MAIN TOPICS

• Object detection and recognition in different sensor domains (stereo vision, lasers, acoustic sensors i.e. sonars, multibeam).
• Image enhancement and distortion removal (dehazing, color correction).
• Sensor fusion and signal processing.
• Environment modeling (bathymetry, 3D representation and mapping, SLAM).
• Simulated environments and continuous system integration (hardware-in-the-loop, synthetic data generation, simulation to real-world transition).
• Deep learning practices and machine learning pipelines in any of the above topics.
• Heavily tested systems in field trials and best practices for deployment and data management.

SUMMARY

Reliable sensory perception of dynamic environments is a requirement to achieve long-term autonomy in robotics. However, in underwater scenarios perception tasks have proved to be particularly challenging. Common sensor feedback in Remote Operated Vehicles (ROVs) and Autonomous Underwater Vehicles (AUVs) are optical cameras and sonars; but camera images suffer from limited range and rapid degradation depending on light behavior and water turbidity, and sonars often lack the resolution needed. As maritime industrial, biological and archaeological activities continue to rapidly increase, efforts are made to boost software and hardware technologies to cope with the harsh underwater environmental conditions.

These technologies cover a wide range of topics such as underwater image enhancement and correction, stereo vision, acoustic/laser mapping, sensor fusion, environment simulation, among many others. For this reason, this workshop in Underwater Robotics Perception aims to create a space where researchers can share their experiences, lessons learned and best practices in the process of transferring their work to field trials. The workshop includes a poster session to give exposition to young researchers, a panel discussion to ensure interaction between the audience and the speakers, and talks from industry partners to discuss methods and pipelines to transfer research into real world solutions.

MOTIVATION

Recently, there has been rapid progress in the development of Unmanned Underwater (UUVs) and Remote Operating Vehicles (ROVs); and marine robotics is expected to have a tremendous impact in the coming years not only in ocean exploration but also exploitation. The capability to perceive the working unstructured and dynamic environment is an essential step towards the development of effective and reliable robotic systems, able to work autonomously and react to external events. Numerous challenges arise while pursuing such objectives in underwater scenarios; contrary to its industrial counterpart, the environment cannot be controlled or tailored to suit an automation task i.e., lighting, object poses, etc.

For these reasons, this workshop aims to provide a broad and extremely interesting overview of the best practices to enable robust perception in underwater robots. Keynote talks from researchers and industry partners, with ample hands-on and field experience, will generate new ideas, collaborations and research interests. The main topics to be addressed in the workshop are mentioned above, but these do not prevent discussions and talks from covering other related subjects.