Terrain-Aware Autonomous Exploration of Unstructured Confined Spaces

  • Héctor Azpúrua UFMG
  • Mario F. M. Campos UFMG
  • Douglas G. Macharet UFMG


This work addresses the problem of exploring confined environments autonomously using terrestrial mobile robots. We propose a methodology for path planning in rough three-dimensional terrains and an exploration strategy that uses the map’s navigable areas, the related navigation cost, and the information expected from a frontier to select the next promising exploration sector. The safe path generation algorithm models the environment as a graph and uses a linear combination of weights applied to multiple traversability metrics of the terrain. The exploration phase uses the expected volumetric information of frontiers; this way, the exploration areas are selected according to their expected utility and visitation cost. We also propose an online planning phase using the raw point cloud to avoid obstacles. The online phase is faster to compute and uses the MI-RRT algorithm, an RRT-based planner biased towards the most informative frontier, capable of simultaneously planning and selecting a target frontier.

Palavras-chave: Exploration, Confined and Subterranean Spaces, Terrain-aware path planning


Allen, B. (2019). Unearthing the subterranean environment.

Azpúrua, H., Campos, M. F., and Macharet, D. G. (2021a). Research statement: Towards terrain-aware autonomous exploration in 3d confined spaces. In Robotics: Science and Systems 2021 (RSS). RSS. (Presented in the RSS Pioneers Workshop).

Azpúrua, H., Campos, M. F., and Macharet, D. G. (2021b). Three-dimensional terrain aware autonomous exploration for subterranean and confined spaces. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 2443-2449. IEEE.

Azpúrua, H., Rezende, A., Potje, G., da Cruz Júnior, G. P., Fernandes, R., Miranda, V., de Resende Filho, L. W., Domingues, J., Rocha, F., de Sousa, F. L. M., et al. (2021c). Towards semi-autonomous robotic inspection and mapping in confined spaces with the espeleorobô. Journal of Intelligent & Robotic Systems, 101(4):1-27.

Azpurua, H., Rocha, F., Garcia, G., Santos, A. S., Cota, E., Barros, L. G., Thiago, A. S., Pessin, G., and Freitas, G. M. (2019). Espeleorobô-a robotic device to inspect confined environments. In 2019 19th International Conference on Advanced Robotics (ICAR), pages 17-23. IEEE.

Azpúrua, H., M. Freitas, G., Clark, L., Agha-mohammadi, A.-a., Pessin, G., F. M. Campos, M., and G. Macharet, D. (2022). A survey on the autonomous exploration of confined subterranean spaces: Perspectives from real-word and industrial robotic deployments. Journal of Robotics and Autonomous Systems. (In revision).

Katz, S., Tal, A., and Basri, R. (2007). Direct visibility of point sets. In ACM SIGGRAPH 2007 papers, pages 24-es. ACM.

Liepa, P. (2003). Filling holes in meshes. In Proceedings of the 2003 Eurographics/ACM SIGGRAPH symposium on Geometry processing, pages 200-205.

Pimentel, J. M., Alvim, M. S., Campos, M. F., and Macharet, D. G. (2018). Information-driven rapidly-exploring random tree for efficient environment exploration. Journal of Intelligent & Robotic Systems, 91(2):313-331.

Santos, A. S., Azpúrua, H. I. P., Pessin, G., and Freitas, G. M. (2018). Path planning for mobile robots on rough terrain. In LARS 2018, pages 265-270. IEEE.

Schubert, E., Sander, J., Ester, M., Kriegel, H. P., and Xu, X. (2017). DBSCAN revisited, revisited: why and how you should (still) use DBSCAN. ACM Transactions on Database Systems (TODS), 42(3):1-21.

Shan, T. and Englot, B. (2018). Lego-loam: Lightweight and ground-optimized lidar odometry and mapping on variable terrain. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 4758-4765. IEEE.
Como Citar

Selecione um Formato
AZPÚRUA, Héctor; CAMPOS, Mario F. M.; MACHARET, Douglas G.. Terrain-Aware Autonomous Exploration of Unstructured Confined Spaces. In: CONCURSO DE TESES E DISSERTAÇÕES EM ROBÓTICA - CTDR (DOUTORADO) - SIMPÓSIO BRASILEIRO DE ROBÓTICA E SIMPÓSIO LATINO-AMERICANO DE ROBÓTICA (SBR/LARS), 14. , 2022, São Bernardo do Campo/SP. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 97-108. DOI: https://doi.org/10.5753/wtdr_ctdr.2022.226846.