Hybrid Path Research Articles

Integrating hybrid deep learning and path allocation for real-time inbound passenger flow prediction and anomaly detection in urban rail transit

This paper study the problem of real-time prediction of inbound passenger flow and the detection and alerting of abnormal passenger flows in urban rail transit (URT) networks. We propose a fused framework that combines a hybrid deep learning model and an evaluation strategy. Specifically, the learning model incorporates Graph Convolutional Networks (GCN), Gated Recurrent Units (GRU), and attention mechanisms to effectively capture spatial and temporal correlations in passenger flow data. The evaluation strategy utilizes a depth-first search algorithm to determine the optimal travel paths for each individual passenger. And based on the paths, we develop a real-time method for estimating the origin–destination (OD) matrix that utilizes both long-term and short-term historical destination trend vectors to reduce dimensions while improving predictive accuracy. Through extensive testing using data from the Shanghai rail transit system, we demonstrate that this fused framework achieves high prediction accuracy for inbound passenger flow at various stations while efficiently identifying and warning sudden large-scale events involving significant increases in passenger flow volume. This research contributes towards improving overall passenger experience as well as operational resilience within urban rail systems when dealing with large-scale influxes of passengers.

Development of an Autonomous Ship Navigation System Based on the A*-AHP Hybrid Path Planning Method

Development of an Autonomous Ship Navigation System Based on the A*-AHP Hybrid Path Planning Method

A novel hybrid path planning method for sweep coverage of multiple UAVs

A novel hybrid path planning method for sweep coverage of multiple UAVs

Hybrid Mobile Robot Path Planning Using Safe JBS-A*B Algorithm and Improved DWA Based on Monocular Camera

This paper addresses the formidable challenge of enabling autonomous navigation in Mobile Robots (MRs), focusing on the development of advanced path planning strategies. Despite their pivotal role in diverse applications, they face challenges in dynamic settings due to limitation in existing Global Path Planning (GPP) and Local Path Planning (LPP) techniques. In response to this, we propose an innovative hybrid path planning approach that enhances the A* algorithm with a risk-aware heuristic function and integrates the Jump Point Search (JPS) technique for route optimization. Additionally, B-spline smoothing is employed for perceptually global trajectory refinement. Our approach also includes an innovative improvement to the Dynamic Window Approach (DWA) to align with the proposed enhanced A* algorithm for effective local navigation. Acknowledging the importance of high-quality input in path planning, we present substantial improvements to the IRDC-Net, a monocular-image semantic-segmentation model that we studied previously. Novel improvements include the integration of quantization and the Adam optimizer, along with the implementation of the Balanced Cross-Entropy loss function. These enhancements not only elevate the output quality of IRDC-Net but also reduce the model’s training parameters. The experimental results demonstrate the performance and viability of the proposed algorithm. Ultimately, the hybrid MR’s path planning algorithm exhibits proficiency across various tasks, particularly in addressing the challenge of evading moving obstacles to ensure the robot’s safety while adhering to the global path.

3D hybrid path planning for optimized coverage of agricultural fields: A novel approach for wheeled robots

AbstractOver the last few decades, the agricultural industry has made significant advances in autonomous systems, such as wheeled robots, with the primary objective of improving efficiency while reducing the impact on the environment. In this context, determining a path for the robot that optimizes coverage while taking into account topography, robot characteristics, and operational requirements, is critical. In this paper, we present H‐CCPP, a novel hybrid method that combines the comprehensive coverage benefits of our previous approach O‐CCPP with the computational efficiency of the Fields2Cover algorithm. Besides optimizing coverage area, overlaps, and overall travel time, it significantly improves the computation process, and enhances the flexibility of trajectory generation. H‐CCPP also considers terrain inclination to address soil erosion and energy consumption. In an effort to support this innovative approach, we have also created and made available a public data set that includes both 2D and 3D representations of 30 agricultural fields. This resource not only allows us to illustrate the effectiveness of our approach but also provides invaluable data for future research in complete coverage path planning (CCPP) for modern agriculture.

A Hybrid Path Planning Technique for the Time-Efficient Navigation of Unmanned Vehicles in an Unconstrained Environment

