Learning lessons for automated vehicle design: Using systems thinking to analyse and compare automation-related accidents across transport domains

Automation is already on our roads, and advanced automated vehicles are anticipated to become a common feature in road transport systems in the near future. While this represents a new era for road systems, automation has existed in other transport systems for decades. The aim of this paper was to analyse accidents involving automated technologies across the transport modes to identify learning opportunities that could be applied in the design of automated vehicles and the wider road systems within which they will operate. Twenty-two investigation reports into automation-related accidents in transport modes traditionally using automation (aviation, maritime and rail) were identified and analysed using the AcciMap technique, with factors codified using a contributing factors taxonomy and analysed using network metrics. To determine their relevance to road automation, the results were compared with an analysis of three recent investigation reports into automated vehicle crashes. The comparison revealed similarities and differences between the contributory factors in the traditional modes and the emerging set of road automation crashes. Two key leverage points were identified: improved human factors integration into the design of automation in all modes; and re-consideration of regulatory approaches across transport domains to ensure they are appropriate for emerging technologies and their associated risks. The analysis also provides support for the utility of previously developed contributory factors taxonomy applied to compare transport domains.