English

OpenMap: Instruction Grounding via Open-Vocabulary Visual-Language Mapping

Robotics 2025-08-05 v1

Abstract

Grounding natural language instructions to visual observations is fundamental for embodied agents operating in open-world environments. Recent advances in visual-language mapping have enabled generalizable semantic representations by leveraging vision-language models (VLMs). However, these methods often fall short in aligning free-form language commands with specific scene instances, due to limitations in both instance-level semantic consistency and instruction interpretation. We present OpenMap, a zero-shot open-vocabulary visual-language map designed for accurate instruction grounding in navigation tasks. To address semantic inconsistencies across views, we introduce a Structural-Semantic Consensus constraint that jointly considers global geometric structure and vision-language similarity to guide robust 3D instance-level aggregation. To improve instruction interpretation, we propose an LLM-assisted Instruction-to-Instance Grounding module that enables fine-grained instance selection by incorporating spatial context and expressive target descriptions. We evaluate OpenMap on ScanNet200 and Matterport3D, covering both semantic mapping and instruction-to-target retrieval tasks. Experimental results show that OpenMap outperforms state-of-the-art baselines in zero-shot settings, demonstrating the effectiveness of our method in bridging free-form language and 3D perception for embodied navigation.

Keywords

Cite

@article{arxiv.2508.01723,
  title  = {OpenMap: Instruction Grounding via Open-Vocabulary Visual-Language Mapping},
  author = {Danyang Li and Zenghui Yang and Guangpeng Qi and Songtao Pang and Guangyong Shang and Qiang Ma and Zheng Yang},
  journal= {arXiv preprint arXiv:2508.01723},
  year   = {2025}
}

Comments

ACM MM '25

R2 v1 2026-07-01T04:31:47.165Z