Spatial-temporal risk field-based coupled dynamic-static driving risk assessment and trajectory planning in weaving segments.

Accuracy of MRI compared with DSA for vascular mapping in SEEG trajectory planning.

Endoscopic Fenestration of Enlarging Symptomatic Thalamic Cysts: Twin Cases.

On-road evaluation of sickness-less motion planning in automated vehicles: 'Head motion first' helps!

Trajectory planning for cooperative on-orbit inspection over multiple waypoints

Deep brain stimulation (DBS) is a well-established therapy for adult neurological disorders, most commonly Parkinson's disease, and is increasingly being explored for medically refractory conditions in the pediatric population. Magnetic Resonance Imaging (MRI) is essential for DBS safety and efficacy through precise surgical targeting and trajectory planning, yet MRI protocols and reporting vary substantially and are constrained by pediatric-specific considerations. We aimed to systematically characterize MRI use and reporting practices in pediatric DBS studies and clinical trial registries. We systematically reviewed the published literature and the clinical trials registry to characterize MRI use in pediatric patients undergoing DBS, identify common imaging practices, and evaluate reporting of MRI sequence parameters (e.g., TR, TE). Preoperative MRI was primarily used for anatomical targeting and surgical planning. Most studies used 1.5T scanners (86%) versus 3T (14%), with T1-weighted (54%) and T2-weighted (53%) sequences most common. Despite MRI's ubiquity, 78% of studies did not report sequence parameters. However, only 4% were published in imaging-related specialty journals, which may explain the limited methodological detail. gov data reflected the same pattern, where DBS trials that mention imaging, rarely specify sequences or acquisition parameters. Heterogeneous MRI protocols and frequent under-reporting limit reproducibility and comparison of targeting approaches across pediatric DBS studies. We advocate for standardized MRI reporting guidelines to strengthen methodological rigour and accelerate collaborative progress in pediatric DBS research.

To address the issue of suboptimal masonry quality in wall-building robots operating within the viscoelastic contact environment of cement mortar, a multi-objective trajectory optimization method is proposed based on Kriging surrogate modeling and the Fractal Evolutionary Particle Swarm Optimization (FEPSO) algorithm in this paper. First, orthogonal experimental design is employed to obtain design variable values, with corresponding objective function values derived experimentally. A Kriging surrogate model linking the objective function to design variables is established to overcome the difficulty in constructing a viscoelastic mechanical model for cement mortar. Subsequently, integrating the Kriging surrogate model, a multi-objective trajectory optimization model for bricklaying is developed. The FEPSO algorithm is employed to solve this model, simultaneously enhancing masonry quality while optimizing other performance metrics. The FEPSO algorithm is compared with NSGA-II and MOPSO optimization algorithms, demonstrating its superiority. Then, the TOPSIS algorithm is applied to derive a compromise solution from the Pareto solution set, which is adopted as the optimal masonry scheme. Finally, the optimal masonry scheme is contrasted with the standard door-shaped trajectory planning method. Results indicate that trajectory optimization increased the wall-building robot's efficiency by 23.66%, reduced energy consumption by 29.33%, and improved trajectory smoothness by 90.47%. Concurrently, environmental contact force decreased by 7.03%, and masonry error decreased from 2.57 to 0.14mm. The proposed method enhances bricklaying quality and provides theoretical references and practical guidance for trajectory planning and construction quality control of similar intelligent construction robots.

Stereo-electroencephalography(SEEG) is a key technique for the presurgical evaluation of drug-resistant focal epilepsy [2]. Robotic assistance facilitates precise multi-trajectory stereotactic implantation and allows workflow standardization [1, 3, 5, 9]. We describe a reproducible image-based robotic SEEG implantation protocol and report our institutional experience. An image-based robot-assisted SEEG technique using the Neuromate® system combined with intraoperative 3D imaging is presented. The workflow includes hypothesis-driven trajectory planning, alphabetical trajectory sequencing, laser-verified stereotactic registration, trajectory-specific skull thickness measurement with depth-controlled drilling, reducer-guided bolt placement, and intraoperative imaging verification. Institutional procedural data were reviewed to illustrate workflow performance and safety. Sixty-eight patients underwent implantation of 952 SEEG depth electrodes (mean 14 electrodes per patient). Mean robotic implantation time was 198min (SD 54.9; range 80-280), corresponding to 14.1min per electrode. Mean stereotactic registration error was 1.7mm. Three patients (4.4%) developed intracranial hemorrhage, with one symptomatic case (1.47%) requiring surgical evacuation. This event occurred during electrode removal rather than implantation. No hemorrhage occurred during robotic electrode insertion, and no electrode repositioning or reintervention was required. Image-based robot-assisted SEEG enables accurate and reproducible multi-trajectory implantation with efficient workflow and low complication rates. Structured trajectory planning and systematic intraoperative verification may improve procedural safety and standardization.

