Abstract
The lateral line organ of fish has inspired engineers to develop flow sensor arrays—dubbed artificial lateral lines (ALLs)—capable of detecting near-field hydrodynamic events for obstacle avoidance and object detection. In this paper, we present a comprehensive review and comparison of ten localisation algorithms for ALLs. Differences in the studied domain, sensor sensitivity axes, and available data prevent a fair comparison between these algorithms from their original works. We compare them with our novel quadrature method (QM), which is based on a geometric property specific to 2D-sensitive ALLs. We show how the area in which each algorithm can accurately determine the position and orientation of a simulated dipole source is affected by (1) the amount of training and optimisation data, and (2) the sensitivity axes of the sensors. Overall, we find that each algorithm benefits from 2D-sensitive sensors, with alternating sensitivity axes as the second-best configuration. From the machine learning approaches, an MLP required an impractically large training set to approach the optimisation-based algorithms’ performance. Regardless of the data set size, QM performs best with both a large area for accurate predictions and a small tail of large errors.
Highlights
Artificial lateral lines (ALLs) are sensor arrays inspired by the biological lateral line organ found in fish and amphibians
The modelbased predictors were slower: the multi-layer perceptron (MLP) could compute roughly four, eight and nine predictions in the time it took for GN, least square curve fit (LSQ) and quadrature method (QM) to compute a prediction
The remaining algorithms were considerably slower than the MLP (36 times for linear constraint minimum variance (LCMV), 175 times for NR, and 300 times for Continuous Wavelet Transform (CWT))
Summary
Artificial lateral lines (ALLs) are sensor arrays inspired by the biological lateral line organ found in fish and amphibians This organ enables fish to detect and locate moving objects such as prey, predators, or social partners [1]. Two types of hydrodynamic imaging are distinguished: active hydrodynamic imaging, where fish use their movement’s flow field to detect stationary obstacles; and passive hydrodynamic imaging, where fish detect fluid flows generated externally. Both types of hydrodynamic imaging have applications for ALLs. Active hydrodynamic imaging is useful for obstacle avoidance of autonomous underwater vehicles (AUVs) [4]. Passive hydrodynamic imaging can be used for tracking the location of objects—for instance, ships in a harbour—or detecting disturbances near underwater installations
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
