RAAS White Paper: Safety Challenges of Autonomous Mobile Systems in Dynamic Unstructured Environments: Situational awareness, decision-making, autonomous navigation, & human-machine interface

Future autonomous mobile systems will be capable of operating in often unstructured and dynamic environment in a safe and meaningful manner and simultaneously work towards given mission objectives without being extensively controlled by human operators. In order to do that an autonomous system has not only to monitor its internal state but also sense, perceive, classify and model what is currently happening around it and even predict what will most likely happen in the near future. The requirement is the same be it a modern highly automated system working or transportation machine, an intelligent field and service robot or a next-generation oceangoing vessel. The current wide range of high-quality sensor systems available commercially-off-the-shelf together with well-matured multi-sensor fusion algorithms provide a solid foundation for that task. In addition, the system should be connected to any available supportive infrastructure (e.g., localization services, dynamic maps, etc.) and have tight interactions with other autonomous mobile systems sharing the same operation space. Furthermore, the autonomous mobile system should, at all times, in any condition, be fully aware of any human presence - intended or unintended. The safety of humans must be ensured at any cost.