arXiv subjects

Richard Bucknall

Publications and source records attributed to Richard Bucknall.

4 recordsLinked to original sources

arXiv2025

Active Tracking of Marine Pollution Sources: An Uncertainty-Aware Categorical Bayesian Framework for Unmanned Surface Vehicles

This paper presents an uncertainty-aware framework for the active tracking of marine pollution sources using Unmanned Surface Vehicles (USVs). The proposed framework employs an Informative Path Planning (IPP) strategy driven by Bayesian inference, modelling the belief of source location as a categorical distribution. This work presents a high-fidelity simulation pipeline, coupling Computational Fluid Dynamics (CFD) for realistic pollutant dispersion with Gazebo-based hydrodynamics and ArduPilot for USV control. Furthermore, this paper introduces the Smallest Credible Interval (SCI) as a metric to quantify estimation uncertainty and to serve as an autonomous termination criterion. Extensive simulations across diverse wave conditions and source locations demonstrate that the proposed framework achieves a 95.8% success rate, significantly outperforming baseline methods in both localisation accuracy and environmental adaptability. This framework provides a scalable and ROS-compatible foundation for fully autonomous environmental monitoring and rapid incident response.

cs.RO↗

arXiv2022

A Fully-autonomous Framework of Unmanned Surface Vehicles in Maritime Environments using Gaussian Process Motion Planning

Unmanned surface vehicles (USVs) are of increasing importance to a growing number of sectors in the maritime industry, including offshore exploration, marine transportation and defence operations. A major factor in the growth in use and deployment of USVs is the increased operational flexibility that is offered through use of autonomous navigation systems that generate optimised trajectories. Unlike path planning in terrestrial environments, planning in the maritime environment is more demanding as there is need to assure mitigating action is taken against the significant, random and often unpredictable environmental influences from winds and ocean currents. With the focus of these necessary requirements as the main basis of motivation, this paper proposes a novel motion planner, denoted as GPMP2*, extending the application scope of the fundamental GP-based motion planner, GPMP2, into complex maritime environments. An interpolation strategy based on Monte-Carlo stochasticity has been innovatively added to GPMP2* to produce a new algorithm named GPMP2* with Monte-Carlo stochasticity (MC-GPMP2*), which can increase the diversity of the paths generated. In parallel with algorithm design, a ROS based fully-autonomous framework for an advanced unmanned surface vehicle, the WAM-V 20 USV, has been proposed. The practicability of the proposed motion planner as well as the fully-autonomous framework have been functionally validated in a simulated inspection missions for an offshore wind farm in ROS.

cs.RO↗

arXiv2022

An Isolated Gate Driver for Multi-Active Bridges with Soft Switching

The design of gate drivers is an important topic in power converter topologies that can help reduce switching losses and increase power density. Gate driving techniques that offer zero-voltage switching and/or zero current switching have recently been successfully proposed for different modular multilevel converters such as the cascaded H bridge. Previous papers on other multilevel converters such as the multi-active bridge, however, do not sufficiently assess the topics of gate driver design for this topology. This work presents a novel isolated gate driver architecture tailored to the multi-active bridge topology. Zero voltage switching is then achieved using two multi-winding transformers. The advantages of the proposed topology are not only a reduction of switching losses but also reduced component count. The topology is evaluated on a prototype using experimental results. It was shown using simulation and experiments that the proposed topology has a high efficiency while providing compact power packaging. Especially for converters with many levels, the proposed topology is therefore advantageous compared to existing solutions.

eess.SY↗

arXiv2021

An Intelligent Energy Management Framework for Hybrid-Electric Propulsion Systems Using Deep Reinforcement Learning

Hybrid-electric propulsion systems powered by clean energy derived from renewable sources offer a promising approach to decarbonise the world's transportation systems. Effective energy management systems are critical for such systems to achieve optimised operational performance. However, developing an intelligent energy management system for applications such as ships operating in a highly stochastic environment and requiring concurrent control over multiple power sources presents challenges. This article proposes an intelligent energy management framework for hybrid-electric propulsion systems using deep reinforcement learning. In the proposed framework, a Twin-Delayed Deep Deterministic Policy Gradient agent is trained using an extensive volume of historical load profiles to generate a generic energy management strategy. The strategy, i.e. the core of the energy management system, can concurrently control multiple power sources in continuous state and action spaces. The proposed framework is applied to a coastal ferry model with multiple fuel cell clusters and a battery, achieving near-optimal cost performance when applied to novel future voyages.

eess.SY↗