Anuj Sehgal

TOUCH: a robotic vision system for underwater object tracking

TOUCH is a real-time computer vision system that has been developed in order to aid the operation of autonomous underwater vehicles (AUVs) and remotely operated vehicles (ROVs). The algorithm is based on a modified 4-connectivity approach that scans the incoming frames for a target hue range and based upon the largest connected blobs of hue, tracks an object and provides the two dimensional Cartesian coordinates of the desired object. Since few algorithms exist for tracking and recognizing objects in underwater environments, this algorithm provides a way for AUVs and ROVs to acquire, track or recognize objects by using a relatively fast and inexpensive vision system. This paper presents the details on TOUCH, its testing, some areas that warrant improvement and possible course of action for the future.

A multi-AUV missions simulation framework for the USARSim Robotics Simulator

The maximum potential for underwater exploration rests within the use of multiple Autonomous Underwater Vehicles (AUVs) and tasks involving human diver-AUV coordination. Such tasks require dependable underwater wireless communications, which normally utilize the rapidly varying acoustic channel. Rigorous testing of underwater acoustic communication systems is necessary to develop a dependable network, however, the high offshore testing costs make this difficult. Though simulators could aid the development of such AUV communication systems, the few existing simulators focus upon simulating a single vehicle and, as such, do not provide tools for simulating underwater communication systems. In this paper we present an underwater communications simulation framework designed for the Unified System for Automation and Robotics Simulator (USARSim). This simulation tool is capable of modeling networked communications between, or with, AUVs by accurately characterizing the underwater acoustic channel. Details on this simulation framework are provided along with some results obtained during development of this tool.

CoViS: An amphibious computer vision system

This paper presents, CoViS, a low-cost real-time amphibious optical computer vision system based on a modified 4-connectivity approach that scans acquired frames from a video stream for a target hue range and then applies a few advanced techniques of image processing to the video as well. The relatively fast and inexpensive system provides Cartesian coordinates for the tracked object, making the system an option for unmanned amphibious vehicles to acquire, track and recognize objects.

Autonomous underwater unmanned vehicular recovery system based on low-cost inter-aural time differentiation passive sonar

Sensing systems for AUVs are deeply researched but post mission deployment recovery systems for these vehicles are equally important. This paper presents a low-cost recovery system designed to provide post mission recovery location discovery capabilities to AUVs. The recovery system discussed relies on inter-aural time differentiation of sonar pulses received by the AUV from a sonar beacon.