact points and post-contact trajectories. A0 is pre-trained on 1 million contact points data and fine-tuned on annotated trajectories, enabling generalization across platforms. Key components include Position Offset Attention for motion-aware feature extraction and a Spatial Information Aggregation Layer for precise coordinate mapping. The model's output is executed by the action execution module. Experiments on multiple robotic systems (Franka, Kinova, Realman, and Dobot) demonstrate A0's superior performance in complex tasks, showcasing its efficiency, flexibility, and real-world applicability.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12636
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation
Xu, Rongtao
Zhang, Jian
Guo, Minghao
Wen, Youpeng
Yang, Haoting
Lin, Min
Huang, Jianzheng
Li, Zhe
Zhang, Kaidong
Wang, Liqiong
Kuang, Yuxuan
Cao, Meng
Zheng, Feng
Liang, Xiaodan
Robotics
Robotic manipulation faces critical challenges in understanding spatial affordances--the "where" and "how" of object interactions--essential for complex manipulation tasks like wiping a board or stacking objects. Existing methods, including modular-based and end-to-end approaches, often lack robust spatial reasoning capabilities. Unlike recent point-based and flow-based affordance methods that focus on dense spatial representations or trajectory modeling, we propose A0, a hierarchical affordance-aware diffusion model that decomposes manipulation tasks into high-level spatial affordance understanding and low-level action execution. A0 leverages the Embodiment-Agnostic Affordance Representation, which captures object-centric spatial affordances by predicting contact points and post-contact trajectories. A0 is pre-trained on 1 million contact points data and fine-tuned on annotated trajectories, enabling generalization across platforms. Key components include Position Offset Attention for motion-aware feature extraction and a Spatial Information Aggregation Layer for precise coordinate mapping. The model's output is executed by the action execution module. Experiments on multiple robotic systems (Franka, Kinova, Realman, and Dobot) demonstrate A0's superior performance in complex tasks, showcasing its efficiency, flexibility, and real-world applicability.
title A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation
topic Robotics
url https://arxiv.org/abs/2504.12636