High precision navigation along specific paths is required for plant protection operations in dwarf and densely planted jujube orchards in southern Xinjiang. This study proposes a robotic path planning and navigation method for dense planting of red jujube orchards based on the improved A* and dynamic window approach (DWA) algorithms using Laser Radar to build maps. First, kinematic and physical robot simulation models are established; a map of the densely planted jujube orchard is constructed using Laser Radar. The robot’s position on the constructed map is described using an adaptive Monte Carlo positioning algorithm. Second, a combination of the improved A* and DWA algorithms is used to implement global and real-time local path planning; an evaluation function is used for path optimisation. The proposed path planning algorithm can accurately determine the robot’s navigation paths, with the average error U, average linear path displacement error, and L-shaped navigation being 2.69, 2.47, and 2.68 cm, respectively. A comparison experiment is set up in the specific path navigation section. The experimental results show that the improved fusion algorithm reduces the average navigation positioning deviation by 0.91cm and 0.54 cm when navigating L and U-shaped specific paths. The improved fusion algorithm is superior to the traditional fusion algorithm in navigation accuracy and navigation stability. It can improve the navigation accuracy of the dense planting jujube garden and provide a reference method for the navigation of the plant protection operation in the densely planted jujube orchards.

To solve the issue that the monocular vision vehicle navigation system is limited by the field of vision acquired by the charge-coupled device camera and cannot acquire navigation turning path information throughout the turning process, decreasing the vehicle turning control accuracy, this paper proposed a turning control algorithm based on monocular vision vehicle turning path prediction. Firstly, the camera’s distortion was adjusted. Secondly, the camera imaging model was built, and the turning path’s position information was determined using the imaging position relationship. The vehicle motion model was built in accordance with the vehicle steering mode. Lastly, the cornering trajectory of a vehicle was estimated using the vehicle’s front axle length and front-wheel adjustment data, determining the vehicle turning point and turn operations on the basis of the projected relationship between the vehicle turning track and the turning path position. The experimental results showed that the proposed algorithm can effectively measure the position parameters of the cornering path and complete vehicle cornering control. The maximum absolute error of intercept and slope in turn path position parameters were 0.2525 m and 0.014 m, respectively. The cornering control accuracy was 0.093 m and 0.085 m, which met the vehicle navigation cornering control requirements. At the same time, the research can provide theoretical reference for research on precise navigation control of other cornering vehicles and other path guidance modes.

In response to the growing need for efficient, stable, and non-destructive gripping in apple harvesting robots, this study proposes a novel rigid–flexible coupled end-effector. The design integrates an underactuated mechanism with a real-time force feedback control system. First, compression tests on ‘Red Fuji’ apples determined the minimum damage threshold to be 24.33 N. A genetic algorithm (GA) was employed to optimize the geometric parameters of the finger mechanism for uniform force distribution. Subsequently, a rigid–flexible coupled multibody dynamics model was established to simulate the grasping of small (70 mm), medium (80 mm), and large (90 mm) apples. Additionally, a harvesting experimental platform was constructed to verify the performance. Results demonstrated that by limiting the contact force of the distal phalange region silicone (DPRS) to 24 N via active feedback, the peak contact forces on the proximal phalange region silicone (PPRS) and middle phalange region silicone (MPRS) were effectively maintained below the damage threshold across all three sizes. The maximum equivalent stress remained significantly below the fruit’s yield limit, ensuring no mechanical damage occurred, with an average enveloping time of approximately 1.30 s. The experimental data showed strong agreement with the simulation, with a mean absolute percentage error (MAPE) of 5.98% for contact force and 5.40% for enveloping time. These results confirm that the proposed end-effector successfully achieves high adaptability and reliability in non-destructive harvesting, offering a valuable reference for agricultural robotics.

With the deep integration of 6G, the Internet of Things, and artificial intelligence, this paper proposes an intrusion detection and defense framework that combines robust AI kernel reconstruction, a cross-layer collaborative perception architecture, and a dynamic defense closed-loop mechanism to address advanced persistent threats and dynamically evolving attacks targeting next-generation consumer services. First, a lightweight detection model ATF-KDBC is designed based on adversarial training and online knowledge distillation. Gradient masking and noise injection are employed to enhance robustness against adversarial samples, while a drift-aware module enables adaptive optimization under concept drift scenarios. The model achieves accuracies of 99.25% and 99.84% on the NSL-KDD and IoT-23 hybrid datasets, respectively, and compresses the model size to 1.08 MB, representing a 97.6% reduction compared with the BERT teacher model. Second, a multidimensional attack chain analysis model is developed based on a STHGN. By integrating semantic, structural, and temporal features with a multi-head self-attention mechanism, the model enables cross-layer threat tracing and millisecond-level response, achieving an F1-score exceeding 97.0% on the DARPA dataset. Furthermore, this study explores the construction of a distributed CTIS network by integrating federated learning and blockchain technology. Zero-knowledge proofs are employed to ensure privacy preservation, while a Quality of Data and Quality of Model scoring mechanism enables efficient and precise deployment of defense strategies. Experimental results demonstrate that the proposed framework significantly outperforms traditional methods in terms of robustness, environmental adaptability, and computational efficiency, thereby providing both theoretical support and a technical pathway for enhancing the resilience and security of next-generation consumer services.