Periodic Reporting for period 1 - JASMINE (Jamming and Spoofing Resilient Deep Learning Based Software-Defined Multi-Antenna Multi-GNSS Receiver (JASMINE))
Okres sprawozdawczy: 2023-10-01 do 2025-09-30
JASMINE tackles a critical PNT challenge: ensuring GNSS integrity and resilience in complex environments facing deliberate threats such as jamming and spoofing, requiring robust, intelligent, and scalable protection. The project’s overarching goal is to advance GNSS integrity monitoring and interference resilience by leveraging state-of-the-art machine learning, reinforcement learning, and high-performance signal processing techniques. By combining physics-based models with data-driven intelligence, JASMINE aims to deliver next-generation GNSS receivers and analytical frameworks capable of adapting to dynamic threats, predicting orbital states beyond nominal validity, and ensuring trust in navigation solutions. The pathway to impact is structured around four core research pillars, each contributing to scientific progress and practical applicability:
1. GPU-Based GNSS SDR Development
To enable real-time, high-throughput GNSS signal processing, JASMINE implemented a scalable Software-Defined Radio (SDR) architecture optimized for NVIDIA RTX A6000 GPUs. This design achieves reproducible real-time performance (~1.18× at 2 MHz across 8 channels) and supports multi-GNSS, multi-frequency, and multi-antenna configurations. Key innovations include in-loop decimation and channel-vectorized correlators, which significantly enhance computational efficiency.
Impact: This work demonstrates practical hardware-software co-design for GNSS SDRs, providing a blueprint for future GPU-accelerated navigation systems and contributing to the scientific community through open, reproducible performance benchmarks.
2.GNSS Orbit Prediction Using Deep Learning
The project developed long-horizon orbit forecasting models using advanced neural architectures such as N-HiTS and BiLSTM, extending broadcast ephemerides beyond their nominal validity. By integrating physics-based constraints (e.g. two-body + J2 perturbation models) with residual learning, these models achieve error reductions of 95–99%, significantly improving prediction accuracy and reliability.
Impact: This approach enhances GNSS orbit integrity, enabling better continuity of service during ephemeris outages and supporting mission-critical applications that require extended prediction horizons.
3. GNSS Jamming and Spoofing Detection via Deep Reinforcement Learning
JASMINE reframed interference detection as a reinforcement learning task, enabling autonomous adaptation to dynamic threat environments. DRL agents such as DQN, PPO, and QR-DQN were trained to learn interference patterns and classify jamming/spoofing events with 98% accuracy.
Impact: This represents a paradigm shift in GNSS security, moving from static detection algorithms to intelligent, learning-based systems that can evolve with emerging threats, strengthening the resilience of GNSS infrastructure.
4. Receiver Autonomous Integrity Monitoring (RAIM) with DRL
A novel RAIM framework based on Deep Reinforcement Learning (PPO) was developed to enhance fault detection and integrity assurance in multi-GNSS receivers. By leveraging constellation-aware features—such as pseudorange residuals, C/N₀, elevation, azimuth, LOS vectors, and satellite geometry, the system achieves ~91% one-shot decision accuracy, even under degraded conditions like ionospheric disturbances and satellite faults. Integrated protection-level computation and fault detection & exclusion (FDE) make this solution suitable for safety-critical applications.
Impact: This work advances integrity monitoring beyond traditional RAIM, introducing adaptive, learning-based mechanisms that ensure trustworthy navigation solutions under challenging scenarios.
1. GPU-Based GNSS SDR Development
To enable real-time, high-throughput GNSS signal processing, JASMINE implemented a scalable Software-Defined Radio (SDR) architecture optimized for NVIDIA RTX A6000 GPUs. This design achieves reproducible real-time performance (~1.18× at 2 MHz across 8 channels) and supports multi-GNSS, multi-frequency, and multi-antenna configurations. Key innovations include in-loop decimation and channel-vectorized correlators, which significantly enhance computational efficiency.
Impact: This work demonstrates practical hardware-software co-design for GNSS SDRs, providing a blueprint for future GPU-accelerated navigation systems and contributing to the scientific community through open, reproducible performance benchmarks.
2.GNSS Orbit Prediction Using Deep Learning
The project developed long-horizon orbit forecasting models using advanced neural architectures such as N-HiTS and BiLSTM, extending broadcast ephemerides beyond their nominal validity. By integrating physics-based constraints (e.g. two-body + J2 perturbation models) with residual learning, these models achieve error reductions of 95–99%, significantly improving prediction accuracy and reliability.
Impact: This approach enhances GNSS orbit integrity, enabling better continuity of service during ephemeris outages and supporting mission-critical applications that require extended prediction horizons.
3. GNSS Jamming and Spoofing Detection via Deep Reinforcement Learning
JASMINE reframed interference detection as a reinforcement learning task, enabling autonomous adaptation to dynamic threat environments. DRL agents such as DQN, PPO, and QR-DQN were trained to learn interference patterns and classify jamming/spoofing events with 98% accuracy.
