Simultaneous localization and mapping (SLAM) is one of the most attractive research hotspots in the field of robotics, and it is also a prerequisite for the autonomous navigation of robots. It can significantly improve the autonomous navigation ability of mobile robots and their adaptability to different application environments and contribute to the realization of real-time obstacle avoidance and dynamic path planning. Moreover, the application of SLAM technology has expanded from industrial production, intelligent transportation, special operations and other fields to agricultural environments, such as autonomous navigation, independent weeding, three-dimensional (3D) mapping, and independent harvesting. This paper mainly introduces the principle, system framework, latest development and application of SLAM technology, especially in agricultural environments. Firstly, the system framework and theory of the SLAM algorithm are introduced, and the SLAM algorithm is described in detail according to different sensor types. Then, the development and application of SLAM in the agricultural environment are summarized from two aspects: environment map construction, and localization and navigation of agricultural robots. Finally, the challenges and future research directions of SLAM in the agricultural environment are discussed.

Facility agriculture is an essential carrier for promoting stable production and supply. In 2020, the planting area of facility agriculture in Beijing (290098000 m²) accounted for 29.06% of the total planting area of crops (998078000 m²), and the output value accounted for 46.56%. In 2022, Beijing Agricultural Technology Extension Station organized relevant departments to summarize and evaluate the agricultural facilities in Beijing through consultation materials, interviews, questionnaires, and field trips, combining survey data and statistical data to draw the following conclusions. Facilities play a major supporting role in stabilizing production and ensuring supply. The number of traditional greenhouses is extensive and covers a large area, so special planning and classification upgrades are urgently needed. Facilities are rich in scientific and technological resources, but the mode of production is out of date. It is of great significance to improve the comprehensive production capacity of facility agriculture and promote the healthy and stable development of facility industry in Beijing to increase the utilization rate of facility agriculture land, strengthen the support of facility science and technology, and cultivate the socialized service organization of facility.

Realtime analyzing the feeding behavior of fish is the premise and key to accurate guidance on feeding. The identification of fish behavior using a single information is susceptible to various factors. To overcome the problems, this paper proposes an adaptive deep modular co-attention unified multi-modal transformers (DMCA-UMT). By fusing the video, audio and water quality parameters, the whole process of fish feeding behavior could be identified. Firstly, for the input video, audio and water quality parameter information, features are extracted to obtain feature vectors of different modalities. Secondly, deep modular co-attention (DMCA) is introduced on the basis of the original cross-modal encoder, and the adaptive learnable weights are added. The feature vector of video and audio joint representation is obtained by automatic learning based on fusion contribution. Finally, the information of visual-audio modality fusion and text features are used to generate clip-level moment queries. The query decoder decodes the input features and uses the prediction head to obtain the final joint moment retrieval, which is the start-end time of feeding the fish. The results show that the mAP Avg of the proposed algorithm reaches 75.3%, which is 37.8% higher than that of unified multi-modal transformers (UMT) algorithm.

Aquatic medicine knowledge graph is an effective means to realize intelligent aquaculture. Graph completion technology is key to improving the quality of knowledge graph construction. However, the difficulty of semantic discrimination among similar entities and inconspicuous semantic features result in low accuracy when completing aquatic medicine knowledge graph with complex relationships. In this study, an aquatic medicine knowledge graph completion method (TransH+HConvAM) is proposed. Firstly, TransH is applied to split the vector plane between entities and relations, ameliorating the poor completion effect caused by low semantic resolution of entities. Then, hybrid convolution is introduced to obtain the global interaction of triples based on the complete interaction between head/tail entities and relations, which improves the semantic features of triples and enhances the completion effect of complex relationships in the graph. Experiments are conducted to verify the performance of the proposed method. The MR, MRR and Hit@10 of the TransH+HConvAM are found to be 674, 0.339, and 0.361, respectively. This study shows that the model effectively overcomes the poor completion effect of complex relationships and improves the construction quality of the aquatic medicine knowledge graph, providing technical support for intelligent aquaculture.

In the process of aquaculture, monitoring the number of fish bait particles is of great significance to improve the growth and welfare of fish. Although the counting method based on onvolutional neural network (CNN) achieve good accuracy and applicability, it has a high amount of parameters and computation, which limit the deployment on resource-constrained hardware devices. In order to solve the above problems, this paper proposes a lightweight bait particle counting method based on shift quantization and model pruning strategies. Firstly, we take corresponding lightweight strategies for different layers to flexibly balance the counting accuracy and performance of the model. In order to deeply lighten the counting model, the redundant and less informative weights of the model are removed through the combination of model quantization and pruning. The experimental results show that the compression rate is nearly 9 times. Finally, the quantization candidate value is refined by introducing a power-of-two addition term, which improves the matches of the weight distribution. By analyzing the experimental results, the counting loss at 3 bit is reduced by 35.31%. In summary, the lightweight bait particle counting model proposed in this paper achieves lossless counting accuracy and reduces the storage and computational overhead required for running convolutional neural networks.