Optimal path planning refers to choosing a collision-free, shortest, and smooth path, which is achieved by proposing a new technique, Optimized A* (OA*). The proposed OA* is the hybrid version of three techniques that are ABA* (Adaptive Bidirectional A*), VTM (Vector triangulation method), and PSF (Path smoothing filter which is the modification of Bezier curve technique). The conventional A* only deal with the heuristic values of concerned nodes, but the proposed ABA* algorithm also considers the occupied cells/ obstacles present near the starting and goal nodes in the grid cells to select the shortest path from start to destination. Due to the involvement of the occupied cells, the execution time, path curves, and the number of operations is primarily reduced because occupied nodes are considered as closed nodes, and its heuristic calculation is not considered in the conventional method. The trajectory generated by the proposed ABA* technique is also further made smoother by implementing a path smoothing filter that is the combination of VTM and modified Bezier curve technique based on selecting optimal control point for the collision free trajectory. While implementing the proposed OA* makes the path trajectory become smoother by reducing the number of sharp turns by 85.36% w.r.t traditional ACO, 73.91% w.r.t improved ACO, and 64.70% w.r.t hybrid solution of ACO+ A*. Due to the reduction in the number of sharp turns in the path trajectory, the acceleration of the mobile robot is increased by 52.96% w.r.t traditional ACO, 28.63% w.r.t improved ACO, and 19.96% w.r.t hybrid solution of ACO+ A*.

A cooperative learning-aware dynamic hierarchical hyper-heuristic for distributed heterogeneous mixed no-wait flow-shop scheduling

The distributed heterogeneous mixed scheduling mode in the manufacturing systems emphasizes the cooperation between factories for the entire production cycle, which poses enormous challenges to the processing and assignment of jobs. Discrepancies in the processing environment and types of machines of each factory during various production stages cause diverse processing paths and scheduling. The distributed heterogeneous mixed no-wait flow-shop scheduling problem with sequence-dependent setup time (DHMNWFSP-SDST), abstracted from the industrial scenarios, is addressed in this paper. The mathematical model of DHMNWFSP-SDST is established. A cooperative learning-aware dynamic hierarchical hyper-heuristic (CLDHH) is proposed to solve the DHMNWFSP-SDST. In CLDHH, a cooperative initialization method is developed to promote diversity and quality of solutions. A hierarchical hyper-heuristic framework with reinforcement learning (RL) is designed to select the algorithm component automatically. Estimation of Distribution Algorithm (EDA) guides the upper-layer RL to select four neighborhood structures. A dynamic adaptive neighborhood switching constructs the lower-layer RL to accelerate exploitation with the dominant sub-neighborhoods. An elite-guided hybrid path relinking achieves local enhancement. The experimental results of CLDHH and six state-of-the-art algorithms on instances indicate that the proposed CLDHH is superior to the state-of-the-art algorithms in solution quality, robustness, and efficiency.

Hybrid Path Planning Strategy Based on Improved Particle Swarm Optimisation Algorithm Combined with DWA for Unmanned Surface Vehicles

Path planning is one of the core issues in the autonomous navigation of an Unmanned Surface Vehicle (USV), as the accuracy of the results directly affects the safety of the USV. Hence, this paper proposes a USV path planning algorithm that integrates an improved Particle Swarm Optimisation (PSO) algorithm with a Dynamic Window Approach (DWA). Firstly, in order to advance the solution accuracy and convergence speed of the PSO algorithm, a nonlinear decreasing inertia weight and adaptive learning factors are introduced. Secondly, in order to solve the problem of long path and path non-smoothness, the fitness function of PSO is modified to consider both path length and path smoothness. Finally, the International Regulations for Preventing Collisions at Sea (COLREGS) are utilised to achieve dynamic obstacle avoidance while complying with maritime practices. Numerical cases verify that the path planned via the proposed algorithm is shorter and smoother, guaranteeing the safety of USV navigation while complying with the COLREGS.

Coupled coordination and pathway analysis of food security and carbon emission efficiency under climate-smart agriculture orientation

Owing to the contradiction between agricultural production and environmental development, the issues of food security and carbon mitigation cannot be isolated, and achieving coupled and coordinated development is the key to agricultural sustainability. This study adopted the coupled coordination model and dynamic qualitative comparative analysis (dynamic QCA) method to measure the coupled coordination degree (CCD) of the food security index (FSI) and agricultural carbon emission efficiency (ACEE) in 31 provinces of China from 2010 to 2021, seeking paths to achieve high coupled coordination from Climate-Smart Agriculture technology, external environment, and incentive dimensions, and simulating path selection differences under various CSA priority scenarios. The results indicated that the CCD of the FSI and ACEE in China significantly increased year-on-year increase, with significant regional differences primarily reflected in the Northeast > East > West > Central regions. Based on the CSA orientation, the “technology-environmental safeguard” linkage path and the “technology-environment-incentive” hybrid path are proposed. There are differences in CSA practices across regions, which require customization based on their unique socioeconomic, ecological, and political landscapes. When priorities favour food security, the “technology-environment-incentive” hybrid pathway supports high CCD, and as priorities increase, the contribution of CSA technologies, centred on water-saving irrigation, increases and the role of the external environment diminishes. When the priority tendency is to mitigate emissions, both paths can achieve high CCD. As the priority tendency for carbon emissions increases, urbanisation and CSA technologies such as water-saving irrigation and straw return become essential factors contributing to higher coupling coordination, and the role of agriculture-related financial expenditures diminishes. These findings provide policy support for safeguarding food security and low-carbon agriculture.

