Khalasi: Energy-Efficient Navigation for Surface Vehicles in Vortical Flow Fields

TL;DR

This paper introduces a reinforcement learning-based method for autonomous surface vehicles to navigate energy-efficiently in vortical ocean flows, leveraging local measurements to adapt to complex, partially observable environments.

Contribution

It presents a novel end-to-end Soft Actor Critic reinforcement learning framework for flow-aware navigation, improving energy efficiency and robustness over traditional methods.

Findings

Achieves 30-50% energy savings compared to existing techniques.

Demonstrates strong generalization to unseen flow conditions.

Provides a scalable approach for long-term ocean surface vehicle autonomy.

Abstract

For centuries, khalasi (Gujarati for sailor) have skillfully harnessed ocean currents to navigate vast waters with minimal effort. Emulating this intuition in autonomous systems remains a significant challenge, particularly for Autonomous Surface Vehicles tasked with long duration missions under strict energy budgets. In this work, we present a learning-based approach for energy-efficient surface vehicle navigation in vortical flow fields, where partial observability often undermines traditional path-planning methods. We present an end to end reinforcement learning framework based on Soft Actor Critic that learns flow-aware navigation policies using only local velocity measurements. Through extensive evaluation across diverse and dynamically rich scenarios, our method demonstrates substantial energy savings and robust generalization to previously unseen flow conditions, offering a promising path toward long term autonomy in ocean environments. The navigation paths generated by our proposed approach show an improvement in energy conservation 30 to 50 percent compared to the existing state of the art techniques.