Phd Position F/m Uav Planning for Prehistoric Caves Exploration

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 320 people 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_.

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