EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909537198407680 |
|---|---|
| author | Zhang, Yi Zhang, Qiang Ju, Xiaozhu Liu, Zhaoyang Mao, Jilei Sun, Jingkai Wu, Jintao Gao, Shixiong Cai, Shihan Qin, Zhiyuan Liang, Linkai Wang, Jiaxu Duan, Yiqun Cao, Jiahang Xu, Renjing Tang, Jian |
| author_facet | Zhang, Yi Zhang, Qiang Ju, Xiaozhu Liu, Zhaoyang Mao, Jilei Sun, Jingkai Wu, Jintao Gao, Shixiong Cai, Shihan Qin, Zhiyuan Liang, Linkai Wang, Jiaxu Duan, Yiqun Cao, Jiahang Xu, Renjing Tang, Jian |
| contents | While multimodal large language models (MLLMs) have made groundbreaking progress in embodied intelligence, they still face significant challenges in spatial reasoning for complex long-horizon tasks. To address this gap, we propose EmbodiedVSR (Embodied Visual Spatial Reasoning), a novel framework that integrates dynamic scene graph-guided Chain-of-Thought (CoT) reasoning to enhance spatial understanding for embodied agents. By explicitly constructing structured knowledge representations through dynamic scene graphs, our method enables zero-shot spatial reasoning without task-specific fine-tuning. This approach not only disentangles intricate spatial relationships but also aligns reasoning steps with actionable environmental dynamics. To rigorously evaluate performance, we introduce the eSpatial-Benchmark, a comprehensive dataset including real-world embodied scenarios with fine-grained spatial annotations and adaptive task difficulty levels. Experiments demonstrate that our framework significantly outperforms existing MLLM-based methods in accuracy and reasoning coherence, particularly in long-horizon tasks requiring iterative environment interaction. The results reveal the untapped potential of MLLMs for embodied intelligence when equipped with structured, explainable reasoning mechanisms, paving the way for more reliable deployment in real-world spatial applications. The codes and datasets will be released soon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11089 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks Zhang, Yi Zhang, Qiang Ju, Xiaozhu Liu, Zhaoyang Mao, Jilei Sun, Jingkai Wu, Jintao Gao, Shixiong Cai, Shihan Qin, Zhiyuan Liang, Linkai Wang, Jiaxu Duan, Yiqun Cao, Jiahang Xu, Renjing Tang, Jian Robotics Artificial Intelligence Computer Vision and Pattern Recognition While multimodal large language models (MLLMs) have made groundbreaking progress in embodied intelligence, they still face significant challenges in spatial reasoning for complex long-horizon tasks. To address this gap, we propose EmbodiedVSR (Embodied Visual Spatial Reasoning), a novel framework that integrates dynamic scene graph-guided Chain-of-Thought (CoT) reasoning to enhance spatial understanding for embodied agents. By explicitly constructing structured knowledge representations through dynamic scene graphs, our method enables zero-shot spatial reasoning without task-specific fine-tuning. This approach not only disentangles intricate spatial relationships but also aligns reasoning steps with actionable environmental dynamics. To rigorously evaluate performance, we introduce the eSpatial-Benchmark, a comprehensive dataset including real-world embodied scenarios with fine-grained spatial annotations and adaptive task difficulty levels. Experiments demonstrate that our framework significantly outperforms existing MLLM-based methods in accuracy and reasoning coherence, particularly in long-horizon tasks requiring iterative environment interaction. The results reveal the untapped potential of MLLMs for embodied intelligence when equipped with structured, explainable reasoning mechanisms, paving the way for more reliable deployment in real-world spatial applications. The codes and datasets will be released soon. |
| title | EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.11089 |