Path Planning Research Articles

Technological State and Optimization Analysis of High-Rise Glass Curtain Wall Cleaning Robots

Abstract. With the proliferation of high-rise buildings in urban areas, glass curtain walls are widely used due to their excellent light transmittance and modern appearance. However, these glass curtain walls are prone to accumulating dust, rain stains, and other dirt during use, affecting their aesthetics and transparency, thus requiring regular cleaning. Traditional manual cleaning methods are inefficient and pose significant safety risks. Consequently, high-rise glass curtain wall cleaning robot technology has become a research hotspot. This paper reviews the current research status of high-rise glass curtain wall cleaning robots, which provides a detailed analysis of four main adhesion methods (magnetic adhesion, thrust adhesion, vacuum negative pressure adhesion, and bionic adhesion), four main motion modes (legged, wheeled, tracked, and external assistance), and two main cleaning methods (physical and chemical). For path planning, this paper explores the application status and challenges of regular scanning, random walking, sensor feedback dynamic planning, and bionic path planning. Through the evaluation of the advantages and disadvantages of existing technologies, this paper identifies the main issues faced by each technology and proposes optimization strategies for adhesion technology, motion modes, cleaning efficiency, and path planning. Future directions include improvements in intelligence and automation, multifunctional integration, energy efficiency enhancement, and human-machine collaboration. This paper aims to provide a comprehensive technological review and constructive suggestions to advance high-rise glass curtain wall cleaning robot technology.

Valley Path Planning on 3D Terrains Using NSGA-II Algorithm

Valley path planning on 3D terrains holds significant importance in navigating and understanding complex landscapes. This specialized form of path planning focuses on finding optimal routes that adhere to the natural contours of valleys within three-dimensional terrains. The significance of valley path planning lies in its ability to address specific challenges presented by valleys, such as varying depths, steep slopes, and potential obstacles. By following the natural flow of valleys, path planning can enhance the efficiency of navigation and minimize the risk of encountering difficult terrain or hazards. In recent years, an increasing number of researchers have focused on the study of valley path planning on 3D terrains. This study presents a valley path planning method utilizing the NSGA-II (Non-dominated Sorting Genetic Algorithm II) approach. To ensure that the paths generated by the algorithm closely follow the valley lines, the algorithm establishes an optimization function that includes three optimization criteria: mean altitude, flight route length, and mean offset. To test the performance of this algorithm, we conducted experiments based on workspaces based on three datasets full of 3D terrains and compared it with three baseline algorithms. The evaluation indicates that the suggested algorithm successfully designs routes that closely follow the valley contours.

Research on robot path planning and obstacle avoidance algorithm in dynamic environment based on deep reinforcement learning

Abstract. In dynamic environments, robot path planning and obstacle avoidance are critical tasks, especially in applications such as autonomous driving, industrial automation, and mobile robotics. These tasks are inherently challenging due to the unpredictability of the environment and the need for real-time decision-making. This paper seeks to address these challenges by developing and analyzing both traditional and optimized models for robot navigation. The initial model utilizes a basic Q-learning algorithm, which provides a straightforward approach to learning from the environment but often struggles with the complexity of dynamic scenarios. To this end, an optimized model is developed that combines the Double Deep Q-Learning algorithm (Double DQN) in conjunction with heuristic strategies. The research employs the MATLAB Reinforcement Learning Toolbox to implement and train these models, and utilizes a simulated environment with dynamic obstacles as a testing site. The simulation generates the necessary data to allow for comprehensive testing and evaluation of the models performance. The results show that the optimized model greatly exceeds the initial model in terms of path planning efficiency and obstacle avoidance capabilities, and that the combination of advanced reinforcement learning techniques and heuristic strategies is extremely important for enhancing the performance and reliability of robotic systems in complex, dynamic environments, offering valuable insights for future applications in various fields of robotics.

Research on autonomous obstacle avoidance and automatic obstacle avoidance of minimally invasive surgical robots

Abstract. With the development of modern society, people pay more and more attention to health and safety, especially to the development of medical techniques. The demand for higher medical standards has led to minimally invasive surgery becoming a better choice for patients. Minimally invasive surgeries involve less trauma, lower blood loss, quicker recovery, and a lower risk of infection. However, compared to traditional surgeries, these surgeries demand higher precision and skill from the surgeons, making surgical robots the preferred tool for most minimally invasive operations. Surgical robots can eliminate the surgeon's hand tremors during the operation, enhance the precision of surgical operations, and offer greater flexibility with their small end size inside human organs. Despite these advantages, minimally invasive surgical robots can not avoid obstacles and plan the path of human organs and cavities in real-time. This paper reviews the dynamic path planning and real-time obstacle avoidance of modern minimally invasive surgical robots, including their development progress and research directions. It also introduces in detail the mainstream research methods of path planning and real-time obstacle avoidance in modern research. Finally, the current technical challenges and the prediction of the future research direction are pointed out and the reference suggestions are provided.

