Humanity is reexamining how we co-create part-nerships with systems required to adapt to our changing needs. Robotic fleet autonomy in Inspection, Maintenance and Repair (IMR) demands robust operational governance, resilience in dynamic operating environments, and a diverse range of capabilities tailored to specific assets. This paper proposes a Symbiotic Multi-Robot Fleet (SMuRF) deployed in partnership with a human-in-the-Ioop via an operational decision support interface. Symbiosis provides a new collab-orative learning strategy to increase robot team performance and resilience to stochastic environmental variables while improving cyber-physical system management for a human-in-the-Ioop. The management of the SMuRF is implemented via a digital architecture that permits near to real-time communication for up to 1800 distributed robots, sensors, and assets. The measured productivity resulted in an improvement between 23 - 62 % due to optimized fleet management and task allocation within the SMuRF. The SMuRF has been validated via an autonomous mission evaluation scenario for an offshore substation with an induced fault on a robot, where autonomous symbiotic interactions utilizing machine learning rectify the issues to ensure the resilience of the mission for the multi-robot fleet.

Mapping structural brain connectomes for living human brains typically requires expert analysis and rule-based models on diffusion-weighted magnetic resonance imaging. A data-driven approach, however, could overcome limitations in such rule-based approaches and improve precision mappings for individuals. In this work, we explore a framework that facilitates applying learning algorithms to automatically extract brain connectomes. Using a tensor encoding, we design an objective with a group-regularizer that prefers biologically plausible fascicle structure. We show that the objective is convex and has unique solutions, ensuring identifiable connectomes for an individual. We develop an efficient optimization strategy for this extremely high-dimensional sparse problem, by reducing the number of parameters using a greedy algorithm designed specifically for the problem. We show that this greedy algorithm significantly improves on a standard greedy algorithm, called Orthogonal Matching Pursuit. We conclude with an analysis of the solutions found by our method, showing we can accurately reconstruct the diffusion information while maintaining contiguous fascicles with smooth direction changes.