RL-NBV: A deep reinforcement learning based next-best-view method for unknown object reconstruction
文献类型：期刊论文
| 作者 | Wang, Tao1,2 ; Xi, Weibin2; Cheng, Yong2,3; Han, Hao2; Yang, Yang2
|
| 刊名 | PATTERN RECOGNITION LETTERS
 |
| 出版日期 | 2024-08-01 |
| 卷号 | 184 |
| 关键词 | Active vision Unknown object reconstruction Deep reinforcement learning View planning Autonomous agents |
| ISSN号 | 0167-8655 |
| DOI | 10.1016/j.patrec.2024.05.014 |
| 通讯作者 | Yang, Yang(yangyang@ipp.ac.cn) |
| 英文摘要 | ABS T R A C T The Next-Best-View (NBV) algorithm is a key component in autonomous unknown object reconstruction. It iteratively determines the optimal sensor pose to capture the maximum information about the object under reconstruction. However, prevailing deep reinforcement learning (DRL) based NBV algorithms tend to transform point cloud, the raw sensor data, into different representations, thereby obscuring natural invariances of the data. In this work, we propose an innovative DRL-based method, denoted as RL-NBV, to learn NBV policy directly from the raw point cloud data. Specifically, we interpret the observation space as the current state of the reconstructed object represented by point clouds and current view selection states. Experimental results indicate that our method outperforms existing methods in terms of reconstruction performance. Moreover, our method significantly improves efficiency over ray-casting-based algorithms as time-consuming ray casting and data transformation are unnecessary. |
| WOS关键词 | ACTIVE VISION ; EXPLORATION ; SYSTEMS ; ROBOT |
| 资助项目 | Comprehensive Research Facility for Fusion Technology Program of China[2018-000052-73-01-001228] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001251468200001 |
| 出版者 | ELSEVIER |
| 资助机构 | Comprehensive Research Facility for Fusion Technology Program of China |
| 源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/136526]  |
| 专题 | 中国科学院合肥物质科学研究院 |
| 通讯作者 | Yang, Yang |
| 作者单位 | 1.Univ Sci & Technol China, Hefei, Peoples R China 2.Chinese Acad Sci, Inst Plasma Phys, Hefei Inst Phys Sci, Hefei, Peoples R China 3.Hefei Comprehens Natl Sci Ctr, Inst Energy, Hefei, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Tao,Xi, Weibin,Cheng, Yong,et al. RL-NBV: A deep reinforcement learning based next-best-view method for unknown object reconstruction[J]. PATTERN RECOGNITION LETTERS,2024,184. |
| APA | Wang, Tao,Xi, Weibin,Cheng, Yong,Han, Hao,&Yang, Yang.(2024).RL-NBV: A deep reinforcement learning based next-best-view method for unknown object reconstruction.PATTERN RECOGNITION LETTERS,184. |
| MLA | Wang, Tao,et al."RL-NBV: A deep reinforcement learning based next-best-view method for unknown object reconstruction".PATTERN RECOGNITION LETTERS 184(2024). |
入库方式： OAI收割
来源：合肥物质科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。