Present-day levels of marine traffic pose a challenge to navigators to avoid vessels safely and efficiently. Unfortunately, despite technological advancements, maritime collisions still occur frequently due to human error. Likewise, deficiencies with unmanned surface vessels (USVs) involve their inability to automatically avoid traffic in a safe manner, complying with the international Regulations for Preventing Collisions at Sea 1972 (COLREGs). This thesis presents an USV obstacle avoidance framework, with holistic considerations of the navigation, guidance and control (NGC) system, as well as synthesis with an obstacle detection subsystem. The primary focus is a real-time path planning system, which incorporates COLREGs. Notable attempts on this topic to date adopt approaches such as evolutionary methods, artificial potential fields (APFs) and multi-objective optimisation strategies, for which prevalent limitations include lack of real-time capabilities, excessive computational effort, the compromise of safety in favour of optimality and failure to consider vessel dynamics.

Carbon Dioxide (CO₂) is considered to be the most detrimental of all the Green House Gases on global warming (IMO, 2009). In an attempt to reduce the amount of CO₂ emissions from ships, this research approaches the problem from the perspective of more efficient design through superior estimation of design points. Conventionally, a propeller is selected from the viewpoint that a ship travels at a constant design speed, with zero drift angle. However, a ship is subjected to the motions imposed on her from the environment. These motions tend to push a ship off her intended course, resulting in helm correction, speed correction (if the ship is to arrive at her intended destination on time) and consequently, altered inflow velocity to the propeller. It is the novel aim of this research to determine if accounting for a ship’s manoeuvring motion will result in a propeller selection that has an overall higher efficiency, compared to one selected which neglects the manoeuvring motion. To achieve this aim, a ship manoeuvring simulator has been developed which incorporates a modified mathematical propeller model that accounts for the unsteady manoeuvring response of a ship subjected to an environment in which she is expected to sail. The developed simulator has an iterative routine which enables it to select a propeller from a standard series that has the highest efficiency for the route in question. Case studies are constructed which highlight how the efficiency of a propeller fairs when using the newly proposed propeller selection method, compared to the conventional propeller selection perspective. The newly proposed propeller selection method is most suited to ships which are susceptible to relatively large drift angles and/or relatively high installed power requirements. Results from the case studies are encouraging, with a gain of 2.34% in open water propeller efficiency for a 3600 Twenty foot Equivalent Unit container ship, equating to a saving of 3.22% in Carbon Dioxide emissions.

The importance of human factors has to be taken into account when determining a yacht’s performance over a course. The crew’s capabilities of technical skills, athletic performance, and his/her ability of making rational decisions under time pressure and in light of uncertainty of the future wind regime are important aspects that will determine the overall performance of a yacht-crew system. This thesis highlights the performance of such a yacht-crew system with a focus on the decision-making process of sailors. Aspects of human behaviour in sport and the decision-making process are explained considering the level of expertise and possible approaches of how to model them are shown. An artificial intelligence AI -system is developed that is capable of simulating the decision-making process of different sailing behaviours/styles as well as different expertise levels of sailors within a dynamically changing yacht racing environment. The constraints of the multiple fleet racing simulator Robo-Race (Scarponi 2008) were determined using a series of tests with real sailors identified three important constrains: (1) the predictable behaviour of the AI-yachts, (2) the predictable and unrealistic weather model and (3) the simple model describing the effects of yacht interaction. These restrictions and constraints that limited the real and AI-sailors natural sailing behaviour have been successfully removed in the updated version of Robo-Race. The new developed decision-making engine based on Decision Field Theory that uses Bayesian Belief Networks as the perceptual processor showed a clear superiority over the old rule-based decision-making engine. Extensive simulations demonstrate the feasibility of modelling various decision-making processes and therefore different behaviours and expertise levels of sailors. A good comparison was found with that obtained between the Robo-Race results and the Olympic fleet racing events.