AutoMine: A Multimodal Dataset for Robot Navigation in Open‐Pit Mines.
Saved in:
| Title: | AutoMine: A Multimodal Dataset for Robot Navigation in Open‐Pit Mines. |
|---|---|
| Authors: | Li, Yuchen1,2,3,4 (AUTHOR), Teng, Siyu1,2,3 (AUTHOR), Wang, Junhui5 (AUTHOR), Ai, Yunfeng1,6 (AUTHOR), Tian, Bin1,7 (AUTHOR), Xuanyuan, Zhe2 (AUTHOR) zhexuanyuan@uic.edu.cn, Bing, Zhenshan4 (AUTHOR), Knoll, Alois C.4 (AUTHOR), Wang, Fei‐Yue7 (AUTHOR), Chen, Long1,7,8,9 (AUTHOR) long.chen@ia.ac.cn |
| Source: | Journal of Field Robotics. Jun2025, Vol. 42 Issue 4, p1523-1536. 14p. |
| Subjects: | Autonomous vehicles, Computing platforms, Data analysis, Acquisition of data, Robotics |
| Abstract: | In the past decade, autonomous driving has witnessed significant advancements, largely attributable to the evolution of precise algorithms and efficient computing platforms. Nevertheless, the open‐pit mine, a typical scenario within closed‐field environments, has garnered limited attention in autonomous driving, primarily owing to the scarcity of data and experimental benchmarks. This work presents original data collected from five platforms, comprising one passenger vehicle, three wide‐body trucks, and one mining truck, across eight different mining sites. We provide a comprehensive elucidation of platform types, sensors, calibration methodologies, synchronization techniques, data collection approaches, and a thorough analysis of the data characteristics. In addition, we offer a detailed benchmark comparison of short and long odometry and navigation performance across multiple vehicles in open‐pit mines. With comprehensive data characteristics, experimental performance evaluations, and thorough analysis, we believe that this work establishes a robust research foundation for navigation and fusion methods in open‐pit mines, thereby constituting a significant contribution to the autonomous driving and field robotics communities. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Field Robotics is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | In the past decade, autonomous driving has witnessed significant advancements, largely attributable to the evolution of precise algorithms and efficient computing platforms. Nevertheless, the open‐pit mine, a typical scenario within closed‐field environments, has garnered limited attention in autonomous driving, primarily owing to the scarcity of data and experimental benchmarks. This work presents original data collected from five platforms, comprising one passenger vehicle, three wide‐body trucks, and one mining truck, across eight different mining sites. We provide a comprehensive elucidation of platform types, sensors, calibration methodologies, synchronization techniques, data collection approaches, and a thorough analysis of the data characteristics. In addition, we offer a detailed benchmark comparison of short and long odometry and navigation performance across multiple vehicles in open‐pit mines. With comprehensive data characteristics, experimental performance evaluations, and thorough analysis, we believe that this work establishes a robust research foundation for navigation and fusion methods in open‐pit mines, thereby constituting a significant contribution to the autonomous driving and field robotics communities. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 15564959 |
| DOI: | 10.1002/rob.22469 |