Sea cucumber detection is widely recognized as the key to automatic culture. The underwater light environment is complex and easily obscured by mud, sand, reefs, and other underwater organisms. To date, research on sea cucumber detection has mostly concentrated on the distinction between prospective objects and the background. However, the key to proper distinction is the effective extraction of sea cucumber feature information. In this study, the edge-enhanced scaling You Only Look Once-v4 (YOLOv4) (ESYv4) was proposed for sea cucumber detection. By emphasizing the target features in a way that reduced the impact of different hues and brightness values underwater on the misjudgment of sea cucumbers, a bidirectional cascade network (BDCN) was used to extract the overall edge greyscale image in the image and add up the original RGB image as the detected input. Meanwhile, the YOLOv4 model for backbone detection is scaled, and the number of parameters is reduced to 48% of the original number of parameters. Validation results of 783 images indicated that the detection precision of positive sea cucumber samples reached 0.941. This improvement reflects that the algorithm is more effective to improve the edge feature information of the target. It thus contributes to the automatic multi-objective detection of underwater sea cucumbers.

The personalized recommendation of the cloud platform for agricultural knowledge and agricultural intelligent service is one of the core technologies for the development of smart agriculture. Revealing the implicit laws and dynamic characteristics of agricultural knowledge demand is a key problem to be solved urgently. In order to enhance the matching ability of knowledge recommendation and service in human-computer interaction of cloud platform, the mechanism of agricultural knowledge intelligent recommendation service integrated with context-aware model was analyzed. By combining context data acquisition, data analysis and matching, and personalized knowledge recommendation, a framework for agricultural knowledge recommendation service is constructed to improve the ability to extract multidimensional information features and predict sequence data. Using the cloud platform for agricultural knowledge and agricultural intelligent service, this research aims to deliver interesting video service content to users in order to solve key problems faced by farmers, including planting technology, disease control, expert advice, etc. Then the knowledge needs of different users can be met and user satisfaction can be improved.

Vegetable production in the open field involves many tasks, such as soil preparation, ridging, and transplanting/sowing. Different tasks require agricultural machinery equipped with different agricultural tools to meet the needs of the operation. Aiming at the coupling multi-task in the intelligent production of vegetables in the open field, the task assignment method for multiple unmanned tractors based on consistency alliance is studied. Firstly, unmanned vegetable production in the open field is abstracted as a multi-task assignment model with constraints of task demand, task sequence, and the distance traveled by an unmanned tractor. The tight time constraints between associated tasks are transformed into time windows. Based on the driving distance of the unmanned tractor and the replacement cost of the tools, an expanded task cost function is innovatively established. The task assignment model of multiple unmanned tractors is optimized by the consensus based bundle algorithm (CBBA) with time windows. Experiments show that the method can effectively solve task conflict in unmanned production and optimize task allocation. A basic model is provided for the cooperative task of multiple unmanned tractors for vegetable production in the open field.

The increasing trend towards independent fruit packaging demands a high appearance quality of individually packed fruits. In this paper, we propose an improved YOLOv5-based model, YOLO-Banana, to effectively grade banana appearance quality based on the number of banana defect points. Due to the minor and dense defects on the surface of bananas, existing detection algorithms have poor detection results and high missing rates. To address this, we propose a density-based spatial clustering of applications with noise (DBSCAN) and K-means fusion clustering method that utilizes refined anchor points to obtain better initial anchor values, thereby enhancing the network’s recognition accuracy. Moreover, the optimized progressive aggregated network (PANet) enables better multi-level feature fusion. Additionally, the non-maximum suppression function is replaced with a weighted non-maximum suppression (weighted NMS) function based on distance intersection over union (DIoU). Experimental results show that the model’s accuracy is improved by 2.3% compared to the original YOLOv5 network model, thereby effectively grading the banana appearance quality.

Peach aphid is a common pest and hard to detect. This study employs hyperspectral imaging technology to identify early damage in green cabbage caused by peach aphid. Through principal component transformation and multiple linear regression analysis, the correlation relation between spectral characteristics and infestation stage is analyzed. Then, four characteristic wavelength selection methods are compared and optimal characteristic wavelengths subset is determined to be input for modelling. One linear algorithm and two nonlinear modelling algorithms are compared. Finally, support vector machine (SVM) model based on the characteristic wavelengths selected by multi-cluster feature selection (MCFS) acquires the highest identification accuracy, which is 98.97%. These results indicate that hyperspectral imaging technology have the ability to identify early peach aphid infestation stages on green cabbages.