Search Results (717)

With the rapid development of complex engineering systems, many real-world optimization problems are characterized by high dimensionality, strong nonlinearity, and variable coupling. To address these challenges, this paper proposes a Public Management–Augmented Multi-Strategy Adaptive Enterprise Development Optimization algorithm (PMAED), which integrates adaptive differential evolution, an eigen-based rotated search strategy, and a hierarchical performance governance mechanism to enhance convergence efficiency and robustness. Experimental results on the CEC2020 and CEC2022 benchmark suites demonstrate that PMAED achieves superior performance across different problem types and dimensionalities. In the Friedman ranking test, PMAED consistently obtains the best average rank (1.90 and 1.60 on CEC2020; 2.00 and 1.92 on CEC2022 for 10D and 20D, respectively), outperforming all compared algorithms. The Wilcoxon rank-sum test further confirms that PMAED achieves statistically significant improvements on the majority of benchmark functions. In high-dimensional scenarios, PMAED shows remarkable optimization accuracy, for example, achieving a mean fitness value of 1.15 × 10³ on the 20-dimensional CEC2020 F1 function, significantly outperforming classical methods. In addition, PMAED is applied to a three-dimensional UAV path planning problem. The results show that the proposed method achieves the lowest average path cost (277.62) and the smallest standard deviation among all algorithms, indicating superior stability and reliability. The planned paths are smoother, safer, and more efficient compared to those generated by other methods. Overall, the proposed PMAED provides a robust and efficient solution for complex continuous optimization problems and demonstrates strong potential for real-world engineering applications. Full article

Addressing high dynamics, stringent non-holonomic constraints, and limited onboard computation in cooperative online trajectory planning for multiple fixed-wing UAVs in complex 3D obstacle environments, this paper proposes a Cooperative-3D-Quick-Dubins-RRT*. First, an offline motion-primitive database is engineered to align with RRT* mechanics: an unconstrained expansion mode facilitates rapid space exploration, while a constrained rewiring mode ensures kinodynamic continuity. This architecture, synergized with four targeted acceleration strategies (dimensionality reduction, elliptical sampling, tree pruning, and pre-discretized collision checking), significantly accelerates convergence. Second, a Dubins-detour-based time-coordination mechanism is designed to map cooperative timing constraints into controllable path-length adjustments, and the feasible adjustment range is analyzed to ensure realizability. Finally, simulations and hardware-in-the-loop experiments across a variety of representative scenarios are conducted for validation. The results show that, compared with the classical Dubins-RRT*, the proposed method achieves clear advantages in planning time and path length, demonstrating its suitability for online cooperative obstacle-avoidance planning of multiple UAVs. Full article

To address the inefficiency of the long single-fruit grasping cycle in traditional fruit harvesting robots, this study proposes a collision-free continuous harvesting solution for cucumber cultivation scenarios, coupled with a customized robotic system equipped with a continuous harvesting end-effector. In terms of visual perception, the YOLOv8n model is enhanced by integrating the GhostNet lightweight architecture, the Context-Guided Fusion Module (CGFM), and the MPDIoU loss function. Ablation experiments confirm the optimal model configuration, and the optimized model achieves a reduced model size of 5.3 MB and computational load of 6.6 GFLOPs while improving the mean average precision (mAP@50) by 2.5%, which facilitates low-cost deployment. For path planning, an Enhanced Bézier Continuous Picking (EBCP) algorithm is developed by combining 3D Gaussian kernel modeling and cubic Bézier curves to generate collision-free continuous trajectories. Simulation and practical experiments demonstrate that the path length of the proposed continuous picking method is only 31.1% that of the traditional path, with a theoretical collision-free rate of 96.69% and an actual collision-free rate of 92.24%. The feasibility and effectiveness of the proposed system are fully verified, providing a technical reference for the continuous operation of fruit harvesting robots. Full article

