Abstract Traditional agricultural plant protection primarily relies on manual labor and indiscriminate chemical spraying, resulting in inefficiency, increased cost, and environmental pollution. The advancement of precision agriculture is impeded by three persistent bottlenecks in field robotics, namely, unreliable wireless communication within crop canopies, computational limitations for real-time edge artificial intelligence (AI), and high costs of system integration. To address these challenges, as a proof-of-concept feasibility study, this work presents the design and integrated laboratory-based verification of a novel, low-cost, AI-driven plant protection robot. Its core innovation lies in the holistic co-design of a custom CRC-16-protected communication protocol, an edge AI-based pest detection pipeline, and a precision spraying mechanism within a unified architecture. Laboratory-based verification demonstrated that (1) an optimized YOLOv11l model achieves a mean Average Precision (mAP@0. 5) of 0. 806 for pest detection, with an inference latency of 35. 7 ms, on a Raspberry Pi 4B; (2) the custom protocol ensured a data fidelity of 99. 91%, with a transmission latency of 12. 3 ± 2. 1 ms; and (3) the robotic platform achieved a path tracking accuracy of 1. 8 ± 0. 5 cm and an operational coverage efficiency of 98. 7 m²/h, with a projected operational cost of approximately 1. 95 per hectare under idealized laboratory conditions. These results confirm the technical feasibility of the integrated approach as a foundation for future field development. This work provides a scalable, cost-effective framework that couples robust perception, reliable communication, and precise actuation, thereby offering a practical proof-of-concept for smart farming applications.
Jiang et al. (Sat,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: