Peter Schneider

Leading AI and Machine Learning projects focused on deep learning, with applications spanning perception, language models, graph neural networks, temporal modeling, autonomy, path planning, and signal processing.

• Principal Investigator for Strike-Aligned AI Research, guiding projects from from early-stage research through cross-program collaboration, stakeholder engagement, and program insertions.
• Architected transformer-based neural networks for constrained multi-objective path planning, learning optimal trajectories that minimize detection risk while satisfying mission constraints; designed end-to-end training pipelines combining behavior cloning pretraining with gradient-based reinforcement learning fine-tuning.
• Architected complex-valued neural networks better exploiting both magnitude and phase in SAR and optical data; successful SAR ATR demo deployed on Triton.
• Architected transformer-based neural networks that predict the optical response of metaoptics faster and more accurately than traditional simulation methods; Trade Secret granted, NG Innovation Award, and paper published in Optics Letters.

Deep learning with SAR imagery.

• Research and development of complex-valued neural networks exploiting both magnitude and phase data in SAR under National Geospatial-Intelligence Agency (NGA) Boosting Innovative GEOINT BAA.
• Evaluated domain shift bias from training with synthetic data; combined collected with synthetic data using transfer learning to significantly improve model performance.
• Redeveloped existing models to modern SOTA single-shot architectures improving performance.
• Presented work at 2020 SAREM forum in Chantilly, Virginia.

Machine Learning and autonomy; worked with the Cognitive Autonomy Research Group.

• Developed and trained neural networks for satellite imagery perception and anomaly detection with time-series telemetry data.
• Developed trajectory optimization and nonlinear state estimation algorithms and supporting simulation platform for autonomous formation flying.

Machine Learning, GNC (Guidance, Navigation & Control), and Modeling & Simulation for national security space supporting the U.S. Space Force and National Reconnaissance Office (NRO).

• Led a team working on the next-generation GPS satellite constellation (GPS Block III) and contributed to launch vehicles (Atlas V and Falcon), missile systems, and other satellite constellations.

GNC (Guidance, Navigation, & Control) and Modeling & Simulation for satellites.

GNC (Guidance, Navigation, & Control) and Modeling & Simulation for the GOES satellite constellation operated by NOAA.