Alessandra Menicucci

About

Alessandra Menicucci is a leading researcher at the intersection of spacecraft guidance, navigation, and control (GNC) and deep learning, with a primary focus on enabling autonomous close-proximity operations in space. Her work is critical for advancing In-Orbit Servicing (IOS) and Active Debris Removal (ADR), where a servicer spacecraft must safely approach and interact with an uncooperative target. Menicucci’s major contributions lie in solving the "domain shift" problem—the critical challenge of training neural networks on synthetic or ground-based data to perform reliably in the vastly different conditions of space. Her most cited work (43 citations) provides the first on-ground validation of a CNN-based monocular pose estimation system, demonstrating a robust method to bridge this gap. She further advanced the field by integrating neural network uncertainty directly into an adaptive Unscented Kalman Filter (14 citations), creating a more resilient estimation pipeline. A hallmark of her research is rigorous experimental validation; notably, her adaptive filter was successfully tested at Stanford’s robotic Testbed for Rendezvous and Optical Navigation (TRON), a world-class hardware-in-the-loop facility. By fusing computer vision with classical filtering and emphasizing real-world testing, Menicucci is paving the way for the next generation of autonomous, safe, and reliable spacecraft operations.

Research Focus

Key Achievements

Top Papers

1. 1
   On-ground validation of a CNN-based monocular pose estimation system for uncooperative spacecraft: Bridging domain shift in rendezvous scenarios

   43 citations · 2022
2. 2
   Leveraging neural network uncertainty in adaptive unscented Kalman Filter for spacecraft pose estimation

   14 citations · 2023

Key Collaborators

Contact & Links