Underwater sensing with edge-computing systems

Recent technological advances in automation, robotics and AI are setting the stage for a new generation of autonomous underwater systems with increased level of autonomy [1]. Endowing these systems with enhanced intelligent sensing capabilities is expected to have a tremendous impact on a variety of underwater applications, including situational awareness, security (e.g., detection and tracking of submarine divers, and ship hull inspections), ground monitoring and exploration (e.g.., marine environment and resource exploration, pipes tracking and inspection, bathymetry), rescue operations, and communication [2]. However, compared to ground-based sensor research, remote underwater environments present additional unique challenges due to factors such as low-lighting conditions, constrained power resources and limited connectivity [3]. Emerging edge-computing sensing and processing technologies provide a promising solution for these critical scenarios by processing data directly at the edge, in real time, and with low power budget [4, 5]. Thus, this PhD project will quantify the effectiveness of different sensor technologies and edge computing systems to endow underwater systems with intelligence perceptive capabilities. Initially, the focus will be on developing and benchmarking different sensing technologies and image processing techniques. We can also explore algorithms for underwater sensing based on unconventional computing paradigms (e.g., spiking neural networks, TinyML) in simulation environments. Expected challenges lay in the physical constraints of the underwater domain and the limited availability of data. In the second stage, the profiled workloads will be deployed on dedicated edge-computing platforms. A successful outcome of this research will pave the way for a novel generation of truly autonomous and energy efficient underwater sensing systems.

We offer you a challenging, stimulating, and pleasant research environment, where you can contribute to international research on artificial intelligence with a close link to the underlying hardware. While you will work in the AI & Data department, you will also be working together with imec hardware, sensor development and university teams on jointly producing novel solutions.

Our ideal candidate for this position has the following skills:

• You have a Master’s degree in Computer Science, Informatics, Physics, Engineering or Electronics.
• You have knowledge about artificial intelligence and machine learning
• You have interest in algorithmic and system design
• You have good programming skills and are flexible in the use of software and coding tools or libraries (git, pytorch, tensorflow, …)
• Understanding of the physics and properties of different sensor modalities (lightwaves, radiowaves, etc.) is considered a plus.
• Experience working with neuromorphic hardware and software is considered a plus
• You can plan and carry out your tasks in an independent way.
• You have strong analytical skills to interpret the obtained research results.
• You are a responsible, communicative, and flexible person.
• You are a team player.
• Your English is fluent, both speaking and writing

References:

[1] Forti, Nicola, et al. "Next-Gen intelligent situational awareness systems for maritime surveillance and autonomous navigation [Point of View]." Proceedings of the IEEE 110.10 (2022): 1532-1537.

[2] Sun, Kai, Weicheng Cui, and Chi Chen. "Review of underwater sensing technologies and applications." Sensors 21.23 (2021): 7849.

[3] Cong, Yang, et al. "Underwater robot sensing technology: A survey." Fundamental Research 1.3 (2021): 337-345.

[4] Frenkel, Charlotte, David Bol, and Giacomo Indiveri. "Bottom-up and top-down approaches for the design of neuromorphic processing systems: tradeoffs and synergies between natural and artificial intelligence." Proceedings of the IEEE 111.6 (2023): 623-652.

[5] Liu, Bin, et al. "A survey of state-of-the-art on edge computing: Theoretical models, technologies, directions, and development paths." IEEE Access 10 (2022): 54038-54063.