Precise spatial distribution of interstitial needles is critical for 3D-printing-assisted brachytherapy in cervical cancer. This study proposes a greedy algorithm-based needle trajectory planning (GANTP) framework to generate patient-specific needle configurations while ensuring needle collision avoidance and achieving clinically acceptable high-risk clinical target volume (HR-CTV) coverage in compliance with OAR dose constraints. The GANTP framework comprises three core steps: (1) Generation of candidate trajectories anchored within clinically viable entry zones; (2) Parameter-driven greedy selection of needle trajectories based on a geometric influence radius (δ) evaluated at three discrete values (12, 15, and 18mm), where δ serves as a geometric surrogate for dose coverage, together with a geometric coverage-ratio threshold (γ = 98%) and a collision-free margin (d) relative to the tandem; and (3) Dosimetric evaluation and inverse planning with dwell-time optimization. The framework was evaluated using CT datasets from 20 cervical cancer patients. Performance metrics, including HR-CTV coverage, organs-at-risk (OAR) doses (D2cc), needle counts, and efficiency, were compared against manual planning. GANTP was able to generate clinically acceptable plans for all 20 cases. Based on a final-selection strategy that prioritized clinically acceptable HR-CTV coverage (≥ 90%) and the lowest needle count among the evaluated δ settings, δ = 15mm was selected for 16 patients and δ = 18mm for 4 patients as the final selected configurations. Compared to manual planning (HR-CTV coverage: 92.62 ± 1.51%), these Final Selected plans achieved clinically acceptable coverage of 91.96 ± 1.24% (P = 0.024), consistently exceeding the 90% clinical threshold. The OAR sparing was no significant difference to manual planning: D2cc for the rectum (66.11 ± 3.99Gy vs. 66.46 ± 4.00Gy, P = 0.542), bladder (78.28 ± 5.16Gy vs. 79.45 ± 4.47Gy, P = 0.201), and sigmoid (63.30 ± 4.86Gy vs. 62.33 ± 6.84Gy, P = 0.916). The algorithm significantly reduced the average number of needles from 5.40 ± 0.94 to 4.25 ± 0.55 (P < 0.001). The most substantial improvement was observed in one case (Patient 2), where the needle count was reduced from 7 to 4 while maintaining a coverage of 91.7%. The total planning workflow time was substantially reduced from 2 to 3h (manual) to 8.2 ± 1.4min (GANTP), with algorithm execution taking less than 190s across all δ settings. GANTP establishes a semi-automated, patient-specific framework for generating collision-free, non-coplanar trajectories that meet clinical dosimetric goals with a reduced mean number of needles. Integrated with 3D-printed templates, this approach demonstrates significant potential for improving the precision and efficiency of interstitial brachytherapy. Future work will include phantom experiments for physical validation.

The road friction coefficient is a key parameter for traffic safety and for advanced driver-assistance systems (ADAS) such as electronic stability control and trajectory planning in autonomous vehicles. Most existing estimation methods rely on dynamic maneuvers, whereas friction estimation during steering at standstill and very low speeds has received limited attention. This paper addresses this gap by introducing two novel friction estimation approaches based on steering torque in standstill and low-speed conditions. The first method employs a Kalman–Bucy filter (KBF) coupled with a simplified brush model, using a single tread element formulation to determine when estimation should be updated or halted. The second method applies an unscented Kalman filter (UKF) to an extended torsional spring model that incorporates a damping term for low-speed maneuvers, while parametric output sensitivity (POS) analysis is used to assess identifiability. Both approaches are compared to an existing method from the literature and are validated in simulation and with experimental data from three vehicles of varying complexity. The results demonstrate accurate and consistent friction estimation during steering at standstill and slow rolling maneuvers, extending the applicability of effect-based methods beyond conventional dynamic driving scenarios.

ABSTRACT This research explores how a Palestinian middle-class neighborhood in the mixed city of Haifa has been perceived by its residents over the past decade, situating these perceptions within a broader sociopolitical and urban context shaped by ethnonational power relations. Drawing on questionnaires and interviews, it examines residents’ satisfaction, their intentions to move, and their engagement with municipal policies and neighborhood development processes. The findings reveal a tension between class position and ethno-national identity that constrains their spatial mobility. This dynamic is embedded in Haifa’s urban structure and the neighborhood’s connection to the historic Palestinian urban network, which continues to influence its planning trajectory. In-depth interviews with neighborhood committee members and municipal representatives further illuminate how residents interpret spatial trends and municipal policy in the city. Together, the results demonstrate how urban policies and sociopolitical power relations are reflected in residents’ lived experiences, contributing to the critical urban literature on marginalized middle-class neighborhoods.