Impact: This represents a paradigm shift in GNSS security, moving from static detection algorithms to intelligent, learning-based systems that can evolve with emerging threats, strengthening the resilience of GNSS infrastructure.
4. Receiver Autonomous Integrity Monitoring (RAIM) with DRL
A novel RAIM framework based on Deep Reinforcement Learning (PPO) was developed to enhance fault detection and integrity assurance in multi-GNSS receivers. By leveraging constellation-aware features—such as pseudorange residuals, C/N₀, elevation, azimuth, LOS vectors, and satellite geometry, the system achieves ~91% one-shot decision accuracy, even under degraded conditions like ionospheric disturbances and satellite faults. Integrated protection-level computation and fault detection & exclusion (FDE) make this solution suitable for safety-critical applications.
Impact: This work advances integrity monitoring beyond traditional RAIM, introducing adaptive, learning-based mechanisms that ensure trustworthy navigation solutions under challenging scenarios.
The JASMINE project advanced GNSS integrity and resilience through four major research activities, each delivering significant scientific contributions:
1. GPU-Based GNSS SDR Development
Activity: Designed and implemented a scalable Software-Defined Radio (SDR) architecture optimized for GPUs to enable real-time, high-throughput GNSS signal processing.
Key Features: The architecture enables real-time processing and can be extended to multi-GNSS, multi-frequency, and multi-antenna configurations with suitable hardware and software adjustments,
leveraging in-loop decimation and channel-vectorized correlators for scalability and efficiency.; in-loop decimation; channel-vectorized correlators.
Achievement: Achieved reproducible real-time performance (~1.18× at 2 MHz across 8 channels), demonstrating practical hardware-software co-design for GNSS SDRs and setting a benchmark for GPU-accelerated navigation systems.
2. GNSS Orbit Prediction Using Deep Learning
Activity: Developed long-horizon orbit forecasting models using advanced neural architectures such as N-HiTS and BiLSTM, integrating physics-based constraints and residual learning.
Achievement: Extended broadcast ephemerides beyond nominal validity with 95–99% error reduction, improving prediction accuracy and reliability for mission-critical applications.
3. GNSS Jamming and Spoofing Detection via Deep Reinforcement Learning
Activity: Framed interference detection as a reinforcement learning task, training DRL agents (DQN, PPO, QR-DQN) to autonomously adapt to dynamic threat environments.
Achievement: Achieved 98% classification accuracy for jamming/spoofing events, marking a paradigm shift toward intelligent, learning-based GNSS security solutions.
4. Receiver Autonomous Integrity Monitoring (RAIM) with DRL
Activity: Designed a RAIM framework using Deep Reinforcement Learning (PPO) to enhance fault detection and integrity assurance in multi-GNSS receivers.
Achievement: Delivered ~91% one-shot decision accuracy under degraded conditions (e.g. ionospheric disturbances, satellite faults), with integrated protection-level computation and fault detection & exclusion (FDE) for safety-critical applications.
1. GPU-Based GNSS SDR Development
Activity: Designed and implemented a scalable Software-Defined Radio (SDR) architecture optimized for GPUs to enable real-time, high-throughput GNSS signal processing.
Key Features: The architecture enables real-time processing and can be extended to multi-GNSS, multi-frequency, and multi-antenna configurations with suitable hardware and software adjustments,
leveraging in-loop decimation and channel-vectorized correlators for scalability and efficiency.; in-loop decimation; channel-vectorized correlators.
Achievement: Achieved reproducible real-time performance (~1.18× at 2 MHz across 8 channels), demonstrating practical hardware-software co-design for GNSS SDRs and setting a benchmark for GPU-accelerated navigation systems.
2. GNSS Orbit Prediction Using Deep Learning
Activity: Developed long-horizon orbit forecasting models using advanced neural architectures such as N-HiTS and BiLSTM, integrating physics-based constraints and residual learning.
Achievement: Extended broadcast ephemerides beyond nominal validity with 95–99% error reduction, improving prediction accuracy and reliability for mission-critical applications.
3. GNSS Jamming and Spoofing Detection via Deep Reinforcement Learning
Activity: Framed interference detection as a reinforcement learning task, training DRL agents (DQN, PPO, QR-DQN) to autonomously adapt to dynamic threat environments.
Achievement: Achieved 98% classification accuracy for jamming/spoofing events, marking a paradigm shift toward intelligent, learning-based GNSS security solutions.
4. Receiver Autonomous Integrity Monitoring (RAIM) with DRL
Activity: Designed a RAIM framework using Deep Reinforcement Learning (PPO) to enhance fault detection and integrity assurance in multi-GNSS receivers.
Achievement: Delivered ~91% one-shot decision accuracy under degraded conditions (e.g. ionospheric disturbances, satellite faults), with integrated protection-level computation and fault detection & exclusion (FDE) for safety-critical applications.
