A Review of Intelligent Perception Technologies and Their Applications in Agricultural AGVs for Agricultural 5.0

Agriculture 5.0 represents a breakthrough transformation from Agriculture 4.0, addressing the needs for safety, sustainability, and resilience in human–robot collaboration in agriculture. By integrating technologies such as artificial intelligence, digital twins, and big data, it achieves breakthroughs in three areas: perception, cognition, and execution. As carriers of agricultural technology, agricultural automated guided vehicles (AGVs) are an indispensable part of agricultural activities and play a crucial role in agricultural production. In the actual operation of AGVs, intelligent perception is a core technological prerequisite for enabling the communication and interaction among machines, humans, and the environment. However, due to the complexity and variability of agricultural environments, intelligent perception technology remains a highly challenging task. While existing reviews have focused on isolated aspects of agricultural automation, a comprehensive synthesis of intelligent perception technologies for agricultural AGVs within the holistic, human-centric framework of Agriculture 5.0 is notably lacking. This review bridges this gap by systematically analyzing and comprehensively reviewing recent advances in intelligent perception for agricultural AGVs, covering multi-sensor technologies, visual perception and target recognition, positioning and navigation algorithms, as well as applications such as path planning, multi-robot coordination, and human–robot collaboration. Furthermore, this paper delves into the potential challenges and future development trends of intelligent perception technology in the context of Agriculture 5.0, highlighting the transformative potential of these technologies in promoting multimodal fusion and addressing safety issues in human–robot collaboration. In the context of Agriculture 5.0, with the continuous advancement of intelligent perception technologies and the ongoing improvement of agricultural intelligent equipment, a human-centered, highly sustainable, resilient, data-driven agricultural production system will ultimately be formed in the future.