NASA Lunar Robotics Challenge

NASA's lunar challenge required autonomous robots to navigate the lunar surface, detect and classify rocks, and make intelligent decisions without human intervention. The environment was simulated in Carla with strict competition rules requiring containerized submissions.

Set up custom Carla simulation environment and managed team development workflow. Containerized entire solution using Docker to meet competition requirements. Implemented autonomous control algorithms for lunar navigation. Integrated Ultralytics YOLOv8 CNN trained on Kaggle rock database for real-time rock detection and classification.

Successfully submitted working solution to NASA competition. Demonstrated leadership and technical project management skills. Gained experience with simulation environments, computer vision, and autonomous systems.

• •Configured custom Carla-based NASA simulation environment
• •Created Docker containers adhering to strict competition rules
• •Led team in brainstorming and implementing autonomous control logic
• •Integrated YOLOv8 for real-time rock detection
• •Trained CNN on specialized lunar rock dataset from Kaggle
• •Managed project timeline and deliverables under competition pressure

• →Implement SLAM for better environment mapping
• →Add path planning with A* or RRT algorithms
• →Fine-tune YOLOv8 specifically on lunar surface imagery
• →Add sensor fusion with LiDAR data