Conventional agricultural methods face serious pressures. A growing global population and rising food demand must be met using shrinking agricultural areas and constrained resources, while many traditional farming tasks remain tedious and dangerous. To address this, the intelligent management of essential inputs such as seeds, plants, water, soil, and energy has become critically important. Therefore, it is needed to focus on strategic agricultural decisions to enhance efficiency of agricultural production, while conserving soil and protecting the environment. This requires Intelligent Robots and Farming Machines (IRFMs) that can autonomously detect, navigate, decide, and operate across all terrains. The adoption of artificial intelligence (AI) within automated farm machinery and robotics is accelerating the evolution of agricultural equipment, processes, and management systems, driving the shift toward more efficient and sustainable farming practices. The existing research gap is that neither the operational efficacy nor the structural/optimization aspects of AI-enabled IRFMs have been thoroughly investigated. To address this, following PRISMA guidelines, this study conducted a systematic review, supported by a bibliometric analysis based on keywords derived from prior publications in the domain. The review examines key trends, applications, and recent developments in AI-enabled drones and IRFMs across agricultural tasks from planting to harvesting, covering studies published between 2012 and 2025 and identifying 218 articles that met the inclusion criteria. The analysis explores how AI and machine learning (ML) enhance IRFMs through automation, particularly in detection, navigation, decision-making, and structural design optimization, while time-series analysis is used to forecast future trends in AI’s role in improving IRFMs structure and performance. Existing challenges in adopting AI techniques for both the structural and practical aspects of IRFMs in sustainable agriculture are also assessed, and potential solutions are proposed. Overall, the findings highlight priority areas for agricultural automation and reveal innovation opportunities and unresolved challenges that can guide future research and support the development of the next generation of AI-enabled farm machinery and robotics.

Keywords