English

PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation

Computer Vision and Pattern Recognition 2025-08-11 v1 Robotics

Abstract

The fragmentation between high-level task semantics and low-level geometric features remains a persistent challenge in robotic manipulation. While vision-language models (VLMs) have shown promise in generating affordance-aware visual representations, the lack of semantic grounding in canonical spaces and reliance on manual annotations severely limit their ability to capture dynamic semantic-affordance relationships. To address these, we propose Primitive-Aware Semantic Grounding (PASG), a closed-loop framework that introduces: (1) Automatic primitive extraction through geometric feature aggregation, enabling cross-category detection of keypoints and axes; (2) VLM-driven semantic anchoring that dynamically couples geometric primitives with functional affordances and task-relevant description; (3) A spatial-semantic reasoning benchmark and a fine-tuned VLM (Qwen2.5VL-PA). We demonstrate PASG's effectiveness in practical robotic manipulation tasks across diverse scenarios, achieving performance comparable to manual annotations. PASG achieves a finer-grained semantic-affordance understanding of objects, establishing a unified paradigm for bridging geometric primitives with task semantics in robotic manipulation.

Keywords

Cite

@article{arxiv.2508.05976,
  title  = {PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation},
  author = {Zhihao Zhu and Yifan Zheng and Siyu Pan and Yaohui Jin and Yao Mu},
  journal= {arXiv preprint arXiv:2508.05976},
  year   = {2025}
}

Comments

Accepted to ICCV 2025. 8 pages main paper, 8 figures, plus supplementary material

R2 v1 2026-07-01T04:40:14.258Z