Highly deviated wells commonly exhibit large errors in horizon calibration because the logging path follows an inclined borehole trajectory, whereas post-stack seismic processing effectively treats wave propagation as vertical. This mismatch has received limited attention. Here, we performed horizon calibration and velocity-model building for highly deviated wells drilled in the Mahu Sag, Junggar Basin, and obtained three key findings. First, the assumed vertical travel path in post-stack data is the primary cause of the initial mis-tie for highly deviated wells. Second, calibration in the deviated interval requires a strategy distinct from that of vertical wells and may involve substantial stretching or squeezing of the original logs to achieve a consistent time-depth relationship. Third, the map-view projection of a highly deviated well is essentially linear; relative to vertical wells, it provides denser in situ velocity constraints and, with pseudo-well control, supplies 2D velocity information along the well-trajectory plane, thereby improving velocity-field modeling. Validation against drilling data showed that this workflow improved well ties and refined the velocity model, providing practical guidance for geological well planning and reducing drilling risk. Full article

The paper introduces a computationally efficient semantic-aware route planning framework for indoor mobile robots, designed for real-time execution on resource-constrained edge hardware (Raspberry Pi 5, CPU-only). The proposed architecture fuses monocular object detection with 2D LiDAR-based range estimation and integrates the resulting semantic annotations into the Nav2 Route Server for penalty-weighted route selection. Object localization in the map frame is achieved through the Angular Sector Fusion (ASF) pipeline, a deterministic geometric method requiring no parameter tuning. The ASF projects YOLO bounding boxes onto LiDAR angular sectors and estimates the object range using a 25th-percentile distance statistic, providing robustness to sparse returns and partial occlusions. All intrinsic and extrinsic sensor parameters are resolved at runtime via ROS 2 topic introspection and the URDF transform tree, enabling platform-agnostic deployment. Detected entities are classified according to mobility semantics (dynamic, static, and minor) and persistently encoded in a GeoJSON-based semantic map, with these annotations subsequently propagated to navigation graph edges as additive penalties and velocity constraints. Route computation is performed by the Nav2 Route Server through the minimization of a composite cost functional combining geometric path length with semantic penalties. A reactive replanning module monitors semantic cost updates during execution and triggers route invalidation and re-computation when threshold violations occur. Experimental evaluation over 115 navigation segments (legs) on three heterogeneous robotic platforms (two single-board RPi5 configurations and one dual-board setup with inference offloading) yielded an overall success rate of 97% (baseline: 100%, adaptive: 94%), with 42 replanning events observed in 57% of adaptive trials. Navigation time distributions exhibited statistically significant departures from normality (Shapiro–Wilk, p < 0.005). While central tendency differences between the baseline and adaptive modes were not significant (Mann–Whitney U, p = 0.157), the adaptive planner reduced temporal variance substantially (σ = 11.0 s vs. 31.1 s; Levene’s test W = 3.14, p = 0.082), primarily by mitigating AMCL recovery-induced outliers. On-device YOLO26n inference, executed via the NCNN backend, achieved 5.5 ± 0.7 FPS (167 ± 21 ms latency), and distributed inference reduced the average system CPU load from 85% to 48%. The study further reports deployment-level observations relevant to the Nav2 ecosystem, including GeoJSON metadata persistence constraints, graph discontinuity (“path-gap”) artifacts, and practical Route Server configuration patterns for semantic cost integration. Full article

To address unstable localization and sparse mapping for autonomous vehicles operating in GPS-denied and low-visibility environments, this paper proposes GTS-SLAM, a tightly coupled dense visual SLAM framework integrating Generalized Iterative Closest Point (GICP) and 3D Gaussian Splatting (3DGS). The system is designed for intelligent driving platforms such as underground mining vehicles, inspection robots, and tunnel autonomous navigation systems. The front-end performs covariance-aware point-cloud registration using GICP to achieve robust pose estimation under low texture, dust interference, and dynamic disturbances. The back-end employs probabilistic dense mapping based on 3DGS, combined with scale regularization, scale alignment, and keyframe factor-graph optimization, enabling synchronized optimization of localization and mapping. A Compact-3DGS compression strategy further reduces memory usage while maintaining real-time performance. Experiments on public datasets and real underground-like scenarios demonstrate centimeter-level trajectory accuracy, high-quality dense reconstruction, and real-time rendering. The system provides reliable perception capability for vehicle autonomous navigation, obstacle avoidance, and path planning in confined and weak-light environments. Overall, the proposed framework offers a deployable solution for autonomous driving and mobile robots requiring accurate localization and dense environmental understanding in challenging conditions. Full article

