Energy Efficient Navigation for ASVs in Turbulent Vortical Fields

Mentor : Prof. Sandeep Manjanna

Problem Statement:

This research project is centered on the development of a sophisticated Deep Reinforcement Learning (DRL) framework aimed at achieving energy-efficient navigation for an underactuated Autonomous Surface Vehicle (ASV). The proposed system is designed to operate in highly dynamic and unpredictable aquatic environments, with a specific emphasis on leveraging the characteristics of vortical flow fields. The primary objective is to optimize the ASV’s trajectory and control mechanisms to minimize energy expenditure, relying predominantly on thrust-based actuation while simultaneously exploiting naturally occurring environmental phenomena, such as turbulence and vortex structures.

Results: