Researchers propose using ‘electrosensing’ algorithm to improve underwater navigation

In a paper published in the SIAM Journal on Imaging Sciences recently, researchers at the Swiss Federal Institute of Technology in Zurich proposed modeling the way in which weakly electric fish perceive their environments. They say that their algorithm, which observes objects via electrosensing, could be used to improve the capabilities of underwater robots.

While humans struggle to navigate murky, turbid underwater environments, weakly electric fish like the knifefish and elephantnose fish do so with ease. That’s because they’re specially adapted to traverse obscured waters without relying on vision. Instead, they sense their environment via electric fields, detecting and locating targets based on the distribution of electrical current over their skin.

These fish have specialized electric organs that discharge small voltages into the surrounding water, creating their own personal electric fields. Nearby objects cause slight disruptions to these fields, which the fish detect with sensitive organs on their skin called electroreceptors.

By comparison, the researchers’ algorithm leverages a dictionary of shapes including a circle, ellipse, triangle, bent ellipse, curved triangle, gingerbread man, and drop. Given data from multiple circular orbits at different distances from a target — i.e., measured and recorded electric perturbations — the algorithm uses a matching procedure to compare the data to the dictionary of possible shapes. It provides a numerical score to indicate the degree of similarity between the unknown target and the dictionary item that it most resembled. The numerical scores from different orbits are then combined to create a belief assignment denoting which dictionary shape the algorithm determines is the best match.

To test their recognition algorithm, the authors simulated a fish with 1,024 electroreceptors evenly distributed throughout its body that made three circular orbits around an object. They claim their approach had a higher rate of correct recognition than previous techniques, but they acknowledge that applying it to real-world devices would require extending the system to handle three dimensions.

“Building autonomous robots with electrosensing technology may supply unexplored navigation, imaging, and classification capabilities, especially when sight is unreliable due to the turbidity of the surrounding waters or poor lighting conditions,” Lorenzo Baldassari, who coauthored the study with colleague Andrea Scapin, said in a statement. “[Weakly electric fish] are an ideal subject for developing new bioinspired imaging techniques.”

VentureBeat

  • up-to-date information on the subjects of interest to you
  • our newsletters
  • gated thought-leader content and discounted access to our prized events, such as Transform
  • networking features, and more

Source: Read Full Article