Adaptive Dynamic Model-Based Path Following Controller Design for an Unmanned Surface Vessel

Abstract The effective design of a path following controller for Unmanned Surface Vessels (USVs) under uncertain influences induced by various factors such as environmental disturbances is a challenging task. In this study, we propose to ful?lling this task through taking benefits from an online parameter identi?cation technique, the discrete-time sliding mode control (DSMC) method, and the improved line of sight (LOS) algorithm. The Particle Swarm Optimization algorithm (PSO) was adopted to provide initial settings for the straightforward online identification method, i.e., the Forgetting Factor Recursive Least Square method (FFRLS). In order to handle the time-varying sideslip angle of a ship that exists in reality due to environmental disturbances, a multi-model course control scheme is proposed to improve the control performance. For this control scheme, a flexible selection mechanism in-between a heading angle or a course angle tracking controller based on the DSMC method is designed. A solution to ?xing the tracking deviation problem of the LOS guidance law is investigated for which the gradient descent method is introduced. A series of experiments are carried out at sea with a USV called Orca to verify and validate the proposed hybrid path following approach. The results showed that tracking errors mainly induced by environmental disturbances existed but the maximum magnitude among them was small enough and remaining within the acceptable range especially from the marine engineering point of view. These results, to a high degree, validated the robustness and precision of the proposed controller.

An Improved Hybrid Path Planning Algorithm in Indoor Environment

Abstract During the path planning of robots in the indoor unstructured complex environment, there are often problems such as unreachable target points, deflection in the planning process, and failure to avoid dynamic obstacles in time. To solve these problems, an improved hybrid indoor path planning algorithm was proposed, wherein the improved global path planning algorithm was effectually integrated with improved local path planning algorithm. Firstly, the heuristic factor of traditional A-Star algorithm was optimized, search range and nodes were reduced, and then the path generated by traditional A-Star algorithm for path planning was smoothed using the angle bisector tangent point method. Secondly, combining path and environment information, local path planning was undertaken by utilizing the improved artificial potential field algorithm, and the unreachable target points problem was addressed by adjusting the repulsive field parameters. Additionally, dynamic potential field function was constructed to make it have the ability to resolve dynamic obstacles. Finally, in the part of actual environment verification, a comparison was made in this paper to assess the performance of the traditional hybrid algorithm against the improved algorithm in terms of path planning. The consequences showed that, by the hybrid algorithm proposed in this paper, the path planning length was reduced by 10.3%, the running time was decreased by 12.5%, and 34 redundant nodes were eliminated. The consequences indicated that the hybrid algorithm can effectively address the indoor unstructured and complex path planning problems.

Hybrid Path Generation Method for Multi-Axis Laser Metal Deposition of Overhanging Thin-Walled Structures.

Additive manufacturing has advantages over other traditional manufacturing technologies for the fabrication of complex thin-walled parts. Previous correlation path strategies, when applied to laser metal deposition processes, suffer from contour deposition transboundary and surface "scar" type overstacking. Therefore, this paper proposes a hybrid path generation method for the laser metal deposition process. First, the topological logic of the STL model of the part is restored to reduce redundant calculations at the stage of obtaining the layered contour. Then, the path points are planned on the basis of the offset contours in a helical upward trend to form a globally continuous composite path in space considering the melt channel width. Finally, vectors that adaptively fit to the model surface are generated for the path points as tool orientations and they are optimized by smoothing the rotation angles. The results of experiments conducted on a multi-axis machine equipped with a laser metal deposition module show that the path generated by the proposed method is not only capable of thin-walled structures with overhanging and curved surface features but also improves the surface imperfections of the part due to sudden changes in the angle of rotation while ensuring the boundary dimensions.

Negative Affect, Harassment and Problematic Alcohol Use in Young Adults

Background: While research suggests that both negative affect and alcohol use are impacted by exposure to harassment (i.e., sexual harassment, generalized harassment or bullying), less is known about the effect of harassment on negative affect subsequently leading to alcohol consumption, particularly in young adults. We examined the mediating role of negative affect on the relationships between sexual and generalized harassment at school and alcohol misuse. Methods: Participants were 2899 incoming freshmen in fall of 2011 who completed a Web-based survey assessing demographics (T0), sexual and generalized harassment at school (T0-T2), negative affect (T3), and problems associated with drinking, binge drinking, and drinking to intoxication (T0, T4, T5). Separate hybrid path models were fitted in Mplus v.8.8 for generalized harassment and sexual harassment and each outcome. Results: Mediation analyses showed a small but significant indirect effect for the sexual harassment model (beta = 0.05, S.E. = 0.01, p < 0.001) and generalized harassment (beta = 0.03, S.E. = 0.01, p < 0.01), indicating that negative affect partially mediated the associations between harassment early in students’ college experience and later problems associated with drinking. No significant indirect effects were found for the binge drinking or intoxication models. Conclusions: High levels of negative affect associated with harassment may contribute to longer term impact on problematic use of alcohol in young adults, providing evidence that the effects of harassment on drinking may partly stem from harassment’s lingering effects on negative affective pathways.

