Otonom plaj temizleme aracının tasarımı ve geliştirilmesi

The alarming rise of marine debris threatens coastal ecosystems, necessitating efficient, eco-friendly cleanup solutions. This study introduces an autonomous beach-cleaning vehicle engineered to tackle this environmental crisis through sophisticated robotics. Designed for independent operation, the machine integrates advanced sensors, artificial intelligence, and renewable energy systems, paving the way for sustainable environmental robotics. Central to its design is a robust navigation suite, including LiDAR technology for superior spatial awareness and obstacle avoidance. The system's vision capability is enhanced by a neural network-driven object detection algorithm, SSD MobileNet V2, which enables accurate distinction between debris and natural beach elements. Powering the vehicle is a 500-Watt solar panel, emphasizing sustainability by harnessing renewable energy. Detailed integration of photovoltaic cells and power management circuits optimizes energy use, supporting prolonged operation with minimal environmental footprint. The machine's mechanical framework combines a custom track system suited for sandy terrain with a durable trash collection mechanism and waste segregation unit, ensuring thorough and efficient cleanup. Extensive field-testing validates its operational coverage, adaptability, and reliability in diverse beach environments. Additionally, the vehicle's autonomous functions undergo comprehensive simulated testing in Gazebo, where full-scale navigation, path planning, and obstacle avoidance are rigorously assessed. SLAM-toolbox and the Nav2 framework facilitate map generation and mission execution, while the A* algorithm and Dynamic Window Approach (DWB) controller guide path planning and speed adjustments. Data from IMU, wheel encoders, and GPS sensors enhance state estimation, improving accuracy and reliability. Environmental evaluations confirm the machine's adherence to conservation standards, safeguarding beach habitats and local wildlife. The report concludes with a discussion on scalability, its implications for conservation strategies, and potential improvements, including adaptive machine learning algorithms for enhanced waste categorization. This autonomous beach-cleaning machine exemplifies the synergy between technology and ecological stewardship, presenting a scalable model for sustainable coastal management.