Egocentric Instruction-oriented Affordance Prediction via Large Multimodal Model

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ji, Bokai, Gu, Jie, Ma, Xiaokang, Tang, Chu, Chen, Jingmin, Li, Guangxia
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912553070755840
author Ji, Bokai
Gu, Jie
Ma, Xiaokang
Tang, Chu
Chen, Jingmin
Li, Guangxia
author_facet Ji, Bokai
Gu, Jie
Ma, Xiaokang
Tang, Chu
Chen, Jingmin
Li, Guangxia
contents Affordance is crucial for intelligent robots in the context of object manipulation. In this paper, we argue that affordance should be task-/instruction-dependent, which is overlooked by many previous works. That is, different instructions can lead to different manipulation regions and directions even for the same object. According to this observation, we present a new dataset comprising fifteen thousand object-instruction-affordance triplets. All scenes in the dataset are from an egocentric viewpoint, designed to approximate the perspective of a human-like robot. Furthermore, we investigate how to enable large multimodal models (LMMs) to serve as affordance predictors by implementing a ``search against verifiers'' pipeline. An LMM is asked to progressively predict affordances, with the output at each step being verified by itself during the iterative process, imitating a reasoning process. Experiments show that our method not only unlocks new instruction-oriented affordance prediction capabilities, but also achieves outstanding performance broadly.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17922
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Egocentric Instruction-oriented Affordance Prediction via Large Multimodal Model
Ji, Bokai
Gu, Jie
Ma, Xiaokang
Tang, Chu
Chen, Jingmin
Li, Guangxia
Robotics
Computer Vision and Pattern Recognition
Affordance is crucial for intelligent robots in the context of object manipulation. In this paper, we argue that affordance should be task-/instruction-dependent, which is overlooked by many previous works. That is, different instructions can lead to different manipulation regions and directions even for the same object. According to this observation, we present a new dataset comprising fifteen thousand object-instruction-affordance triplets. All scenes in the dataset are from an egocentric viewpoint, designed to approximate the perspective of a human-like robot. Furthermore, we investigate how to enable large multimodal models (LMMs) to serve as affordance predictors by implementing a ``search against verifiers'' pipeline. An LMM is asked to progressively predict affordances, with the output at each step being verified by itself during the iterative process, imitating a reasoning process. Experiments show that our method not only unlocks new instruction-oriented affordance prediction capabilities, but also achieves outstanding performance broadly.
title Egocentric Instruction-oriented Affordance Prediction via Large Multimodal Model
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.17922