[robotics-worldwide] [jobs] Fully funded PhD position in Marine Robotics and SLAM for AUVs operating under the Arctic/Antarctic sea-ice

Salavasidis, Georgios georgios.salavasidis at noc.ac.uk
Thu Dec 12 03:42:09 PST 2019

Dear Colleagues,

The National Oceanography Centre (NOC) and the University of Southampton (UoS) in the UK invite applications for a PhD position in Marine Robotics (https://urldefense.proofpoint.com/v2/url?u=http-3A__noc.ac.uk_gsnocs_project_development-2Drobust-2Dsimultaneous-2Dlocalisation-2Dand-2Dmapping-2Dtechniques-2Dautonomous&d=DwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=iW45nDTL4GoAUj6Xn0WXnjq4woB09-DJRgIlzZ9Lwyo&s=ZvEfLqX-v2z1yGaALit_Fk9FibJ5H37MfroLqomDjBw&e= ) under the Training/PhD Programme INSPIRE funded by the Natural and Environmental Research Council.

The programme is a 3.5 year fully-funded (fees and stipend) PhD studentship offered to an excellent **EU/UK student** that will be registered at the UoS, and hosted at the NOC. The successful candidate will undertake research focusing on AUV navigation in remote and challenging environments and will develop new Simultaneous Localisation and Mapping (SLAM) techniques for high-powered AUVs operating under the polar (Arctic/Antarctic) sea-ice. The student will be provided opportunities to contribute and engage with research and vehicle deployments originating from the Marine Autonomous and Robotic Systems (MARS) group at the NOC which hosts Europe’s largest fleet of Marine Autonomous Systems.

Rationale/Methodology: Despite the considerable effort directed towards AUV navigation, a self-contained solution still remains a key challenge. Due to the cumulative error that inertial navigation experiences with time, AUVs typically require external navigation support or regular surfacing to obtain GPS fixes and limit the error, which options can be undesirable/unavailable in certain applications (e.g. deep-water and/or under-ice deployments). In response to the presently limited navigation capability, this project will focus on the development of robust SLAM algorithms for high-powered AUVs enabling operations in GPS-denied environments. While SLAM has been proven to be effective for land and aerial robots operating in structured environments, the application of these techniques in the highly unstructured underwater domain is immature with outstanding challenges to be addressed. Examples include: scalability to larger areas, where computationally and memory-efficient map representations are required; feature extraction and data association, which become further complicated tasks whilst operating underwater in unstructured environments where unique features can rarely be detected with the on-board sensors.

The NOC is currently developing the Autosub2KUI, a high-powered AUV specifically designed for operations under the sea-ice. The basic sensor suite includes both ranging/imaging sonars and cameras enabling multiple navigation options. This research will focus on developing algorithms for online sonar-based SLAM whilst mapping not only the seafloor but also the underside of the ice. The candidate will develop robust and computationally feasible in real-time navigation and 3D mapping algorithms which scale the applicability of SLAM to large environments. For the problems of the feature detection, classification, and data association, new solutions will be investigated including machine learning techniques (e.g. deep learning). Upon the successful demonstration of the effectiveness of the algorithms in computer simulations, the candidate will have the opportunity to test the algorithm in real-time via field experiments.

Training: The INSPIRE Doctoral Training Partnerships (DTP) programme provides comprehensive personal and professional development training alongside extensive opportunities for students to expand their multi-disciplinary outlook through interactions with a wide network of academic, research and industrial/policy partners. The project will offer training and the candidate will acquire skills/experience in the following areas:

  *   Marine robotics and AUVs
  *   Underwater perception and navigation
  *   Bayesian estimation, machine learning, and optimisation techniques
  *   Development of high-performance software algorithms for robots
  *   Collaborations with experts in marine technology and ocean sciences, as well as working in research groups
  *   Participation in field experiments and research cruises (depending on availability/schedule).

