Ravos: Exercising Contextually Aware Distributed Autonomic Control in Land Vehicles Benjamin Campbell, Glen Pearce, Ant Perry, Brendan Sims, Mohammad Zamani, Lance Newby and Robert Hunjet Land Division Defence Science and Technology Group Edinburgh, Australia Abstract—This paper explores the need for contextually aware distributed autonomic control of land vehicle mission systems. It proposes Ravos, a distributed, autonomic land vehicle mission system controller. It describes exemplar applications enabled by contextually aware autonomic control and the architectural requirements to achieve them in an integrated manner. We explain how the capabilities provided by these systems would be beneficial to land forces and conclude with a description of the planned future work required to develop Ravos. Keywords—autonomic control; distributed control; context awareness; resilient positioning; collaborative pose filter; low probability of detection I. INTRODUCTION The transition of land military vehicles to digitised platforms brings with it growth in the number and complexity of mission systems hosted on these vehicles. This has and will continue to increase the cognitive burden imposed on vehicle operators in administering and controlling their mission systems in complex military environments. It can be assumed that this complexity is further exacerbated in the case where coordinated operation of these systems over multiple vehicles is required. To this extent, full capabilities of these mission systems remain unexploited. Given these challenges, we argue it would be advantageous for low level mission systems to be supervised and controlled by an intelligent software system (referred to here as an autonomic manager), enabling optimal configuration across multiple sub-systems and reducing the cognitive load of the vehicle operators. This control would be responsive to environmental and system state change (context- aware), and autonomic, i.e. self-Configuring, self-Healing, self- Optimising and self-Protecting (self-CHOP) [1]. The initial research efforts on autonomic control have mainly been focused on complex Information Technology (IT) applications [2]. The Advanced Vehicle Systems (AVS) research team in DST Group is aiming to extend the applicability of autonomic control to mission systems on and across military vehicles. AVS is developing an intelligent software solution called Ravos that exercises contextually aware autonomic management of distributed land mission systems. A number of technical challenges specific to land vehicles and military environments need to be tackled before achieving this goal. One noteworthy example is that distributed context awareness needs to be achieved with respect to mission systems of different domains such as positioning, communications, electronic warfare and vehicle protection. Moreover, exercising correct autonomic control with respect to the context needs to extend across various mission systems across these different domains in order to be effective. Furthermore, mission system operational scope is often distributed across multiple land vehicles that rely on a congested and potentially contested local wireless network. The contributions of this paper are: • a number of proof of concept applications being developed by AVS in order to validate the general framework of the Ravos software. In particular, we provide an exemplar autonomic software concept for control of networking devices that seeks to adaptively adjust transmission power to ensure connectivity with friendly vehicles while also trying to minimise probability of detection by enemy. In another example we introduce a prototype of autonomic software for adaptive navigation sensor selection and configuration based on context derived from user needs, sensor performance and other relevant situational awareness considerations. Finally, a collaborative localisation application is introduced that leverages communication and non-GPS positioning devices as a distributed autonomic controller for dealing with GPS challenged situations. • architectural considerations proposed for Ravos which addresses the effective integration of various autonomic controllers. Integration of context aware, distributed, self- adaptive autonomic controllers has a number challenges in terms of mechanisms for dissemination of information and objectives, timeliness of decisions, coordination and arbitration of conflicting actions between autonomic controllers. For example, rather than incorporating a stovepiped network device controller and a stovepiped collaborative localisation controller that may counteract each other by contentious requests on a radio device, we seek an architecture that avoids this problem by providing appropriate cross-domain information, interfacing protocols and coordination and arbitration. • distributed context awareness considerations and the approach taken in Ravos for translating high level mission goals to appropriate low level objectives and constraints for individual autonomic controllers. The ultimate goal of Ravos is to unburden the vehicle operator in low level situational assessment, decision making and control of mission systems. In this paper we discuss the enablers which Ravos amalgamates in order to translate operator’s intent to mission system controllers.