Retraction Note: Reinforcement learning-driven deep learning approaches for optimized robot trajectory planning

This study aimed to evaluate the effectiveness of artificial intelligence (AI)-based pedicle screw trajectory planning combined with robotic-assisted screw placement in patients with lumbar degenerative disease (LDD) and low bone mass, based on a multicenter study. This retrospective study included patients with LDD and low bone mass, defined as a bone mineral density of 40-120mg/cm3 measured by quantitative computed tomography, a range previously shown to benefit from AI-assisted screw trajectory planning. All patients underwent open posterior lumbar fusion between October 2022 and February 2023 and were categorized according to surgical technique into the AI-assisted (AI) group, which used AI-based planning with robotic-assisted screw placement, or the free-hand (FH) group, in which screws were placed manually. Clinical and radiographic outcomes were compared between the two groups. A total of 90 patients were included, with 42 in the AI group and 48 in the FH group. The mean follow-up duration was 29.7 months. Compared with the FH group, the AI group achieved a higher proportion of Grade A screw position and a lower rate of screw loosening. The AI group showed better preservation of intervertebral space height at final follow-up and shorter bone graft fusion time. Both groups showed significant postoperative improvements in Visual Analog Scale (VAS) and Oswestry Disability Index (ODI) scores, and the AI group exhibited significantly lower VAS scores for low back pain and ODI scores at final follow-up. AI-assisted pedicle screw trajectory planning combined with robotic guidance improves screw placement accuracy, preserves intervertebral space height, accelerates bone graft fusion, and enhances clinical outcomes in patients with LDD and low bone mass.

Laser interstitial thermal therapy (LITT) is a novel and effective treatment for malignant glioma patients who could not undergo surgical resection. Preoperative planning for better tumor coverage and less probe use is a critical step of LITT's success, which can be challenging for surgeons as different constraints need to be considered. Here we proposed an automatic algorithm to plan trajectory combination for LITT, extending previous studies on LITT that used only one probe for treatment. Furthermore, we combined iterative optimization with Lagrangian relaxation and thus achieved both mathematic optimality and solving efficiency, which existing ablation planning research may fail to balance. The planning algorithm was evaluated in 16 cases of tumors and was compared with surgeon's planning result. In all cases our planning result achieved an average ablation rate of 99.83% and satisfied multiple constraints, outperforming the manual planning in probe usage and extent of ablation. By solving the relaxation model, our proposed method proved to be capable of reducing the number of probes to minimum with an average time cost of 39.73 seconds.

To overcome the inherent limitations of conventional offline programming in adapting to dimensional deviations and assembly-induced errors during robotic welding of ship structures, this paper proposes a point-cloud-enhanced visual scanning paradigm that enables automatic weld seam identification and collision-free trajectory planning. A dedicated monochromatic vision system is rigidly integrated onto a six-axis industrial robot, enabling high-fidelity feature extraction and geometric contour reconstruction for the precise localization of multi-configuration weld seams. The proposed approach substantially reduces manual teaching operations, enhances environmental adaptability in unstructured shipbuilding workshops, and improves global positioning accuracy. The core technical contributions are threefold: (1) systematic design and precision calibration of the integrated robotic vision system, including a hand–eye calibration procedure; (2) development of a hybrid 2D image-3D point cloud processing pipeline that combines SURF and FLANN for image stitching with RANSAC-based plane segmentation and PCA-driven contour reconstruction; and (3) extensive experimental validation across five distinct workpiece configurations. These results confirm the system’s strong applicability for intelligent and efficient shipbuilding welding, significantly outperforming conventional offline programming, which exhibits deviations exceeding 5 mm under identical conditions. Quantitative error analysis demonstrates that the online recognition method achieves a weld localization root mean square error (RMSE)of 0.82 mm, a standard deviation of 0.45 mm, and a verified maximum absolute deviation of 1.5 mm.