Requirements: The ideal candidate will have a strong academic background and strong mathematical skills, particularly in relation to reasoning about probabilities. In more detail:

  *   MSc degree in computer science/engineering/applied mathematics, or a relevant discipline
  *   Programming skills (e.g. python/C++/Matlab)

  *   Strong analytical skills and ability to work at the intersection of several research domains
  *   Fluent use of English (both written and spoken) and excellent communication and teamwork skills
  *   Experience in the following areas will be considered favourably: robotics, control, estimation/filtering, machine learning, artificial intelligence

About MARS group: The Marine Autonomous and Robotic Systems group (https://urldefense.proofpoint.com/v2/url?u=http-3A__www.noc.ac.uk_technology_technology-2Ddevelopment_marine-2Dautonomous-2Drobotic-2Dsystems&d=DwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=iW45nDTL4GoAUj6Xn0WXnjq4woB09-DJRgIlzZ9Lwyo&s=nANZhVfGg9qgfmqazZx-gOsOTbQhNIlboA-kEz6nptw&e= ) operates and maintains the UK’s marine science robotic fleet. The fleet is housed in a new state of the art facility which is ranked as one of the best in Europe. The fleet consists of large propeller-driven AUVs, subsea gliders, unmanned surface vehicles, and ROVs. This fleet, amongst the largest of its kind, is used by the UK science community and wider stakeholders to address global marine science questions. It operates worldwide from the coast to the deep oceans, and the vehicles have been deployed beneath glacial ice tongues in Antarctica, under sea ice in the Arctic, and have operated in every ocean in between.

INSPIRE PhD programme/Application Process and Deadlines: Further information about the INSPIRE programme can be found in: https://urldefense.proofpoint.com/v2/url?u=http-3A__inspire-2Ddtp.ac.uk&d=DwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=iW45nDTL4GoAUj6Xn0WXnjq4woB09-DJRgIlzZ9Lwyo&s=Wf5LTkBQ2-Arp3wY-UkUuyiufDGNh18w9G13Bc7ZEUY&e= <https://urldefense.proofpoint.com/v2/url?u=http-3A__inspire-2Ddtp.ac.uk_&d=DwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=iW45nDTL4GoAUj6Xn0WXnjq4woB09-DJRgIlzZ9Lwyo&s=O6wZOcmGvso-s3wUk6WEtd_xZ9pGsoTl_I4QWoRmz9E&e= > (including the description how to apply). Note, the application deadline is 03 January 2020 (https://urldefense.proofpoint.com/v2/url?u=http-3A__noc.ac.uk_gsnocs_project_development-2Drobust-2Dsimultaneous-2Dlocalisation-2Dand-2Dmapping-2Dtechniques-2Dautonomous&d=DwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=iW45nDTL4GoAUj6Xn0WXnjq4woB09-DJRgIlzZ9Lwyo&s=ZvEfLqX-v2z1yGaALit_Fk9FibJ5H37MfroLqomDjBw&e= ).

Please reach out to geosal at noc.ac.uk<mailto:geosal at noc.ac.uk> if you have questions.

Kind Regards,
Georgios Salavasidis

Dr Georgios Salavasidis
Marine Robotics Research Engineer
Marine Autonomous and Robotic Systems
National Oceanography Centre
European Way
SO14 3ZH
Email: geosal at noc.ac.uk<mailto:geosal at noc.ac.uk>

This email and any attachments are intended solely for the use of the named recipients. If you are not the intended recipient you must not use, disclose, copy or distribute this email or any of its attachments and should notify the sender immediately and delete this email from your system.
The National Oceanography Centre (NOC) has taken every reasonable precaution to minimise risk of this email or any attachments containing viruses or malware but the recipient should carry out its own virus and malware checks before opening the attachments. NOC does not accept any liability for any losses or damages which the recipient may sustain due to presence of any viruses.
Opinions, conclusions or other information in this message and attachments that are not related directly to NOC business are solely those of the author and do not represent the views of NOC.

More information about the robotics-worldwide mailing list