paper-with-me

홈 › Papers

TRACER: Texture-Robust Affordance Chain-of-Thought for Deformable-Object Refinement

2026-01-28 · Wanjun Jia, Kang Li, Fan Yang, Mengfei Duan, Wenrui Chen, Yiming Jiang, Hui Zhang, Kailun Yang, Zhiyong Li, Yaonan Wang arxiv

The central challenge in robotic manipulation of deformable objects lies in aligning high-level semantic instructions with physical interaction points under complex appearance and texture variations. Due to near-infinite degrees of freedom, complex dynamics, and heterogeneous patterns, existing vision-based affordance prediction methods often suffer from boundary overflow and fragmented functional regions. To address these issues, we propose TRACER, a Texture-Robust Affordance Chain-of-thought with dEformable-object Refinement framework, which establishes a cross-hierarchical mapping from hierarchical semantic reasoning to appearance-robust and physically consistent functional region refinement. Specifically, a Tree-structured Affordance Chain-of-Thought (TA-CoT) is formulated to decompose high-level task intentions into hierarchical sub-task semantics, providing consistent guidance across various execution stages. To ensure spatial integrity, a Spatial-Constrained Boundary Refinement (SCBR) mechanism is introduced to suppress prediction spillover, guiding the perceptual response to converge toward authentic interaction manifolds. Furthermore, an Interactive Convergence Refinement Flow (ICRF) is developed to aggregate discrete pixels corrupted by appearance noise, significantly enhancing the spatial continuity and physical plausibility of the identified functional regions. Extensive experiments conducted on the Fine-AGDDO15 dataset and a real-world robotic platform demonstrate that TRACER significantly improves affordance grounding precision across diverse textures and patterns inherent to deformable objects. More importantly, it enhances the success rate of long-horizon tasks, effectively bridging the gap between high-level semantic reasoning and low-level physical execution. The source code and dataset will be made publicly available at https://github.com/Dikay1/TRACER.

📄 PDF Abstract BibTeX arXiv:2601.20208

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AffordanceGrasp-R1:Leveraging Reasoning-Based Affordance Segmentation with Reinforcement Learning for Robotic Grasping

2026-02-03 · Dingyi Zhou, Mu He, Zhuowei Fang, Xiangtong Yao 외 arxiv

We introduce AffordanceGrasp-R1, a reasoning-driven affordance segmentation framework for robotic grasping that combines a chain-of-thought (CoT) cold-start strategy with reinforcement learning to enhance deduction and s…

Reinforcement LearningRobotic Grasping

Learning Foresightful Dense Visual Affordance for Deformable Object Manipulation

2023-03-20 · ICCV 2023 1 · Ruihai Wu, Chuanruo Ning, Hao Dong

Understanding and manipulating deformable objects (e.g., ropes and fabrics) is an essential yet challenging task with broad applications. Difficulties come from complex states and dynamics, diverse configurations and hig…

Deformable Object ManipulationObject

PET Tracer Separation Using Conditional Diffusion Transformer with Multi-latent Space Learning

2025-06-20 · Bin Huang, Feihong Xu, Xinchong Shi, Shan Huang 외

In clinical practice, single-radiotracer positron emission tomography (PET) is commonly used for imaging. Although multi-tracer PET imaging can provide supplementary information of radiotracers that are sensitive to phys…

Computational Efficiency

Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model

2025-08-08 · Hanqing Wang, Shaoyang Wang, Yiming Zhong, Zemin Yang 외 arxiv

Affordance grounding focuses on predicting the specific regions of objects that are associated with the actions to be performed by robots. It plays a vital role in the fields of human-robot interaction, human-object inte…

Zero-shot GeneralizationReinforcement Learning

Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought

2026-05-26 · Yuchen Guo, Junli Gong, Hongmin Cai, Yiu-ming Cheung 외 arxiv

Recent segmentation models couple large language models (LLMs) with mask decoders to ground complex language expressions into masks, yet their instructions remain target-referential: they describe, constrain, or imply th…