Informative path planning (IPP) tasks UAV with locating and accurately measuring high concentrations of specific phenomena in initially unexplored, budget constrained search space. Adaptive-IPP closes the loop between sensing and planning by replanning sensor trajectories as a probabilistic belief about the environment evolves but even state-of-the-art planners face two challenges while replanning their trajectory online: 1.) Replanning during deployment incurs substantial online computation and thus time costs during deployment, which is problematic in a time-budgeted mission and 2.) the resulting path-optimization landscape is non-convex, producing a fundamentally multimodal set of valid solutions. Behaviorally cloning such an expert with a deterministic, MSE-trained policy mode-averages these equally valid trajectories, producing plans that correspond to none of them and fail to learn the underlying monitoring objective in unseen environments.This thesis presents a path-planning framework that instead uses a conditional denoising diffusion model to generate valid 3D waypoint sequences for continuous environments. A novel CMA-ES-based data collection procedure exposes multiple deployable expert trajectories per belief state, giving the diffusion model a genuinely multimodal demonstration set to learn from. We tested our diffusion based model in simulated missions on synthetic Gaussian random fields and real-world agriculture maps based on the National Agricultural Imagery Programme (NAIP) and found that diffusion reduces time-integrated map uncertainty by roughly 34\% relative to the online replanning expert that it was trained on, while replanning approximately 11× faster by appropriately learning the goal of online replanning through the multimodal dataset, and consistently outperforms a deterministic learning baseline trained on the same demonstrations. These results suggest that diffusion-based behavioral cloning preserves valid planning modes and enables real-time, non-myopic informative path planning. ... Read more

Space structures such as the International Space Station experience continuous degradation throughout their operational lifetime due to micrometeoroid impacts, radiation exposure, thermal cycling, and material ageing. Current external inspection approaches rely primarily on astronaut spacewalks and robotic manipulators, which introduce operational risks, require significant resources, and provide limited flexibility. As orbital infrastructure grows in scale and complexity, autonomous inspection systems become increasingly necessary.

This report presents the detailed design of Project EVE, an autonomous inspection system consisting of two free-flying drones designed to inspect large space structures using complementary non-destructive testing methods. The objective is to detect, localise, and characterise structural damage while reducing dependence on human intervention.

The selected architecture employs two specialised vehicles. Alpha performs rapid large-area inspection and identifies regions of interest, while Beta conducts detailed follow-up inspection. Together, the drones combine optical imaging, three-dimensional structured light, infrared thermography, and shearography to enable both surface and subsurface defect detection. To support detailed inspections in orbit, a deployable shading mechanism creates controlled thermal transients without dedicated heating hardware.

The final integrated design demonstrates that autonomous multi-drone inspection can provide a scalable, safer, and operationally flexible alternative to conventional inspection approaches for future long-duration space infrastructure. ... Read more