Diptanshu Mann

Agricultural operations encounter increasing expectations for efficiency, accuracy, and sustainability. This research seeks to enhance these procedures with the incorporation of autonomous equipment, directed by model-based systems engineering (MBSE). Autonomous systems are widely acknowledged for their ability to exceed conventional manual techniques, improving productivity and minimizing environmental effects. The study examines essential input variables, including remote sensing data (e.g., NDVI) and land topography, to enhance efficiency of agricultural practices such as route planning, irrigation management, and grain storage optimization through MBSE. The primary scientific objective of this study is to identify the minimum autonomy requirements needed to maximize operational efficiency, reduce labor demands, and minimize costs in agricultural systems. To achieve these aims, the study will implement an MBSE framework that investigates varying levels of autonomy, ranging from semi-autonomous to fully autonomous systems.

Beyond optimizing current agricultural practices, the study extends to the concept development of a fully battery-electric tractor, addressing charging infrastructure and its integration into sustainable farming operations by looking at autonomy as an electrification enabler. Finally, the study will propose a human-machine interaction system for autonomous machinery, utilizing large language model (LLM) based user interfaces to serve as operational assistants. These systems aim to facilitate real-time decision-making and automated report generation, further enhancing the efficiency and adaptability of agricultural operations. This study's scientific and societal significance lies in its potential to revolutionize agricultural practices through advanced autonomous systems, promoting sustainable farming, reducing human labor, and enabling smarter resource management.