An ACO-MPC Framework for Energy-Efficient and Collision-Free Path Planning in Autonomous Maritime Navigation

TL;DR

This work tackles energy-efficient, collision-free autonomous maritime navigation by integrating Ant Colony Optimization with Model Predictive Control (ACO–MPC). It introduces a matrix-based framework where candidate paths are generated by ants on a discretized grid, guided by pheromones and heuristics, within a receding-horizon optimization that accounts for energy costs and obstacles. A linear energy-consumption model, fitted from real-world environmental data, is embedded into a matrix-based MPC that optimizes battery dynamics and propulsion planning, with path decisions supplied by the ACO module. Simulation results show substantial energy savings and successful collision avoidance across diverse sea conditions and obstacle configurations, highlighting the practical potential of combining metaheuristic search with receding-horizon control for robust maritime routing.

Abstract

Automated driving on ramps presents significant challenges due to the need to balance both safety and efficiency during lane changes. This paper proposes an integrated planner for automated vehicles (AVs) on ramps, utilizing an unsatisfactory level metric for efficiency and arrow-cluster-based sampling for safety. The planner identifies optimal times for the AV to change lanes, taking into account the vehicle's velocity as a key factor in efficiency. Additionally, the integrated planner employs arrow-cluster-based sampling to evaluate collision risks and select an optimal lane-changing curve. Extensive simulations were conducted in a ramp scenario to verify the planner's efficient and safe performance. The results demonstrate that the proposed planner can effectively select an appropriate lane-changing time point and a safe lane-changing curve for AVs, without incurring any collisions during the maneuver.

Figures (8)

• Figure 1: The example of an autonomous ship.
• Figure 2: High-level overview of the proposed ACO--MPC framework for autonomous ship navigation. Beginning with real-world data collection, the system preprocesses this information and fits a linear model relating renewable resources to energy consumption. These insights feed into the ACO--MPC module, where path planning decisions are continuously optimized to balance energy efficiency, collision avoidance, and operational constraints. The final output is an energy-efficient and collision-free navigation strategy tailored for complex maritime environments.
• Figure 3: The hourly velocity of the ship over 12 months based on HOMER-generated synthetic resource datasets.
• Figure 4: Daily renewable generation profile in June, illustrating solar, wind, and total renewable power.
• Figure 5: Comparison of original data versus linear model predictions for total renewable generation.