Neuromorphic Control Framework for Planetary Rovers (R-STDP SNN)

🚀 Release Summary This is the official release of the software and hardware artifacts associated with the research paper: "Autonomous Navigation for Planetary Rovers Using Reward-Modulated Spiking Neural Networks on Embedded Hardware." This release freezes the exact code version used to generate the experimental results presented in the paper, ensuring reproducibility. 📦 Included Artifacts Simulation Suite: Python scripts for R-STDP training, synapse optimization, and weight export. Embedded Firmware: Optimized C++ code for the Arduino Uno (ATmega328P) implementing the "Dual-Engine" SNN architecture. Benchmark Data: Raw telemetry logs and comparative performance metrics (SNN vs. ANN) validating a 1.63x speedup and 70% energy reduction. Hardware Schematics: Pinout configurations for the TCS3200 sensor and L298N motor drivers. 🔧 System Requirements Hardware: Arduino Uno R3, TCS3200 Color Sensor, L298N Driver. Software: Python 3.8+ (for training), Arduino IDE 1.8+ (for deployment). 📖 Citation If you utilize this codebase or dataset in your research, please cite