Back CNES

037-Multi-sensor based navigation for caves and lava tube exploration

037-Multi-sensor based navigation for caves and lava tube exploration

  • Contract :Ph.D.
  • Duration :36 months
  • Working time :Full-time
  • Experience :Entry Level
  • Education level :Master’s Degree, MA/MS/MSc

Your mission at CNES :

One of the biggest challenges when it comes to create settlements on other planets is building a safe space to live. Whether it’s on Mars or on the Moon, space settlers will have to live, work and sleep in an environment of extreme temperatures, without oxygen, while being bombarded with radiation and micrometeorites. Caverns on the Moon and Mars can offer enough space, protection against cosmic radiation and stable temperatures for astronaut bases [4]. A first step for such settlements is the ability to explore and map such environment thanks to autonomous robots. While exploring the cavity it will be necessary, both for navigation and scientific purposes, to keep track of the surrounding environment through high-precision mapping. The lack of georeferencing systems represents a challenge that can be overcome with real-time mapping through technologies such as laser scanners, photogrammetry and inertial systems that can be combined in a SLAM (Simultaneous Localisation and Mapping) approach.
Note that on Earth also, complex underground settings present significant challenges for military and civilian first responders. The hazards vary drastically across domains that can degrade or change over time and are often too high-risk for personnel to enter. In such disaster response scenarios, localisation and mapping approaches are mandatory.
Proposal
In the context of robot autonomous navigation, SLAM techniques are widely used. They allow the exploration of unknown environments and their mapping in both a geometric, a semantic or a topological way. Such approaches mainly used visual modalities (RGB camera, IR camera) or LiDAR modalities (RGB-D camera or 2D/3D LiDAR). Based on such mapping, not only the size and morphology of the explored area can be obtained but also the semantic interpretation of the perceptions and the detection or identification of objects of interest. Even if such approaches already exists, none of the proposed solution is based on a complete hybridisation between vision and LiDAR technologies. Such fusion would improve the performances of the navigation system by compensating weakness of both visual and LiDAR sensors. At ISAE-SUPAERO we realised a complete bibliography study of such bi-modal approach. We shown that such hybridisation is a mandatory step for improving the navigation system in harsh environment. Considering Lava tube exploration some methods have been proposed but using only visual modality. This project proposes to explore a Visual/LiDAR fully hybridised SLAM solution in the context of underground cave exploration and mapping which meet application for both space exploration but also for earth underground applications.
The proposed PhD will focus on the development of such hybridized solution, mandatory for complex navigation tasks, while keeping in mind the implementation on low-power on-board computer.
Attached document
Cited rerefences and more informations about the proposal team background are in the attached document.

The CV of the candidate is also provided at the end of the document.

For more information, contact  eric.chaumette@isae.fr from TéSA

Candidate profile searched:

The CV of the candidate is attached at the end of the proposal.
It is a student from ISAE-SUPAERO following a specific research program (half time in classes, half time working on SLAM research project in the Navigation team of DEOS lab).


We suggest you to contact first the PhD supervisor about the topics and the co-financial partner (found by the lab !). Then, prepare a resumé, a recent transcript and a reference letter from you M2 supervisor/ engineering school director and you will be ready to apply online !

CNES will inform about the status of your application in mid-June.

More details on CNES website : https://cnes.fr/en/web/CNES-en/10685-st-doctoral-grants.php

,
  • Our address

    7 Boulevard de la Gare, 31500 Toulouse, France
    Would you like to calculate the access time? Click here