3D Affordance Keypoint Detection for Robotic Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zhiyang, Zhao, Ruiteng, Zhou, Lei, Yuan, Chengran, Wu, Yuwei, Guo, Sheng, Zhang, Zhengshen, Liu, Chenchen, Ang Jr, Marcelo H
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911290325204992
author Liu, Zhiyang
Zhao, Ruiteng
Zhou, Lei
Yuan, Chengran
Wu, Yuwei
Guo, Sheng
Zhang, Zhengshen
Liu, Chenchen
Ang Jr, Marcelo H
author_facet Liu, Zhiyang
Zhao, Ruiteng
Zhou, Lei
Yuan, Chengran
Wu, Yuwei
Guo, Sheng
Zhang, Zhengshen
Liu, Chenchen
Ang Jr, Marcelo H
contents This paper presents a novel approach for affordance-informed robotic manipulation by introducing 3D keypoints to enhance the understanding of object parts' functionality. The proposed approach provides direct information about what the potential use of objects is, as well as guidance on where and how a manipulator should engage, whereas conventional methods treat affordance detection as a semantic segmentation task, focusing solely on answering the what question. To address this gap, we propose a Fusion-based Affordance Keypoint Network (FAKP-Net) by introducing 3D keypoint quadruplet that harnesses the synergistic potential of RGB and Depth image to provide information on execution position, direction, and extent. Benchmark testing demonstrates that FAKP-Net outperforms existing models by significant margins in affordance segmentation task and keypoint detection task. Real-world experiments also showcase the reliability of our method in accomplishing manipulation tasks with previously unseen objects.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22195
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 3D Affordance Keypoint Detection for Robotic Manipulation
Liu, Zhiyang
Zhao, Ruiteng
Zhou, Lei
Yuan, Chengran
Wu, Yuwei
Guo, Sheng
Zhang, Zhengshen
Liu, Chenchen
Ang Jr, Marcelo H
Robotics
This paper presents a novel approach for affordance-informed robotic manipulation by introducing 3D keypoints to enhance the understanding of object parts' functionality. The proposed approach provides direct information about what the potential use of objects is, as well as guidance on where and how a manipulator should engage, whereas conventional methods treat affordance detection as a semantic segmentation task, focusing solely on answering the what question. To address this gap, we propose a Fusion-based Affordance Keypoint Network (FAKP-Net) by introducing 3D keypoint quadruplet that harnesses the synergistic potential of RGB and Depth image to provide information on execution position, direction, and extent. Benchmark testing demonstrates that FAKP-Net outperforms existing models by significant margins in affordance segmentation task and keypoint detection task. Real-world experiments also showcase the reliability of our method in accomplishing manipulation tasks with previously unseen objects.
title 3D Affordance Keypoint Detection for Robotic Manipulation
topic Robotics
url https://arxiv.org/abs/2511.22195