ROBOCOMPLEX
Robotics and Communications
in Complex Environments
PID2022-139615OB-I00/MCIN/AEI/10.13039/501100011033/FEDER-UE
Embedded Files
Referencia:
PID2022-139615OB-I00
IP:
Luis Montano (montano@unizar.es)
Danilo Tardioli (dantard@unizar.es)
Duración:
01/09/2023 - 31/08/2026
Equipo de Investigación:
José Luis Villarroel salcedo
Francisco Lera García
Natalia Ayuso Escuer
Alejandro Mosteo Chagoyen
Luis Riazuelo Latas
Equipo de Trabajo:
Diego Martínez Baselga
Lorenzo Cano Andrés
María Teresa Lázaro
Julio Placed
Lorenzo Montano-Olivan
Yaroslav Marchukov
Jorge Bes Carreras
Juan Dendarieta
The objective is to generate knowledge in the context of developing fully autonomous robotics systems, involving UGV, UAV and USV, for use in large and complex environments, especially those in which out-of-the-box solutions do not work such as confined underground settings (caves, mines, etc.) or large crowded spaces like airports, events locations, etc. The scientific proposal in the ROBOCOMPLEX project has these general objectives:
Extending the communication range and preserving the bandwidth in unstructured underground environments.
Planning and navigation in highly dynamic environments.
Alternative navigation for underground environments.
Publications: [C5].
1. Communications: The objectives of this task are twofold: on the one hand we intend to study the use of FSO and RF directive antennas to improve the communication range in unstructured environments and, on the other hand, we aim to develop network communication protocols to improve the bandwidth in robotics networks. The specific objectives are:
Free Space Optical communications technology for underground.
Directive antennas for RF underground communication.
Communication protocols for spatial reuse.
2. Planning and navigation in highly dynamic environments: Developing planning and reactive techniques for 2D and 3D dynamic and crowded scenarios, with multiple agents (people and vehicles) moving around. New techniques integrating environment models and Deep Reinforcement Learning will be developed. The specific objectives are:
Cooperative Reinforcement learning for collaborative and adversarial behaviors.
Multi-robot cooperative collision avoidance.
Uncertainty-based deep reinforcement learning robot navigation.
Integrating 3D-DOVS rule-based and DRL planners for dynamic environments.
Publications: [C1],[C2],[C6],[J1],[J3],[J5],[J6],[J7],[J8].
3. Topological-semantic mapping, localization and navigation: Underground environments present a set of unique challenges that make it difficult for traditional navigation technologies to operate in. Some of these challenges are the lack of visibility, the rough and slippery terrain, the presence of tunnels with few geometrical features (that are a challenge for scan-matching-based localization techniques) and the impossibility of using GNSS-based global localization techniques. For this reason, we propose the development of novel and more tailored navigation approaches for these environments. The specific objectives are:
Topological navigation in underground scenarios.
Topological mapping in underground environments.
Mapping from heterogeneous robot teams and sensors.
High-speed traversal of tunnels with drones.
Multi-robot coordination.
Publications: [C3],[C4],[C5],[J2],[J4],[J9].
4. Demonstrators: One of the objectives of this project is to develop the following demonstrators.
Navigation through the Somport Tunnel .
RoboBoat: A robotic boat for 3D mapping of partially flooded underground sites.
Planning and navigation in dynamic environments (University hall).
Tunnels, open-pit mines, roads under construction (G-Loc, LG-SLAM).
Autonomous bathymetry and geopointing to enhance communications (Pantano de las Navas).
Autonomous inspection of water channels with USV (Canal-túnel de Estada).
Publications: [C3],[C4],[C5],[J2],[J3],[J4],[J7],[J8],[J9].
Publications
Journals
[J1] D Martinez-Baselga, L Riazuelo, L Montano. Long-Range Navigation in Complex and Dynamic Environments with Full-Stack S-DOVS. Applied Sciences 13 (15), 8925, DPI: 10.3390/app13158925, 2023.
