fairfolio
Saved Projects
← Back to Explore

Developing Autonomous and Adaptive Systems For Space-Exploration Robotics With Neuromorphic Frameworks and Artificial Intelligence

JSHS · 2025

Rithvik Suren, Thomas Brown · Academy of Aerospace and Engineering, Windsor, CT

Overview

Space exploration represents humanity’s greatest endeavor into unknown environments. However, we face challenges in developing independent, autonomous and adaptive systems as we continue to identify novel regions. Current AI -driven rovers, such as NASA’s Perseverance, are constrained by SWaP (size, weight, and power) , radiation-resistant hardware performance, and onboard processing limitations for SLAM. This research investigates the potential of neuromorphic frameworks integrating Spiking Neural Networks (SNNs) with reinforcement learning (RL) to enhance power efficiency, adaptability, and radiation robustness for extraterrestrial exploration. Thereby, this novel design improves power consumption, radiation resistance, and robust real -time processing for upcoming rovers. The hierarchical system operates on a Raspberry Pi, leveraging event -driven computation akin to SNNs. Testing procedures included system performance tracking, radiation simulation, and action -space clustering evaluation. Results demonstrated a 30× reduction in CPU time and balanced resource utilization of 11% RAM and CPU, compared to traditional algorithms (RAM: 96.3%, CPU: 6%). t - SNE action-distribution visualizations revealed that SNN-PPO exhibited structured clustering and rapid adaptation, akin to biological learning. Radiation simulation testing confirmed system stability, a key requirement for planetary missions. A Welch’s t -test comparing action -space clustering between SNN-PPO and ANN-PPO yielded t ≈ 7, p < 0.01, confirming that SNN -PPO forms significantly more structured policies, reinforcing its advantage in decision -making under uncertainty. These findings highlight the framework’s potential for increasing rover efficiency while operating in constrained environments. By demonstrating adaptive and power -efficient AI for space robotics, this work advances the development of compact, autonomous planetary rovers and sets the foundation for next-generation space exploration systems.

Competition history

  • JSHS 2025 Category not listed

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Source: Junior Science and Humanities Symposium

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google