Research of hybrid path planning with improved A* and TEB in static and dynamic environments

Research of hybrid path planning with improved A* and TEB in static and dynamic environments

Hybrid path planning method for USV using bidirectional A* and improved DWA considering the manoeuvrability and COLREGs

This paper proposes a hybrid dynamic path planning algorithm that integrates global path planning (GPP) and local path planning (LPP). The objective is to effectively address the challenges associated with path planning and collision avoidance for unmanned surface vehicles (USV) in complex environments. The bidirectional A* algorithm is used to search the optimized strategy based on the actual geographical information map for the navigation routes of USV. The Dynamic Window Algorithm (DWA) is employed, and a novel cost function is formulated considering the USV's manoeuvring characteristics, dynamic constraints, and environmental information. The primary purpose is to ensure the compliance of the USV with COLREGs during dynamic obstacle avoidance. It accomplishes this by providing positive reinforcement for achieving the correct turning speed when the USV determines the orientation of an approaching ship. Another evaluation function is introduced to mitigate the problem of local optima in complex environments that the LPP may encounter. The actual work map is used to model the application scenario with the obstacles in the presence of incoming ships, the simulation results show that the proposed algorithm is capable of generating adaptive, collision-free routes while adhering to COLREGs rules.

Hybrid path planning method based on skeleton contour partitioning for robotic additive manufacturing

Hybrid path planning method based on skeleton contour partitioning for robotic additive manufacturing

Design and Implementation of a Hybrid Path Planning Approach for Autonomous Lane Change Manoeuvre

Design and Implementation of a Hybrid Path Planning Approach for Autonomous Lane Change Manoeuvre

A hybrid path finder-based vortex search algorithm for optimal energy-efficient node placing and routing in UWSN

In recent times, the research community has demonstrated significant interest in Underwater Wireless Sensor Networks (UWSNs), where extensive sensor deployments in oceans and rivers aim to monitor the underwater environment. Energy consumption poses a primary challenge due to the difficulty of replacing or recharging batteries in these environments. Existing studies have employed K-Means technology to minimize power consumption in underwater transmission nodes. However, these studies have often overlooked the consideration of residual energy and void region creation in their optimization approaches. To address these challenges, we introduce a novel Hybrid path finder-based vortex search (HPF-VS) algorithm, utilized for cluster head selection and optimization of node locations and remaining energy. To extend network coverage beyond limited transmission ranges, inaccessible nodes at the network periphery employ the improved Dwarf Mongoose Optimization (IDMO) algorithm. Our proposed techniques demonstrate superior performance compared to existing methods, showcasing minimized energy consumption, reduced delay, improved packet delivery ratio, and enhanced throughput. Specifically, the proposed approach achieves a delay of 2.01 s and a throughput of 32.21 Kbps, surpassing the performance of state-of-the-art methodologies we benchmarked against.

A Subgraph Retrieval Method for Complex Questions Based on Hybrid Semantics and Path Representation

Current subgraph retrieval methods generally fall into two categories: those that rely on semantic matching, which use only surface-level semantic information of relations and lack flexibility; and those based on personalized PageRank algorithms, which fail to leverage the semantic connection between the relation and the question, rendering them susceptible to noisy data. To address these issues, this paper introduces a novel retrieval model that employs hybrid semantics of relations and path representations. Specifically, hybrid semantics involves merging relational and entity information within a knowledge graph to extract the deep semantics of relations and enhance semantic representation by integrating it with the explicit descriptive text of the relations. Path representation merges the semantics of the current relation with those of preceding ones to form a complete path representation. This representation is then semantically matched with the question to compute a score, which determines whether the relation should form part of the subgraph. We integrated our subgraph retrieval model with the Neural Symbolic Machine (NSM) reasoning model and evaluated it on the publicly available CWQ and WebQSP datasets. The experimental results demonstrate that our method performs exceptionally well on these datasets, validating the efficacy of utilizing deep semantics and path representations for the retrieval of subgraphs in response to complex questions.

A Hybrid Path Planning Method Based on Improved A* and CSA-APF Algorithms

A Hybrid Path Planning Method Based on Improved A* and CSA-APF Algorithms