The JASMINE project delivered significant advancements in GNSS integrity and resilience through four major research outcomes:
1. GPU-Based GNSS SDR Architecture
Achieved reproducible real-time performance (~1.18× at 2 MHz across 8 channels) using NVIDIA RTX A6000 GPUs.
Architecture can be extended to multi-GNSS, multi-frequency, and multi-antenna configurations with suitable hardware/software adjustments.
Demonstrated practical hardware-software co-design for high-throughput GNSS signal processing.
2. GNSS Orbit Prediction Using Deep Learning
Developed physics-constrained deep learning models (N-HiTS, BiLSTM) for long-horizon orbit forecasting.
Reduced prediction errors by 95–99%, extending broadcast ephemerides beyond nominal validity.
Supports continuity of service during ephemeris outages for mission-critical applications.
3. Jamming and Spoofing Detection via Deep Reinforcement Learning
Framed interference detection as a reinforcement learning task, enabling adaptive threat classification.
DRL agents (DQN, PPO, QR-DQN) achieved 98% detection accuracy, advancing intelligent GNSS security.
4. Receiver Autonomous Integrity Monitoring (RAIM) with DRL
Developed a DRL-based RAIM framework achieving ~91% one-shot decision accuracy under degraded conditions.
Integrated protection-level computation and fault detection/exclusion for safety-critical applications.
Potential Impacts
Scientific Impact: Establishes new paradigms in GNSS integrity monitoring and interference resilience through AI-driven methods and GPU acceleration.
Societal Impact: Enhances reliability of GNSS for aviation, autonomous systems, emergency services, and critical infrastructure.
Industrial Impact: Provides a foundation for next-generation GNSS receivers and security solutions, enabling commercialization opportunities in high-value markets.
To transition these results into widespread adoption and impact, the following actions are essential:
Further Research & Demonstration
Large-scale field trials for jamming/spoofing detection and RAIM under real-world conditions.
Integration with multi-sensor fusion (e.g. IMU, vision) for resilience in GNSS-denied environments.
Commercialization & Market Access
Development of cost-effective GPU-based SDR hardware for industry deployment.
Partnerships with GNSS receiver manufacturers and PNT service providers.
IPR Support & Standardization
Protection of novel algorithms and architectures through patents.
Regulatory & Policy Framework
Supportive regulations for interference detection and reporting.
Alignment with aviation and autonomous vehicle safety standards.
Internationalization & Collaboration
Cross-border research collaborations for global GNSS resilience.
Participation in EU and international programs on secure PNT.
1. GPU-Based GNSS SDR Architecture
Achieved reproducible real-time performance (~1.18× at 2 MHz across 8 channels) using NVIDIA RTX A6000 GPUs.
Architecture can be extended to multi-GNSS, multi-frequency, and multi-antenna configurations with suitable hardware/software adjustments.
Demonstrated practical hardware-software co-design for high-throughput GNSS signal processing.
2. GNSS Orbit Prediction Using Deep Learning
Developed physics-constrained deep learning models (N-HiTS, BiLSTM) for long-horizon orbit forecasting.
Reduced prediction errors by 95–99%, extending broadcast ephemerides beyond nominal validity.
Supports continuity of service during ephemeris outages for mission-critical applications.
3. Jamming and Spoofing Detection via Deep Reinforcement Learning
Framed interference detection as a reinforcement learning task, enabling adaptive threat classification.
DRL agents (DQN, PPO, QR-DQN) achieved 98% detection accuracy, advancing intelligent GNSS security.
4. Receiver Autonomous Integrity Monitoring (RAIM) with DRL
Developed a DRL-based RAIM framework achieving ~91% one-shot decision accuracy under degraded conditions.
Integrated protection-level computation and fault detection/exclusion for safety-critical applications.
Potential Impacts
Scientific Impact: Establishes new paradigms in GNSS integrity monitoring and interference resilience through AI-driven methods and GPU acceleration.
Societal Impact: Enhances reliability of GNSS for aviation, autonomous systems, emergency services, and critical infrastructure.
Industrial Impact: Provides a foundation for next-generation GNSS receivers and security solutions, enabling commercialization opportunities in high-value markets.
To transition these results into widespread adoption and impact, the following actions are essential:
Further Research & Demonstration
Large-scale field trials for jamming/spoofing detection and RAIM under real-world conditions.
Integration with multi-sensor fusion (e.g. IMU, vision) for resilience in GNSS-denied environments.
Commercialization & Market Access
Development of cost-effective GPU-based SDR hardware for industry deployment.
Partnerships with GNSS receiver manufacturers and PNT service providers.
IPR Support & Standardization
Protection of novel algorithms and architectures through patents.
Regulatory & Policy Framework
Supportive regulations for interference detection and reporting.
Alignment with aviation and autonomous vehicle safety standards.
Internationalization & Collaboration
Cross-border research collaborations for global GNSS resilience.
Participation in EU and international programs on secure PNT.