Artificial intelligence is transforming agriculture from a mechanized, labor-intensive sector into a data-driven, perception-enabled, and increasingly autonomous production system. In this review, AI serves as an umbrella term encompassing machine learning, computer vision, and robotic control, among other technologies. We synthesize recent advances across the tillage–sowing–management–harvesting (TSMH) workflow, covering intelligent tillage, precision sowing, field management, and robotic harvesting. The literature shows that AI has significantly improved agricultural perception, prediction, and task-level decision-making. However, large-scale adoption remains constrained by data heterogeneity, limited cross-scene generalization, environmental uncertainty, and insufficient integration across operational stages. Future progress will depend on multimodal data fusion, lightweight and interpretable models, cloud-edge collaboration, and full-chain decision architectures. By framing current research within the TSMH pipeline, this review highlights both technical advances and the critical bottlenecks that must be addressed to move smart agriculture from stage-specific intelligence toward system-level autonomy. Representative studies indicate that AI models can improve soil-property prediction and reduce sowing miss-detection rates to below 3% under controlled or bench-top conditions. However, field deployment may be affected by environmental variability, including illumination changes, dust, vibration, occlusion, and hardware constraints. These limitations highlight the need for robust and edge-compatible architectures.

The driving speed of autonomous agricultural vehicles is influenced by surrounding cooperative vehicles during cooperative operations, leading to challenges in simultaneously optimizing operational efficiency, energy consumption, safety, and driving smoothness. This bottleneck hinders the development of autonomous cooperative systems. To address this, we propose a hierarchical speed decision control framework. The speed decision layer employs a maximum entropy-constrained proximal policy optimization (DMEPPO) reinforcement learning method, incorporating operational efficiency, energy consumption, safety, and smoothness as reward metrics to determine the optimal speed target. The speed control layer utilizes a Linear Matrix Inequality (LMI)-based robust control method for precise speed tracking. The experimental results demonstrate that the proposed DMEPPO achieved convergence after 2000 iterations and better learning performance, while the LMI-based controller achieved robust and responsive tracking. This architecture provides a theoretical foundation for speed decision control in agricultural vehicle cooperation scenarios. By considering aspects of speed decision-making control such as energy conservation, good solutions can be provided for the sustainable development of agriculture.

Background: In this study, an apple foam net packing machine is designed to improve the efficiency of apple foam net packing, reduce the intensity of manual work, and meet the market demand for diverse forms of apple packing. Methods: Based on the analysis of apple shape characteristics, a secondary posture adjustment method for apples with a vertical posture adjustment mechanism and a side posture adjustment mechanism is proposed. Based on the observation of human hand-set nets and the analysis of the mechanical characteristics of nets, a dual-system net opening method combining a net slackening system and a net opening system is proposed. Results: The experiment shows that: the apple foam net sleeve packing machine can reach 99% of the apple’s posture adjustment rate, the net opening rate can reach 99%, and the packing rate can reach 98.10%. The packing speed is 10 s/pcs, and the packing efficiency is 355–365 pcs/h. The length of the fused mesh net sleeve is mainly distributed between 138 and 143 mm, which accounts for approximately 80% of the total number of samples. Conclusions: The apples packed by this machine are neatly packaged according to specifications. It can improve the efficiency of apple foam net sleeve packing and replace manual work.