[J2] JL Villarroel, F Lera, D Tardioli, L Riazuelo, L Montano. RoboBoat: A robotic boat for 3D mapping of partially flooded underground sites. Journal of Field Robotics, 1-25, DOI: 10.1002/rob.22303, 2024.
[J3] Y Marchukov, L Montano. Occupation-aware planning method for robotic monitoring missions in dynamic environments. Robotics and Autonomous Systems, DOI:10.1016/j.robot.2024.104892, 2024.
[J4] L Montano-Oliván, JA Placed, L Montano, MT Lázaro. G-loc: Tightly-coupled graph localization with prior topo-metric information. IEEE Robotics and Automation Letters (RA-L), DOI: 10.1109/LRA.2024.3457383, 2024.
[J5] D Martinez-Baselga, E Sebastián, E Montijano, L Riazuelo, C Sagüés, L. Montano. AVOCADO: Adaptive optimal collision avoidance driven by opinion. IEEE Transactions on Robotics, DOI: 10.1109/TRO.2025.3552350, 2025.
[J6] D. Martínez-Baselga, L. Knoedler, O. Degroot, J. Alonso-Mora, L. Riazuelo, L. Montano. SHINE: Social Homology Identification for Navigation in Crowded Environments. The International Journal of Robotics Research (IJRR). 2025. Aceptado.
[J7] D. Martinez-Baselga, L. Riazuelo, L. Montano. RUMOR: Reinforcement learning for Understanding a Model of the Real World for Navigation in Dynamic Environments.. Robotics and Autonomous Systems (RAS). 2025. DOI: 10.1016/j.robot.2025.105020.
[J8] Y Marchukov, L Montano. Traversability-aware path planning in dynamic environments. IEEE Robotics and Automation Letters (RA-L). 2025. En revisión.
[J9] J. Bes, J. Dendarieta, L. Riazuelo, Luis Montano. DWA-3D: A Reactive Planner for Robust and Efficient Autonomous UAV Navigation in Confined Environments. Robotics and Autonomous Systems (RAS). 2025. En revisión.
Conferences
[C1] D Martinez-Baselga, L Riazuelo, L Montano. Improving robot navigation in crowded environments using intrinsic rewards. 2023 IEEE International Conference on Robotics and Automation (ICRA), London, DOI: 10.1109/ICRA48891.2023.10160876, 2023.
[C2] D Martinez-Baselga, L Riazuelo, L Montano. D-TOP: Deep Reinforcement Learning with Tuneable Optimization for Autonomous Navigation. IEEE, 7th Iberian Robotics Conference (ROBOT), 1-6, DOI: 10.1109/ROBOT61475.2024.10796966, 2024.
[C3] L. Cano, D. Tardioli, A. Mosteo. Purely Topological Exploration of Underground Environments. ROBOT2024, DOI: 10.1109/ROBOT61475.2024.10797436, 2024.
[C4] L. Cano, D. Tardioli, A. Mosteo. Procedural Generation of Underground Tunnel Networks for Robotics Simulation. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2024), DOI: 10.1109/IROS58592.2024.10801552, 2024.
[C5] L Montano-Oliván, JA Placed, L Montano, MT Lázaro. From underground mines to offices: A versatile and robust framework for range-inertial SLAM. IEEE, 7th Iberian Robotics Conference (ROBOT), 1-8, DOI: 10.1109/ROBOT61475.2024.10796903, 2024.
[C6] D. Martinez-Baselga, O. de Groot, L. Knoedler, J. Alonso-Mora, L. Riazuelo, L. Montano. Hey robot! personalizing robot navigation through model predictive control with a large language model. ICRA 2025. (Mayo 2025).
[C7] L. Montano. Robotics and communications in complex environments (ROBOCOMPLEX). IEEE, 7th Iberian Robotics Conference (ROBOT2024), 2024.
Page updated
Google Sites
Report abuse