The role of autonomous vehicles (AVs) in assisting people is recognised and, therefore, is in constant development in numerous fields. Specifically, AV’s ability to alleviate global stressors, including an increased potential for food shortages and the decline in workers for potentially laborious work. An area where AVs developments are particularly prevalent is in agriculture. However, the few AVs being used in agriculture are often custom built for specific purposes and require large development time as a result. This thesis aims to build and evaluate a versatile architecture that can be transferred to any agricultural vehicle, thus decreasing the development time. This thesis presents a novel architecture known as a semi-autonomous architecture (SAA). The research involved investigating and incorporating specific sensors, and also developing a common software module to perform the localisation, navigation and mapping particularly suited for corridor crop agricultural environment. This architecture was integrated and implemented on a Yamaha golf cart, infusing it with purposely positioned sensors and supportive electronics to allow a Robotic Operating System (ROS) framework to gather information and control the vehicle. As the architecture is modular in nature, it can be transferred to different customised platforms. To determine the efficacy of the SAA, the platform went through a field trial and simulations to test the fundamentals of an agricultural AV. This meant investigating the SAA’s ability to map, plan paths, avoid obstacles and maintain a specific distance from a row. The evaluation demonstrated that both ’RTAB-Map’ and ’Gmapping’ could produce accurate maps of a vineyard. Additionally, grid-based planners, such as Dijkstra and A*, performed better than a sample-based planner bias-IRRT*. Regarding obstacle avoidance, the SAA required a greater range of sensors to detect small and oddly shaped objects that could be found in a vineyard. The SAA maintained within 5mm of the specified distance when aiming to follow the row. The results from these experiments demonstrated the SAA’s ability to successfully transform a Yamaha golf cart into a semi-autonomous agricultural vehicle.