Phd position f - m uav planning for prehistoric caves exploration & mapping h/f

A propos d'Inria

Inria est l'institut national de recherche dédié aux sciences et technologies du numérique. Il emploie 2600 personnes. Ses 215 équipes-projets agiles, en général communes avec des partenaires académiques, impliquent plus de 3900 scientifiques pour relever les défis du numérique, souvent à l'interface d'autres disciplines. L'institut fait appel à de nombreux talents dans plus d'une quarantaine de métiers différents. 900 personnels d'appui à la recherche et à l'innovation contribuent à faire émerger et grandir des projets scientifiques ou entrepreneuriaux qui impactent le monde. Inria travaille avec de nombreuses entreprises et a accompagné la création de plus de 200 start-up. L'institut s'eorce ainsi de répondre aux enjeux de la transformation numérique de la science, de la société et de l'économie. PhD Position F/M UAV Planning for Prehistoric Caves Exploration & Mapping
Le descriptif de l'offre ci-dessous est en Anglais
Type de contrat : CDD

Niveau de diplôme exigé : Bac +5 ou équivalent

Fonction : Doctorant

Niveau d'expérience souhaité : Jeune diplômé

A propos du centre ou de la direction fonctionnelle

The Inria research centre in Lyon is the 9th Inria research centre, formally created in January 2022. IT brings together approximately 320people in 19 research teams and research support services.

Its staff are distributed in Villeurbanne, Lyon Gerland, and Saint-Etienne.

The Lyon centre is active in the fields of software, distributed and high-performance computing, embedded systems, quantum computing and privacy in the digital world, but also in digital health and computational biology.

Contexte et atouts du poste

This PhD will BE funded by the ANR project ARCAVE- Aerial Robots for Prehistoric Caves Exploration & Mapping.

The PhD will ideally start in January 2026 but later starting dates can also BE considered in function of the candidate's availability.

The selected candidate will join the INRIA Chroma team () at CITI-lab INRIA/INSA Lyon, and work under the supervision of Alessandro Renzaglia and Olivier Simonin. Our goal is to design algorithms and develop models allowing mobile robots to navigate and cooperate to achieve complex tasks in challenging and dynamic environments. Within this context, an important line of research focuses on online planning for guiding both single and multiple aerial robots for active data acquisition. Our approach for addressing this challenge is to bring together probabilistic methods, planning techniques and multi-agent decision models.

Close collaboration with the other project partners, the Coperninc team at GIPSA-Lab in Grenoble and the Prehistoric Art research group led by Carole Fritz, is also expected.

Mission confiée

Context. The ARCAVE project, which brings together researchers in robotics and in archaeology, has the ambitious goal of designing an innovative robust and safe autonomous aerial robotic system to obtain high-resolution 3D reconstructions of Prehistoric caves, extremely fragile and often difficult to access environments, going beyond the state-of-the-art for control, planning, and 3D photogrammetry solutions. Within this context, this Ph.D. thesis will focus on designing new path-planning solutions to optimize the data-gathering process for the 3D reconstruction and high-resolution image acquisition while respecting all the operational and safety constraints imposed by this complex task.

Objectives. The exploration and mapping of prehistoric sites to obtain accurate 3D reconstructions of the scenes requires optimized data acquisition plans. Depending on the scope, data will BE collected using simple cameras for photogrammetry-based approaches or laser-based sensors providing 3D point clouds. This Ph.D. will focus on the path planning problem to perform this mission autonomously, where a human expert will only have the role of supervising the whole mission and providing information about the main areas of interest. This problem, strictly related to both Next-Best View and Coverage Path Planning, is a challenging problem where future observation positions are selected based on the available information and image accuracy requirements. Moreover, caves present complex structures that generate strong constraints for both navigation and localization, requiring a continuous connection with a central positioning station. To ensure complete visual coverage of the areas of interest and respect all constraints in these scenarios, an accurate definition of the viewpoint sequence will BE paramount. This will BE achieved by combining global and local information gain criteria and utilizing both coarse 3D point clouds of the environment available prior to the mission and the data gathered online. Finally, although the ARCAVE project will propose the use of a single UAV to carry out the data-gathering tasks, a preliminary study on the possible use of multiple UAVs will BE carried out to show their potential and to analyze the challenges of this solution, which would push the limits of prehistoric cave studies even further. A first validation phase will BE conducted in realistic simulations based on an already existing framework developed by the CHROMA team in Gazebo. Afterwards, the experimental validation in real conditions, conducted in close collaboration with the Copernic team at GIPSA-Lab in Grenoble and with the Prehistoric Art research group led by Carole Fritz, will also play an important role in this thesis.

References
[1] P. Petracek, V. Kratky, T. Baca, M. Petrlik, and M. Saska. New era in cultural heritage preservation : Cooperative aerial autonomy for fast digitalization of difficult-to-access interiors of historical monuments. In : IEEE Robotics & Automation Magazine (2023).
[2] J. Lim, N. Lawrance, F. Achermann, T. Stastny, R. Bähnemann, and R. Siegwart. Fisher information based active planning for aerial photogrammetry. In : IEEE Intern. Conf. on Robotics and Automation, 2023.
[3] A. Renzaglia, J. Dibangoye, V. Le Doze, and O. Simonin. A common optimization framework for multi-robot exploration and coverage in 3D environments. In : Journ. of Intelligent & Robotic Systems, 2020.
[4] Z. Shen, J. Song, K. Mittal, and S. Gupta. CT-CPP : Coverage path planning for 3D terrain reconstruction using dynamic coverage trees. In : IEEE Robotics and Automation Letters, 2021.
[5] M. Zhang, et al. SOAR : Simultaneous exploration and photographing with heterogeneous UAVs for fast autonomous reconstruction. In IEEE Intern. Conf. on Intelligent Robots and Systems, 2024.

Principales activités

The main tasks to BE carried out during the Ph.D. will BE :
- Study and become familiar with existing coverage and next-best-view planning solutions for autonomous data acquisition.
- Design and analyze novel planning strategies to guide UAVs in achieving high-quality 3D reconstruction and photogrammetry, leveraging both prior knowledge and online-acquired data.
- Implement and test the proposed solutions in simulation (Gazebo) as well as on a real platform, in close collaboration with team members and project partners.
- Extend the developed planning solutions to multi-UAV systems and evaluate their performance in simulation.
- Maintain continuous interaction with project partners to fully understand the objectives, constraints, and challenges of the project, ensuring smooth integration of the developed solutions and effective project progress.

Compétences

Experience required
- The candidate must have a Master (or equivalent) in computer science, robotics or closely related fields.
- Knowledge in robotics is required. Experiences with planning algorithms, 3D perception, and aerial vehicles will BE appreciated.
- Proficiency in C++ and Python programming is required. Experiences with ROS and Gazebo are highly valued.

Avantages
- Subsidized meals
- Partial reimbursement of public transport costs
- Leave : 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
- Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage

Rémunération

1st and 2nd year : 2100 Euros gross salary /month

3rd year : 2200 Euros gross salary / month