SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910795331272704 |
|---|---|
| author | Liu, Yuecheng Chi, Dafeng Wu, Shiguang Zhang, Zhanguang Hu, Yaochen Zhang, Lingfeng Zhang, Yingxue Wu, Shuang Cao, Tongtong Huang, Guowei Huang, Helong Tian, Guangjian Qiu, Weichao Quan, Xingyue Hao, Jianye Zhuang, Yuzheng |
| author_facet | Liu, Yuecheng Chi, Dafeng Wu, Shiguang Zhang, Zhanguang Hu, Yaochen Zhang, Lingfeng Zhang, Yingxue Wu, Shuang Cao, Tongtong Huang, Guowei Huang, Helong Tian, Guangjian Qiu, Weichao Quan, Xingyue Hao, Jianye Zhuang, Yuzheng |
| contents | Spatial reasoning is an essential problem in embodied AI research. Efforts to enhance spatial reasoning abilities through supplementary spatial data and fine-tuning have proven limited and ineffective when addressing complex embodied tasks, largely due to their dependence on language-based outputs. While some approaches have introduced a point-based action space to mitigate this issue, they fall short in managing more intricate tasks within complex environments. This deficiency arises from their failure to fully exploit the inherent thinking and reasoning capabilities that are fundamental strengths of Vision-Language Models (VLMs). To address these limitations, we propose a novel approach named SpatialCoT, specifically designed to bolster the spatial reasoning capabilities of VLMs. Our approach comprises two stages: spatial coordinate bi-directional alignment, which aligns vision-language inputs with spatial coordinates, and chain-of-thought spatial grounding, which harnesses the reasoning capabilities of language models for advanced spatial reasoning. We evaluate SpatialCoT on challenging navigation and manipulation tasks, both in simulation and real-world settings. Experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches in both tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_10074 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning Liu, Yuecheng Chi, Dafeng Wu, Shiguang Zhang, Zhanguang Hu, Yaochen Zhang, Lingfeng Zhang, Yingxue Wu, Shuang Cao, Tongtong Huang, Guowei Huang, Helong Tian, Guangjian Qiu, Weichao Quan, Xingyue Hao, Jianye Zhuang, Yuzheng Robotics Artificial Intelligence Computer Vision and Pattern Recognition Spatial reasoning is an essential problem in embodied AI research. Efforts to enhance spatial reasoning abilities through supplementary spatial data and fine-tuning have proven limited and ineffective when addressing complex embodied tasks, largely due to their dependence on language-based outputs. While some approaches have introduced a point-based action space to mitigate this issue, they fall short in managing more intricate tasks within complex environments. This deficiency arises from their failure to fully exploit the inherent thinking and reasoning capabilities that are fundamental strengths of Vision-Language Models (VLMs). To address these limitations, we propose a novel approach named SpatialCoT, specifically designed to bolster the spatial reasoning capabilities of VLMs. Our approach comprises two stages: spatial coordinate bi-directional alignment, which aligns vision-language inputs with spatial coordinates, and chain-of-thought spatial grounding, which harnesses the reasoning capabilities of language models for advanced spatial reasoning. We evaluate SpatialCoT on challenging navigation and manipulation tasks, both in simulation and real-world settings. Experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches in both tasks. |
| title | SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.10074 |