At present, container handling facilities are huge in size, low in automation, and complicated to operate, which are not suitable for applications in the limited spaces. Inspired by humans’ flexible collaboration when carrying a heavy and large object, in this article we devise a novel dual-forklift collaborative mechanism to address this problem. Specifically, we design a turn lock and hydraulic lifting structure to enable a rigid connection between each forklift and the target container, deploy a four-wheel steering structure in each forklift for omnidirectional motion, and construct a novel vision system by leveraging both RGB camera and time-of-flight depth camera. Furthermore, to provide visual feedback to the controller such that the dual forklift can connect, lift, and handle the container successfully, we devise a coarse-to-fine container detection and corner junction location model. Experiments demonstrate that our model outperforms representative models in terms of both precision and efficiency. Besides, the designed dual-forklift system can accomplish the handling tasks at narrow spaces, confirming its practical value in industrial applications.

The sampling-based RRT* algorithm has been extensively employed for path planning. The improved variant, F-RRT*, significantly reduces the initial cost by generating new nodes; however, it also leads to increased computational time and poses challenges in narrow passage environments. To address these issues, this paper proposes an improved F-RRT* algorithm based on the Generalized Voronoi Diagram (GVD), called GVDF-RRT*. First, a sparse sampling strategy based on GVD is proposed, which improves the sampling efficiency and reduces the initial sampling nodes and initial time by guiding the random tree to explore the space quickly through GVD nodes. At the same time, the success rate of planning in narrow passage environments is improved by equalizing the sampling probability of each channel in the map. Secondly, a node direct connection mechanism is established, which reduces the redundant computation and further reduces the initial time by hierarchical processing of creation nodes, while combined with the forward optimization mechanism to optimize the paths in iteration, effectively reducing the path cost. Finally, simulations in three test environments show that, compared to RRT*, Q-RRT*, and F-RRT*, the GVDFRRT* algorithm reduces the initial number of sampled nodes by 47.42%-76.57%, the initial time by 37.07%-86.00%, and the initial path cost by 0.47%-0.91%, while significantly improving the success rate in narrow passage environments. This further demonstrates that the proposed GVDF-RRT* significantly outperforms the baseline method in terms of initial performance and adaptability to narrow passage environments.

Inventory counting of logistics boxes in complex scenarios has always been a core task in intelligent logistics systems. To solve the problems of a high leakage rate and low computational efficiency caused by stacking, occlusion, and rotation in box detection against complex backgrounds in logistics environments, this paper proposes a lightweight, rotated object detection model: REW-YOLO (RepViT-Block YOLO with Efficient Local Attention and Wise-IoU). By integrating structural reparameterization techniques, the C2f-RVB module was designed to reduce computational redundancy in traditional convolutions. Additionally, the ELA-HSFPN multi-scale feature fusion network was constructed to enhance edge feature extraction for occluded boxes and improve detection accuracy in densely packed scenarios. A rotation angle regression branch and a dynamic Wise-IoU loss function were introduced to further refine localization and balance sample quality. Experimental results on the self-constructed BOX-data dataset demonstrate that the REW-YOLO achieves 90.2% mAP50 and 130.8 FPS, with a parameter count of only 2.18 M, surpassing YOLOv8n by 2.9% in accuracy while reducing computational cost by 28%. These improvements provide an efficient solution for automated box detection in logistics applications.

To address the issues of excessive sheet metal thinning and geometric deviation in single point incremental forming (SPIF), this paper proposed a bi-objective process parameter optimization framework for Al1060 sheet based on a multilayer perceptron (MLP) surrogate model and an improved multi-objective grey wolf optimization (IMOGWO) algorithm. Finite element simulations based on ABAQUS were conducted to generate a dataset considering variations in tool radius, initial sheet thickness, tool path strategy, step depth and forming angle. The trained MLP was used as the objective function in the optimization process to enable the rapid prediction of forming quality. The IMOGWO algorithm, enhanced by the Spm chaotic mapping initialization, an improved convergence coefficient updating mechanism and associative learning mechanism, was then employed to efficiently search for Pareto optimal solutions. For a truncated conical component case, optimal parameter sets were selected from the Pareto front via the entropy-weighted TOPSIS method for order preference by similarity to an ideal solution. Experimental verification showed close agreement with the simulated results, with relative errors of only 0.58% for the thinning rate and 3.10% for the geometric deviation. This validation demonstrates the feasibility and potential of the proposed method and its practical potential for improving the quality of SPIF forming.

To address the issues of traditional magnetorheological brakes (MRBs) lacking power-off braking, instantaneous self-locking and zero energy consumption pressure maintenance, a detachable permanent magnet and self-locking MRB (DPMSMB) was proposed in this paper. The embedded permanent magnets provide an inherent holding torque for fail-safe operation under power-off conditions. The dynamic range of the braking torque is broadened by tuning the coil current. A mathematical model of the braking torque was established based on the Herschel–Bulkley model. The magnetic field strength was calculated by coupling the reluctance of the coil and permanent magnets. A multi-objective Gray Wolf optimization algorithm was applied to the structural optimization of the DPMSMB, considering both structural compactness and braking performance under predefined design constraints. Experiments show that at 50 rpm, the permanent magnets generated a braking torque of 61.5 N·m independently, which increases to 135.2 N·m or decreases to 2.1 N·m when coupled with ±2.0 A current. The theoretical and experimental results consistently demonstrate that the DPMSMB can achieve power-off self-locking and real-time tuning of the braking torque. In addition, the detachable permanent magnet design effectively solves the problems associated with traditional fixed magnets when filling magnetorheological fluid (MRF), such as uneven filling and magnetic field interference, and alleviates the sedimentation phenomenon caused by long-term static MRF. This study presents a MRB featuring power-off self-locking and a broadened dynamic range for high-safety braking scenarios in mechanical systems.

Single-point incremental forming (SPIF) produces localized plastic deformation, resulting in thickness reduction, geometrical deviation, and microstructural evolution. To establish the relationship between forming quality and microstructural response, this study develops a cross-scale analysis framework integrating finite element simulation, Kocks–Mecking (K–M)-based statistically stored dislocation (SSD) density inference, metallographic observation and electron backscatter diffraction (EBSD) characterization. Applied to an Al 1060 truncated-cone part, the framework converts the simulated equivalent plastic strain (PEEQ) into SSD density via the K–M model calibrated using the Voce hardening model and the Taylor relation. The inferred SSD density distribution is then spatially correlated with thinning rate, geometrical deviation, grain size, grain-boundary misorientation, kernel average misorientation (KAM), and geometrically necessary dislocation (GND) density across different forming regions. The inferred SSD density rapidly approached a saturation level of 1.55 × 10¹³ m⁻², while the high-SSD density region progressively expanded during forming. This regional evolution was qualitatively consistent with the EBSD observations. The average grain size decreased from 30.4 μm to 21.9 μm, and the medium-angle grain-boundary fraction increased from 10.3% to 34.5%. Regionally, thickness reduction correlates strongly with PEEQ accumulation, SSD storage, and grain refinement, whereas geometrical deviation is more closely related to early-stage deformation heterogeneity. These findings provide a physically based route for predicting and controlling SPIF accuracy.