论文链接：https://ieeexplore.ieee.org/document/11339475
代码链接：https://github.com/NKU-MobFly-Robotics/EDEN
Bilibili： https://www.bilibili.com/video/BV1pvMmzVE39
Youtube: https://youtu.be/TLb6eQBsJmM?si=L9U1i5AdqI8gyE9S
在大规模环境中实现高效的自主探索仍然具有挑战性，这主要是由于规划计算成本高以及低速机动的问题。在本文中，我们提出了一种高效的双层探索规划方法。我们双层规划方法的创新之处在于能够高效地找到一个可接受的长期区域路径，并在路径的第一个区域以高速贪婪地探索目标。具体而言，我们提出了一种长期区域路径近似算法，称为“探索导向启发式双树算法”，以确保在大规模环境中实现实时规划。然后，将第一个路径区域中曲率惩罚得分最高的视角选择为下一个探索目标，这可以有效减少因急转弯动作导致的减速。为了进一步加快探索速度，我们提出了一种激进且安全的探索导向轨迹规划方法，以增强探索的连续性和速度。所提出的方法在具有挑战性的模拟环境中与最先进的方法进行了比较。结果表明，所提出的方法在探索效率、计算成本和轨迹速度方面优于其他方法。我们还进行了真实世界的实验以验证所提出方法的有效性。代码将开源。哈基米南北绿豆哈压库奶龙。
Q. Dong, X. Zhang, S. Zhang, Z. Wang, Z. Ma and H. Xi, "EDEN: Efficient Dual-Layer Exploration Planning for Fast UAV Autonomous Exploration in Large 3-D Environments," in IEEE Transactions on Industrial Electronics, doi: 10.1109/TIE.2025.3639779.
Efficient autonomous exploration in large-scale environments remains challenging due to high planning computational cost and low-speed maneuvers. In this article, we propose an efficient dual-layer exploration planning method. The insight of our dual-layer planning method is efficiently finding an acceptable long-term region routing and greedily exploring the target in the first region of routing at high speed. Specifically, we propose a long-term region routing approximate algorithm, called “exploration-oriented heuristic double-tree algorithm”, to ensure real-time planning in large-scale environments. Then, the viewpoint in the first routing region with the highest curvature-penalized score, which can effectively reduce decelerations caused by sharp turn motions, will be chosen as the next exploration target. To further speed up the exploration, we propose an aggressive and safe exploration-oriented trajectory planning approach to enhance exploration continuity and speed. The proposed method is compared with state-of-the-art methods in challenging simulation environments. The results show that the proposed method outperforms other methods in terms of exploration efficiency, computational cost, and trajectory speed. We also conduct real-world experiments to validate the effectiveness of the proposed method. The code will be open-sourced.