Firefighters must locate victims reliably to carry out rescue operations within burning structures during urban firefighting events. Low visibility, reduced oxygen levels, weakened structural rigidity, and dense smoke make it difficult to locate victims. In addition to these challenges, victims may be unconscious and unable to report their locations to firefighters. This research work explores the Double Deep Q-Network (Double DQN), Dueling Deep Q-Network (Dueling DQN), and Dueling Double Deep Q-Network (D3QN) agents for an unmanned aerial vehicle (UAV) to navigate around a structure and locate trapped victims within it. The UAV’s position, Light Detection and Ranging (LiDAR), and infrared camera data are utilized as inputs for the Deep Q-Networks. The PER is used to store transitions and sample them according to priority for training. Python’s Pygame library is used in this research to create a simulated environment in which infrared camera and LiDAR data are simulated. The performance of the UAV agent is evaluated using cumulative maximum reward, reward distribution histogram, Temporal Difference (TD) error over time, and number of successful episodes. Among the three DQN UAV agents, the Dueling DQN and Double DQN have potential for real-world applications in firefighting. Full article

Aiming at the inherent defects of the Horned Lizard Optimization Algorithm (HLOA), such as insufficient global exploration capability, premature convergence to local optima, and inadequate balance between exploration and exploitation, this paper proposes an enhanced Improved Horned Lizard Optimization Algorithm (IHLOA) integrated with multi-strategy improvements. Firstly, the Fuch chaotic mapping is introduced for population initialization, which enhances the ergodicity and diversity of the initial population by leveraging the pseudo-random and aperiodic characteristics of chaotic sequences, laying a high-quality foundation for subsequent optimization searches. Secondly, the golden sine strategy is embedded into the iterative update process to dynamically adjust the search step size and direction. This strategy utilizes the periodic amplitude variation in the sine function and the golden section coefficient to balance the global exploration for potential optimal regions and local exploitation for refined optimization, thereby accelerating convergence speed while avoiding local stagnation. Finally, the orthogonal crossover strategy is incorporated in the late iteration stage to promote effective information interaction between parent and offspring populations. By means of chromosome segment exchange and elitist retention mechanisms, this strategy reduces dimensional search blind spots and further enhances the algorithm’s ability to capture high-quality solutions. Comprehensive experimental evaluations are conducted based on classical benchmark test functions and eight state-of-the-art meta-heuristic algorithms. The results demonstrate that the IHLOA outperforms comparative algorithms in terms of optimization accuracy, convergence speed, and stability across 30-D, 50-D, and 80-D scenarios. For practical path planning applications, the IHLOA achieves remarkable performance improvements: in single-goal path planning, it reduces the path length by 2.54–87.64% compared with benchmark algorithms; in multi-goal path planning, it realizes a 1.24–7.99% reduction in path length and an 11.91% average reduction in the number of turning points relative to the original HLOA. Additionally, the IHLOA exhibits excellent robustness and adaptability in dynamic obstacle environments, effectively shortening the path length and reducing robot stuck times. This research not only enriches the improvement framework of meta-heuristic algorithms but also provides a high-efficiency optimization solution for mobile robot path planning in complex environments. Full article

Wing–diesel hybrid ships are a practical approach to sustainable maritime transport that harnesses wind energy to supplement diesel propulsion and reduce carbon emissions. The core optimization problem addressed in this study is the global energy efficiency optimization of path planning and propulsion system cooperative control for wing–diesel hybrid ships under two typical sail operation statuses (sail-deployed and sail-stowed) with dynamic changes in complex maritime meteorological and hydrological conditions. To address this issue, this paper proposes a global energy efficiency optimization framework based on an improved Deep Q-Network (DQN) and D*Lite algorithm. Firstly, the D*Lite algorithm is reconstructed with an incremental replanning mechanism and risk-aware cost function to generate real-time safe path constraints. Secondly, the DQN is improved by adopting a dueling network, noisy exploration and prioritized experience replay, and a differentiated reward function dynamically weighted by sail statuses is designed for it. Finally, a fuel consumption prediction model based on the gradient boosting algorithm is integrated into the reward function to realize an accurate energy efficiency assessment. Empirical results confirm that the framework achieves remarkable carbon reduction effects: the optimized routes reduce the total fuel consumption by 5.02%, cut carbon dioxide emissions by 140.66 tons, and improve the energy efficiency operational index by 7.50%. This framework provides an effective technical solution for the dynamic energy efficiency optimization of wing–diesel hybrid ships under different sail operation statuses. Full article

