Supervised Learning of Natural-Terrain Traversability with Synthetic 3D Laser Scans
Source abstract
Abstract
Autonomous navigation of ground vehicles on natural environments requires looking for traversable terrain continuously. This paper develops traversability classifiers for the three-dimensional (3D) point clouds acquired by the mobile robot Andabata on non-slippery solid ground. To this end, different supervised learning techniques from the Python library Scikit-learn are employed. Training and validation are performed with synthetic 3D laser scans that were labelled point by point automatically with the robotic simulator Gazebo. Good prediction results are obtained for most of the developed classifiers, which have also been tested successfully on real 3D laser scans acquired by Andabata in motion.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robotics and Sensor-Based Localization · Robotic Path Planning Algorithms · Image Processing and 3D Reconstruction
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Dpto. de Ingeniería de Sistemas y Automática, Universidad de Málaga, 29071 Málaga, Spain
Funding
Junta de Andalucía
References (25)
Show source-provided references
1. Terrain traversability analysis methods for unmanned ground vehicles: A survey10.1016/j.engappai.2013.01.006 ↗
2. Supervised traversability learning for robot navigation
3. Zhang, K., Yang, Y., Fu, M., and Wang, M. (2019). Traversability assessment and trajectory planning of unmanned ground vehicles with suspension systems on rough terrain. Sensors, 19.10.3390/s19204372 ↗
4. Zhu, Q., Wu, J., Hu, H., Xiao, C., and Chen, W. (2018). LIDAR point cloud registration for sensing and reconstruction of unstructured terrain. Appl. Sci., 8.10.3390/app8112318 ↗
5. Learning for autonomous navigation10.1109/MRA.2010.936946 ↗
6. Continuous mapping and localization for autonomous navigation in rough terrain using a 3D laser scanner10.1016/j.robot.2016.10.017 ↗
7. Driving on point clouds: Motion planning, trajectory optimization, and terrain assessment in generic nonplanar environments10.1002/rob.21700 ↗
8. Douillard, B., Underwood, J., Kuntz, N., Vlaskine, V., Quadros, A., Morton, P., and Frenkel, A. (2011, January 9–13). On the segmentation of 3D LIDAR point clouds. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China.10.1109/ICRA.2011.5979818 ↗
9. Vu, H., Nguyen, H.T., Chu, P.M., Zhang, W., Cho, S., Park, Y.W., and Cho, K. (2017). Adaptive ground segmentation method for real-time mobile robot control. Int. J. Adv. Robot. Syst., 14.10.1177/1729881417748135 ↗
10. Natural terrain classification using three-dimensional ladar data for ground robot mobility10.1002/rob.20134 ↗
11. Object detection and terrain classification in agricultural fields using 3D Lidar data10.1007/978-3-319-20904-3_18 ↗
12. Xiong, X., Munoz, D., Bagnell, J., and Hebert, M. (2011, January 9–13). 3-D scene analysis via sequenced predictions over points and regions. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China.10.1109/ICRA.2011.5980125 ↗
13. Pomares, A., Martínez, J.L., Mandow, A., Martínez, M.A., Morán, M., and Morales, J. (2018, January 19–22). Ground extraction from 3D Lidar point clouds with the Classification Learner App. Proceedings of the 26th Mediterranean Conference on Control and Automation (MED), Zadar, Croatia.10.1109/MED.2018.8442569 ↗
14. Learning traversability from point clouds in challenging scenarios10.1109/TITS.2017.2769218 ↗
15. Sánchez, M., Martínez, J.L., Morales, J., Robles, A., and Morán, M. (2019, January 18–20). Automatic generation of labelled 3D point clouds of natural environments with Gazebo. Proceedings of the IEEE International Conference on Mechatronics (ICM), Ilmenau, Germany.10.1109/ICMECH.2019.8722866 ↗
16. Suger, B., Steder, B., and Burgard, W. (2015, January 26–30). Traversability analysis for mobile robots in outdoor environments: A semi-supervised learning approach based on 3D-Lidar data. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA.10.1109/ICRA.2015.7139749 ↗
17. Terrain classification in complex three-dimensional outdoor environments10.1002/rob.21521 ↗
18. Normal Distributions Transform Traversability Maps: LIDAR-Only Approach for Traversability Mapping in Outdoor Environments10.1002/rob.21657 ↗
19. Shan, T., Wang, J., Englot, B., and Doherty, K. (2018, January 29–31). Bayesian generalized kernel inference for terrain traversability mapping. Proceedings of the 2nd Conference on Robot Learning, Zurich, Switzerland.
20. Training a terrain traversability classifier for a planetary rover through simulation10.1177/1729881417735401 ↗
21. Learning ground traversability from simulations10.1109/LRA.2018.2801794 ↗
22. Koenig, K., and Howard, A. (October, January 28). Design and use paradigms for Gazebo, an open-source multi-robot simulator. Proceedings of the IEEE-RSJ International Conference on Intelligent Robots and Systems (IROS), Sendai, Japan.
23. Martínez, J.L., Morán, M., Morales, J., Reina, A.J., and Zafra, M. (2018). Field navigation using fuzzy elevation maps built with local 3D laser scans. Appl. Sci., 8.10.3390/app8030397 ↗
24. Scikit-learn: Machine learning in Python
25. Martínez, J.L., Morales, J., Reina, A.J., Mandow, A., Pequeño-Boter, A., and García-Cerezo, A. (2015, January 17–19). Construction and calibration of a low-cost 3D laser scanner with 360° field of view for mobile robots. Proceedings of the IEEE International Conference on Industrial Technology (ICIT), Seville, Spain.10.1109/ICIT.2015.7125091 ↗