Flow feature extraction for underwater robot localization: Preliminary results

Underwater robots conventionally use vision and sonar sensors for perception purposes, but recently bio-inspired sensors that can sense flow have been developed. In literature, flow sensing has been shown to provide useful information about an underwater object and its surroundings. In the light of this, we develop an underwater landmark recognition technique which is based on the extraction and comparison of compact flow features. The proposed features are based on frequency spectrum of a pressure signal acquired by a piezo-resistive sensor. We report experiments in semi-natural (human-made flume with obstacles) and natural (river) underwater conditions where the proposed technique successfully recognizes previously visited locations.

I. Introduction

In order to autonomously localize and perform other useful tasks, such as object recognition and mapping, robots have to perceive their surroundings. Robots use different kinds of sensors for perceiving their environment such as cameras, sonar, lidar and radar. In underwater robotics, it has recently been discovered that flow sensing can also provide cues for perception of a robot's surroundings. The idea is biomimetic; blind cave fish for instance, despite having no vision capability at all, are able to perform navigation through complex environments using their flow sensing organ, the lateral line [1]. Introduction of flow sensing into robotics owes to the development of artificial lateral line sensors and sensor systems that can sense flow in underwater environments, such as [2], [3], [4] and [5].