Older adults often need guidance when visiting new buildings for the first time. However, indoor navigation remains challenging due to the lack of Global Positioning System (GPS) availability, visually repetitive corridors, and frequent location failures. This article presents a multimodal indoor navigation assistant that combines graph-based route planning with visual landmark verification to provide step-by-step guidance. The environment is modelled as a directed graph whose nodes are annotated with semantic landmarks, and the graph is constructed primarily from a video of the building, reducing the need for 3D scanners, beacons, or other specialised instruments. Routes are calculated using Dijkstra’s shortest-path algorithm over the semantic graph. During navigation, camera frames are analysed using a restricted vision-language recognition strategy that only considers candidate landmarks from the current and next nodes, reducing false detections and improving interpretability. To increase robustness, a temporary voting mechanism was introduced to confirm node transitions, as well as a hierarchical redirection strategy with local and global recovery. The system is implemented in two modes: handheld mode with visual cues using augmented reality arrows, mini map and voice instructions, and hands-free mode with front camera using voice instructions and keywords. Evaluation involved preliminary technical testing in the United Kingdom followed by formal user validation in Spain. During these trials, participants reported high usability, strong confidence and safety, and increased perceived independence. Full article

The ability to autonomously navigate and explore complex 3D environments in a purposeful manner, while integrating visual perception with natural language interaction in a human-like way, represents a longstanding research objective in Artificial Intelligence (AI) and embodied cognition. Vision-Language Navigation (VLN) has evolved from geometry-driven to semantics-driven and, more recently, knowledge-driven approaches. With the introduction of Large Language Models (LLMs) and Vision-Language Models (VLMs), recent methods have achieved substantial improvements in instruction interpretation, cross-modal alignment, and reasoning-based planning. However, existing surveys primarily focus on traditional VLN settings and offer limited coverage of LLM-based VLN, particularly in relation to Sim2Real transfer and edge-oriented deployment. This paper presents a structured review of LLM-enabled VLN, covering four core components: instruction understanding, environment perception, high-level planning, and low-level control. Edge deployment and implementation requirements, datasets, and evaluation protocols are summarized, along with an analysis of task evolution from path-following to goal-oriented and demand-driven navigation. Key challenges, including reasoning complexity, spatial cognition, real-time efficiency, robustness, and Sim2Real adaptation, are examined. Future research directions, such as knowledge-enhanced navigation, multimodal integration, and world-model-based frameworks, are discussed. Overall, LLM-driven VLN is progressing toward deeper cognitive integration, supporting the development of more explainable, generalizable, and deployable embodied navigation systems. Full article

This study proposes TNAP-DDQN, a deep reinforcement learning method for urban low-altitude UAV path planning under residential noise threshold constraints. With time cost and safety risk as the optimization objectives, operational constraints such as collision risk and maximum AGL altitude are incorporated to achieve coordinated optimization of noise compliance, operational safety, and efficiency. To mitigate action space contraction and training instability induced by multiple constraints, a Noise-Degradation-Mask-based Action Bias Network (NDM-ABN) is introduced at the action selection layer. A three-tier degradation scheme prevents empty candidate sets, while bias-based decision making is applied to approximately tied actions to stabilize the policy. Moreover, multi-step prioritized experience replay (PER) improves sample efficiency and long-horizon return modeling, and potential-based reward shaping (PBRS) transforms sparse constraint signals into auxiliary rewards. Simulation results indicate that: (1) NDM-ABN is the key module for stabilizing the noise-exposure process by suppressing high-noise actions; (2) the required AGL is related to the UAV source noise level and local noise limits, implying the need for differentiated AGL altitude classes; and (3) the maximum admissible UAV source noise level increases as the threshold is relaxed. The proposed method provides quantitative guidance for noise-entry and AGL altitude regulation, while future work will incorporate additional metrics (e.g., A-weighted equivalent sound level) to better capture noise fluctuations and short-term peaks. Full article