For precision assembly tasks, the accuracy and efficiency of robotic arm trajectory planning directly impact product quality and production efficiency in manufacturing, making it a core technology driving industrial automation upgrades. This research endeavors to establish a sophisticated multi-objective trajectory planning model, specifically engineered to cater to the intricate demands of precision assembly scenarios. The model optimizes for "maximum efficiency, minimum energy consumption, and minimal impact," quantifying time costs, energy expenditure, and the influence of mechanical impact on assembly precision during the process. To enhance the performance of traditional multi-objective particle swarm optimization (MOPSO), this study proposes an improved CEMOPSO algorithm. This approach enhances initial population diversity by incorporating Chebyshev mapping strategies, dynamically adjusts particle search directions through evolutionary elimination mechanisms, and optimizes constraint handling capabilities via a designed infeasibility evaluation function. Engineering experiments using pyrotechnic grain assembly as a typical scenario validate CEMOPSO's practical application value. Implementing this algorithm increased robotic arm assembly efficiency by 15.2%, reduced energy consumption by 20.4%, and decreased impact by 26.4%. This demonstrates the effectiveness and engineering applicability of the theoretical methods developed in this study for complex precision assembly tasks.

Connected and automated vehicle (CAV) platoons provide significant advantages in enhancing traffic efficiency and safety through vehicle-to-vehicle cooperative driving. However, owing to the uncertainty of human-driven vehicles in mixed traffic environments, platoons must frequently split to avoid potential collisions and merging is required to maintain platoon following. To address this challenge, this paper proposes a cooperative control architecture for CAV platoons that includes a single-vehicle cruising control mode and a platoon-following control mode, enabling independent operation of each mode and discrete event transitions around split and merge maneuvers. In single-vehicle mode, a driving safety potential field model is proposed for collision-avoidance trajectory planning, and a distributed model predictive control algorithm is designed to achieve the distinct control objectives of the two modes. Then, a long short-term memory (LSTM) neural network and fuzzy logic are combined to predict collision risk and determine platoon split events. A cooperative control system is implemented to ensure continuous control and flexible switching between the two modes. Finally, joint simulations in PreScan, CarSim, and MATLAB/Simulink were conducted to evaluate the performance of the system across various obstacle scenarios. The results demonstrate that the proposed control architecture effectively coordinates vehicle maneuvers and adapts platoon formation to changes in traffic conditions.

The rapid evolution of 5G and emerging 6G networks has increased the demand for wireless communication systems that deliver high capacity, low latency, and adaptability. However, conventional terrestrial infrastructure remains costly and inflexible, particularly in dynamic or remote environments. This article develops a new Federated Reinforcement Learning (FRL)-based UAV communication system using Selective Entropy-Fused Proximal Policy Optimization (SEF-PPO) is proposed to enhance the performance of locally-on-policy learning in real-time decision-making environments. In contrast to existing digital twin or offline-trained deep reinforcement learning (DRL) methods, the proposed solution eliminates the need for replay buffers, thereby reducing memory and computational requirements for UAV platforms. UAVs learn collaboratively while preserving data privacy and maintaining robustness to non-IID user distributions through federated aggregation with a High-Altitude Platform (HAP). The framework integrates trajectory planning, user association, energy-efficient resource allocation, and handover management within a unified adaptive architecture. Experimental results demonstrate significant improvements in throughput, fairness, latency, and energy efficiency compared with baseline methods, including DMTD, DRL-EC3, and greedy and random algorithms. Overall, the proposed design enables scalable, energy-aware, and environment-responsive UAV coordination, offering a deployment-ready solution for next-generation wireless networks without requiring simulation-based pretraining.

Transsulcal parafascicular approach for resection of a brain metastasis using a syringe-based tubular system: a technical video demonstration

Robotic drug grasping in complex smart pharmacy environments requires accurate detection and efficient execution, yet existing methods struggle with clutter, overlapping, and small target objects. To improve robotic grasping of chaotic and variably shaped drugs, we propose a novel multi-stage framework that integrates enhanced perception, grasp detection, and trajectory planning. First, images are preprocessed with an improved Super-Resolution Convolutional Neural Network (SRCNN) to enhance input quality. Next, drug segmentation is performed using our YOLO-EASB instance segmentation algorithm (YOLOv5+E-A-SPPFCSPC+BIFPNC), and the most suitable targets are identified by evaluating mask completeness. The segmented drugs are then processed by our improved Adaptive Feature Fusion and Grasp-Aware Network (IAFFGA-Net) with an optimized loss function, ensuring robust grasp detection in cluttered environments. For execution, we combine improved Particle Swarm Optimization and 3-5-3 interpolation to generate efficient and smooth robotic arm movements. Finally, the system is deployed on an adaptive collaborative robot capable of adjusting to diverse production environments. Experiments on our custom dataset demonstrate 97.3% drug recognition accuracy, while chaotic drug grasping tests achieved at least 80% success, satisfying the requirements of intelligent pharmacies.