Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.19766 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914193487167488 |
|---|---|
| author | Ding, Hongyu Liang, Xinyue Fang, Yudong Wu, You Shi, Jieqi Huo, Jing Li, Wenbin Wu, Jing Lai, Yu-Kun Gao, Yang |
| author_facet | Ding, Hongyu Liang, Xinyue Fang, Yudong Wu, You Shi, Jieqi Huo, Jing Li, Wenbin Wu, Jing Lai, Yu-Kun Gao, Yang |
| contents | In this paper, we propose SEA, a novel approach for active robot exploration through semantic map prediction and a reinforcement learning-based hierarchical exploration policy. Unlike existing learning-based methods that rely on one-step waypoint prediction, our approach enhances the agent's long-term environmental understanding to facilitate more efficient exploration. We propose an iterative prediction-exploration framework that explicitly predicts the missing areas of the map based on current observations. The difference between the actual accumulated map and the predicted global map is then used to guide exploration. Additionally, we design a novel reward mechanism that leverages reinforcement learning to update the long-term exploration strategies, enabling us to construct an accurate semantic map within limited steps. Experimental results demonstrate that our method significantly outperforms state-of-the-art exploration strategies, achieving superior coverage ares of the global map within the same time constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19766 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SEA: Semantic Map Prediction for Active Exploration of Uncertain Areas Ding, Hongyu Liang, Xinyue Fang, Yudong Wu, You Shi, Jieqi Huo, Jing Li, Wenbin Wu, Jing Lai, Yu-Kun Gao, Yang Robotics In this paper, we propose SEA, a novel approach for active robot exploration through semantic map prediction and a reinforcement learning-based hierarchical exploration policy. Unlike existing learning-based methods that rely on one-step waypoint prediction, our approach enhances the agent's long-term environmental understanding to facilitate more efficient exploration. We propose an iterative prediction-exploration framework that explicitly predicts the missing areas of the map based on current observations. The difference between the actual accumulated map and the predicted global map is then used to guide exploration. Additionally, we design a novel reward mechanism that leverages reinforcement learning to update the long-term exploration strategies, enabling us to construct an accurate semantic map within limited steps. Experimental results demonstrate that our method significantly outperforms state-of-the-art exploration strategies, achieving superior coverage ares of the global map within the same time constraints. |
| title | SEA: Semantic Map Prediction for Active Exploration of Uncertain Areas |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.19766 |