Research interests

• Autonomous robotic platforms allow detailed observations to be made over large areas in the ocean. For these systems to be useful, it is necessary to develop advanced sensing capabilities and methods to allow the robots to safely navigate and accurately localize themselves in complex, GPS denied environments. Once observations have been made, it’s necessary to interpret the large volumes of data that are gathered in an efficient and scalable way. For more information on research activities, please visit the Ocean Perception research website.
• Seafloor 3D visual reconstruction: Development of deep-sea imaging hardware and processing pipelines for calibration, localisation and 3D mapping of the seafloor with full-field uncertainty characterisation.
• BioCam (NERC NE/P020887/1): Development of a deep-sea, high-altitude seafloor imaging system for monitoring seafloor ecological variables as part of the Oceanids Marine Sensor Capital program. This project is a collaboration with Sonardyne International Ltd, the National Oceanography Centre and the ACFR University of SydneyAT-SEA (NERC NE/T010592/1): 3D visual survey of decommissioned seafloor infrastructure using a shore launched Autonomous Underwater Vehicle (Boaty McBoaface) as part of the INSITE program. This project is a collaboration with the National Oceanography Centre. Automated interpretation of data: Development of AI methods for rapid scalable interpretation of seafloor imagery.
• TechOceanS (EU H2020 101000858): Development of content aware compression, prioritization and transmission of marine imagery for near-realtime remote awareness of seafloor observations over the low communication bandwidths. This project is a consortium project led by the National Oceanography Centre. Robotics: Development of low-cost, long endurance seafloor imaging floats and highly intelligent and manoeuvrable robotic imaging platform for visual survey of complex environments.
• DriftCam (EPSRC FellowshipEP/S001182/1): Development of low-cost passive drifting seafloor imaging floats for multi-week endurance seafloor surveys. Challenges are around structuring surveys where you can only go with the flow, localization will low cost sensors, and ensuring failsafe surfacing. This project is in collaboration with Sonardyne International Limited. Smarty200 (EPSRC EP/V035975/1): Core equipment grant for an INS equipped compact AUV for visual surveys of highly complex underwater environments and rapid acoustic and surface satellite communication. This project is in collaboration with Sonardyne International, Voyis and Iqua robotics.

Current research

Autonomous robotic platforms allow detailed observations to be made over large areas in the ocean. For these systems to be useful, it is necessary to develop advanced sensing capabilities and methods to allow the robots to safely navigate and accurately localize themselves in complex, GPS denied environments. Once observations have been made, it’s necessary to interpret the large volumes of data that are gathered in an efficient and scalable way. For more information on research activities, please visit the Ocean Perception research website.

Seafloor 3D visual reconstruction: Development of deep-sea imaging hardware and processing pipelines for calibration, localisation and 3D mapping of the seafloor with full-field uncertainty characterisation.

• BioCam (NERC NE/P020887/1): Development of a deep-sea, high-altitude seafloor imaging system for monitoring seafloor ecological variables as part of the Oceanids Marine Sensor Capital program. This project is a collaboration with Sonardyne International Ltd, the National Oceanography Centre and the ACFR University of Sydney
• AT-SEA (NERC NE/T010592/1): 3D visual survey of decommissioned seafloor infrastructure using a shore launched Autonomous Underwater Vehicle (Boaty McBoaface) as part of the INSITE program. This project is a collaboration with the National Oceanography Centre.

Automated interpretation of data: Development of AI methods for rapid scalable interpretation of seafloor imagery.

• TechOceanS (EU H2020 101000858): Development of content aware compression, prioritization and transmission of marine imagery for near-realtime remote awareness of seafloor observations over the low communication bandwidths. This project is a consortium project led by the National Oceanography Centre.

Robotics: Development of low-cost, long endurance seafloor imaging floats and highly intelligent and manoeuvrable robotic imaging platform for visual survey of complex environments.

• DriftCam (EPSRC FellowshipEP/S001182/1): Development of low-cost passive drifting seafloor imaging floats for multi-week endurance seafloor surveys. Challenges are around structuring surveys where you can only go with the flow, localization will low cost sensors, and ensuring failsafe surfacing. This project is in collaboration with Sonardyne International Limited.

Smarty200 (EPSRC EP/V035975/1): Core equipment grant for an INS equipped compact AUV for visual surveys of highly complex underwater environments and rapid acoustic and surface satellite communication. This project is in collaboration with Sonardyne International, Voyis and Iqua robotics.

In situ laser spectroscopy: Development of laser spectroscopic methods (LIBS, Raman) and scintillation methods for in situ chemical analysis of marine sediments and particles.

• RamaCam (NERC NE/R01227X/1) Combined holographic microscopy and Raman spectroscopy for visual and chemical classification of marine  particules. Part of a joint UK-Japan government SCICORP Marine sensor proof of concept program. This project is a collaboration with University of Aberdeen, IIS University of Tokyo and JAMSTEC in Japan.

^{I teach robotic engineering, in particular development and testing of robust algorithms for intelligent robotics. We code in python, and all my modules have a strong practical element, where students work on implementing methods they learning in class on physical robotic platforms. Challenging but also rewarding!}

^{SESS6072: Maritime Robotics - module page and course notes (vpn required to access)}

^{FEEG6043: Intelligent Mobile Robotics - module page and course notes (vpn required to access)}

Blair Thornton is a Professor of Marine Autonomy within Engineering and Physical Sciences at the University of Southampton. He previously held an EPSRC innovation fellowship for Robotics and Artificial Intelligence systems for ocean research, and is currently Co-Director of the FEPS In situ and Remote Intelligent Sensing Centre of Excellence (IRIS).

His research develops autonomous marine robotic, sensing and intelligence capabilities that support marine science. He is dedicated to fielding systems in real environments and overcoming bottlenecks in the flow of information from data collection through to generating human insight.

After graduating from ship-science in 2002, Blair went on to complete his PhD in underwater robotics at Southampton in 2006. During his PhD, he spent 2 years at the URA laboratory, Institute of Industrial Science (IIS) at the University of Tokyo, Japan, and continued his research as a government funded postdoctoral fellow and then as staff, until he rejoined the University of Southampton in 2016. During this time, he has participated in more than 55 ocean research expeditions (30 of which as principal investigator) and spent over 500 days at sea. He is an associate editor for the IEEE/Journal of Oceanic Engineering, IEEE/Robotics and Automation Letters, and a Guest Editor on the Field Robotics Journal Marine Robotics Special Issue. He was awarded the Okamura Kenji prize for outstanding contribution to marine technology in 2014 for his contribution to seafloor debris and radiation monitoring following the 2011 earthquake, tsunami and Fukushima nuclear disaster in the Tohoku region of Japan. In 2019, he was awarded 2^nd place in the Shell Ocean Discovery Xprize as a founding member of Team KUROSHIO.

Prizes