This article addresses the problem of finding the shortest route for Automated Guided Vehicles (AGVs) in a production environment with constrained battery state-of-charge (SoC) and time-dependent operating conditions. The route map is divided into a uniform grid containing stationary obstacles and two types of dynamic obstacles: human, for which AGV transportation is prohibited, and inanimate (moving objects), which impose a penalty function. A key contribution of the proposed methodology is the introduction of a battery residual charge matrix, which embeds cell-level energy feasibility directly into the grid-based environment representation by determining minimum admissible SoC constraints and accounting for transition-dependent energy costs. This matrix restricts the set of traversable cells under low-energy conditions, enabling energy-aware route feasibility evaluation during both initial planning and adaptive replanning. The proposed approach is based on the A* and D* Lite algorithms, providing shortest-path construction that explicitly integrates battery SoC into the spatio-temporal cost function. To avoid collisions in a multi-agent environment during routing, a simplified hybrid scheme with M* elements performs local coordination and adaptive trajectory replanning. The effectiveness of the proposed methodology was assessed using travel time, temporal complexity, and spatial complexity metrics. Simulation results on a $10\times 10$ grid showed that agents with sufficient battery completed routes of 8 and 11 cells with travel times of 7.2 to 10.7 conventional units. A critically low-energy agent was initially unable to move, but after adjusting the minimum SoC constraint, all agents completed their routes with travel times up to 11.4 conventional units, demonstrating the direct impact of energy constraints on system performance. Additional experiments with varying agent counts and SoC thresholds confirmed reliable balancing of route feasibility and energy constraints across configurations. Full article

Addressing the challenges in 3D reconstruction of large-scale open-pit mines, such as dramatic terrain undulations, complex texture features, and the difficulty of balancing geometric accuracy with real-time rendering efficiency using traditional methods, this paper proposes a high-fidelity reconstruction framework integrating UAV multi-modal data with the state-of-the-art 3D Gaussian Splatting (3DGS) architecture. First, an integrated air-ground multi-modal data acquisition system is established. Using a UAV equipped with LiDAR and a high-resolution camera, high-quality geometric and textural data of the mining area are acquired through terrain-adaptive flight planning. Second, to tackle the VRAM bottlenecks and loose geometric structures inherent in original 3DGS for large scenes, we adopt the advanced CityGaussianV2 architecture as our core reconstruction engine. By leveraging its divide-and-conquer parallel training strategy, 2DGS planar geometric constraints, and Decomposed Gradient Densification (DGD) mechanism, this framework effectively overcomes memory limitations and significantly enhances the geometric sharpness of slope crests and toes. Finally, engineering validation was conducted at Kambove Mining. Experimental results demonstrate that the proposed method achieves centimeter-level geometric accuracy, a real-time web rendering frame rate exceeding 60 FPS, and a model storage compression rate of over 90%. The digital twin control platform built upon this model successfully achieves deep fusion and visual scheduling of multi-source heterogeneous data, providing a novel technical path for constructing high-precision reality-based foundations for smart mines. Full article

In structured orchard environments, harvesting robots operate where rigid bodies (e.g., trunks, poles, and wires) coexist with flexible foliage. Strict avoidance of all obstacles significantly compromises operational efficiency. To address this, this study proposes an end-to-end autonomous harvesting framework characterized by an “avoid-rigid, push-through-soft” strategy. This framework explicitly propagates uncertainties from sensor data and reconstruction processes into the planning and policy phases. First, a multi-task perception network acquires 2D semantic masks of fruits and branches. Class probabilities and instance IDs are back-projected onto a 3D Gaussian Splatting (3DGS) representation to construct a decision-oriented, semantically enhanced 3D scene model. The policy network accepts multi-channel 3DGS rendered observations and proprioceptive states as inputs, outputting a continuous preference vector over eight predefined motion primitives. This approach unifies path planning and action decision-making within a single closed loop. Additionally, a dynamic action shielding module was designed to perform look-ahead collision risk assessments on candidate discrete actions. By employing an action mask to block actions potentially colliding with rigid obstacles, high-risk behaviors are effectively suppressed during both training and execution, thereby enhancing the robustness and reliability of robotic manipulation. The proposed method was validated in both simulation and real-world scenarios. In complex orchard scenarios, the proposed AE-TD3 algorithm achieves a harvesting success rate of 77.1%, outperforming existing RRT (53.3%), DQN (60.9%), and TD3 (63.8%) methods. Furthermore, the method demonstrates superior safety and real-time performance, with a collision rate reduced to 16.2% and an average operation time of only 12.4 s. Results indicate that the framework effectively supports efficient harvesting operations while ensuring safety. Full article