Shoal performs engineering research in cutting-edge systems engineering with a particular focus on early lifecycle design. Our research aims to further practice in this area, as well as extending this approach into non-traditional domains. Shoal also has research experience in aerospace modelling and simulation, specialising in probabilistic risk assessment for weapons testing, experimental flight vehicles, and space vehicle re-entry. Shoals is conducting research into the application of machine learning technology across several engineering domains and enabling our clients to utilise the latest developments in this field. In addition to these key research areas, Shoal has a significant research track record in the fields of small satellites and quantum computing. Recent research work is outlined below, followed by a publication list with links to our research products.
Model-Based Systems Engineering Practice
Shoal is at the cutting-edge of developing and applying a model-based approach to conceptual design. We apply rigorous, sophisticated analysis to understand the behaviour, needs and requirements of complex systems. This understanding is fostered by our model-based approach, which ensures that this design work is done using systems thinking, that key relationships of aspects of the design are highlighted and that the system designed and implemented will solve the problem.
This work began in the Defence domain in 2009, supporting the capability design of Australian Defence’s most important acquisition projects through the development and application of the Whole-of-System Analytical Framework (WSAF). This framework was initially developed in conjunction with the Defence Science and Technology Group, and Shoal has continued to develop and hone it through use on of key Defence projects. Shoal has several ongoing research efforts that aim to extend the methodology, both in scope and application domain.
Artificial Intelligence and machine learning
The development and realisation of Artificial Intelligence (AI) and machine learning is both exciting and challenging. Recent breakthroughs in the AI research field are allowing new levels of automation and for deriving insight from complex data. While the opportunities for application are numerous, equally, there are potential challenges unique to AI. This can stem from the non-deterministic and evolving behaviour of AI systems, issues related to model accuracy (leading to a lack of trust in the system), and its interactions with its operating environment. Defining the challenges and understanding the risks is extremely important. Shoal supports clients to understand the various applications, risks, challenges and benefits of AI. We assess how you may apply machine learning techniques to provide a ‘fit for purpose’ solution to your problem. This includes understanding what you need the machine learning to do, as well as what you require to implement it and maintain it in operations.
Aerospace Vehicle Behaviour
Shoal has a long history in aerospace vehicle behaviour research. This research has focused on the probabilistic range safety analysis of aerospace vehicles which has the modelling and simulation of complex, guided aerospace vehicles at its core. Much of this work is built upon the Range-Safety Template Toolkit (RSTT), developed in partnership with the Defence Science and Technology Group since 2004. This toolkit has been developed for and applied to a range of guided missiles and spacecraft. Shoal continues to pursue research in this area, looking to improve the accessibility of this toolkit and to apply the approach in the world of Unmanned Aerial Systems.View Publications