Maritime

This is another short extract from the Thesis that I thought was particularly relevant given recent news coverage of the dangers of autonomy and AI, particularly in the field of “killer robots”. Legal Considerations in Design Trust If there is one key feature of the application of robotics and autonomy to the defence field that separates it from applications in commercial and civil fields, it is the potential direct impact on life and safety. ...

I’m leaving Northern Ireland, and I’m moving to Liverpool. Via Portsmouth. I have spoken with a few people about the situation I find myself in, and a few more people about my decision, but I want to get it all down somewhere. Where did this come from? The short answer is that a series of unexpected events mean that it makes sense to move my research. Recently, my PhD supervisor, Prof Alan Marshall, was offered a research Chairship at the University of Liverpool, which he gladly accepted. It’s a great move for him (Another Russell Group, one of the original ‘redbrick’ universities, etc etc), but that’s his life not mine so all it does is provide an option. (Disclosure: I also work with Alan on his spinout Wireless Security company, TOM Ltd) ...

Biblio Sorbi, Toni, Dio De Capua, Rossi TERA, Genova Grade 1 What is this work about? Collaborative target tracking behaviours What are the main findings of this work? No surprise; two AUVs with a comms link are better at tracking, and that tracking is easier when the targets are stupid/random. What gap in our understanding does this work fill? Highlights MLO tracking operations, and provides insight into globally aware control systems ...

Biblio Carreras, Batlle, Ridao, and Roberts; An Overview on Behaviour based methods for AUV control, Girona, Spain What is this work about? A review and analysis of four AUV behaviour based reactionary control architectures, presenting four control architectures; Scheme, Subsumption, PDL, and Action Selection Dynamics, i.e. cooperative (schema, PDL) and competitive (Sub, ASD) What are the main findings of this work? Competitive models are often easier to design as only one behaviour is resident at a time, however this leads to ’jaunty’ and often sub-optimal results, as in this case where authors say the resultant pats for both competitive models are non-optimal ...