A modified extended Kalman filter based fusion of auto-correlation data for robot SLAM estimation

Abstract. With the popularization of robot technology, various technological developments related to robots have gradually entered a stage of rapid development. Especially path planning technology, which has been a very important and worthwhile part of robot motion and behavior since the concept of robots emerged. In this technology, various obstacles, environmental changes, and efficiency factors usually need to be considered. Whether in the past, present, or future, robot behavior pursues greater precision, reliability, adaptability to the environment, and even anthropomorphism. In order to achieve these goals, the idea of data fusion has emerged in the development of robot data processing. Therefore, the research direction is to use Kalman filtering for noise filtering and data correction to improve the accuracy of fused data. By using a feasible and strongly correlated data fusion method, combined with an improved extended Kalman filter, various data generated by robots can be fused in multiple dimensions and have correlations, reducing the negative impact of data differences and improving the quality and reliability of data fusion.

Optimizing intelligent penetration path planning using reinforcement learning: A focus on valid action masking and sample enhancement

Abstract. As penetration testing is a crucial technique for the rapid evolution of cybersecurity to identify system vulnerabilities, traditional penetration testing methods face the difficulty of large amounts of manual labor and professional knowledge, which makes them difficult to scale. This paper proposes a highly automated and efficient penetration testing approach based on the MASK-SALT-DQN algorithm. MASK-SALT-DQN is a reinforcement learning model that effectively optimizes penetration path planning by valid action masking and sample enhancement. Through valid action masking, the MASK-SALT-DQN model filters out redundant and invalid actions in the solution space, reducing the complexity of the action space and improving the convergence speed and efficiency. In addition, the sample enhancement method increases the frequency of critical exploitation actions and positive rewards in the sparse-reward environment, speeding up the learning process of the agent. Experiments have been conducted on the NASim attack simulation network to demonstrate the advantages of the proposed model over the baseline method. The experimental results show that our model has a significant performance advantage over baseline methods in large networks, and it can be applied to the field of scalable and efficient automated penetration testing.

Method of Motion Path Planning Based on a Deep Neural Network with Vector Input

The article deals with the problem of path planning in a two-dimensional environment based on deep learning neural networks. Deep neural networks require large amounts of data and place high computational requirements on computing tools. The lack of sufficient data leads to a decrease in the accuracy of the neural network, and high computational requirements at the learning stage limit the use of this technology in engineering practice. In this paper, the forms of representation of the environment for the input of a neural network are studied. Vector form allows to reduce the amount of information supplied to the input of a neural network, but it leads to the need to use more complex neural networks. In this article, a combined form of representation is proposed, including a vector global and local map layout. The vector part of the map includes the position of the robot, the position of the target point and a description of obstacles. The local raster map describes the area closest to the robot. Using numerical research, the effectiveness of this form of data representation for a precise neural network is shown, compared with the raster representation of the map. In this article, two structures of neural networks are studied, one of which uses 8 possible directions of movement, and the other uses 3 possible directions of movement. It is shown that when using 3 possible directions, the cycling of trajectories planned by the neural network is eliminated, which leads to an increase in accuracy.

Research on path planning in UAV-assisted emergency communication

The rapid development of UAV communication technology makes it have application potential in wireless systems. However, for the optimization problem of UAV base station providing communication for ground personnel in the disaster area under special natural disasters, traditional deep reinforcement learning is used. Algorithms cannot solve such problems well. This article proposes the AD3QN algorithm combined with the attention mechanism, which can communicate with disaster victims on the ground better and more quickly, providing better information collection for rescue missions and completing the task of communication optimization. In the mission simulation environment, in order to make the environment more realistic, we innovatively designed the ground user distribution model, air-to-ground communication model, and electromagnetic interference model. Finally, the effect of the proposed algorithm is evaluated by comparing different deep reinforcement learning algorithms. The results show that the algorithm we proposed can provide communication services faster and has higher practicability in terms of algorithm.

Path planning for submersible surface ships in a three-dimensional environment considering safety distance

Currently, path planning for an unmanned ship is usually performed in a single domain on the water surface or underwater, and little research exists on path planning for a three-dimensional (3D) environment where the ship crosses the water’s surface and underwater. The existing 3D path planning research still has improvement possibilities in reserving a safe distance between the ship and the obstacles. In this paper, path planning for a submersible surface ship (SSS) in a 3D environment is carried out based on an ant colony algorithm. Path safety is enhanced by introducing constraints related to boat width to keep the path at a safe distance from obstacles. By extracting key points, the length of the path is further reduced. The algorithmic procedure with the objective of the shortest time was obtained by assigning different speeds to the SSS sailing at the same depth and across different depths. The rationality and superiority of the method given in this paper are verified in several sets of simulations and comparative experiments. The paper concludes that path selection is more inclined to choose the water surface as the depth of the obstacles increases and the density of the obstacles decreases.

Cooperative Path Planning for Multi-UAVs with Time-Varying Communication and Energy Consumption Constraints

In the field of Unmanned Aerial Vehicle (UAV) path planning, designing efficient, safe, and feasible trajectories in complex, dynamic environments poses substantial challenges. Traditional optimization methods often struggle to address the multidimensional nature of these problems, particularly when considering constraints like obstacle avoidance, energy efficiency, and real-time responsiveness. In this paper, we propose a novel algorithm, Dimensional Learning Strategy and Spherical Motion-based Particle Swarm Optimization (DLS-SMPSO), specifically designed to handle the unique constraints and requirements of cooperative path planning for Multiple UAVs (Multi-UAVs). By encoding particle positions as motion paths in spherical coordinates, the algorithm offers a natural and effective approach to navigating multidimensional search spaces. The incorporation of a Dimensional Learning Strategy (DLS) enhances performance by minimizing particle oscillations and allowing each particle to learn valuable information from the global best solution on a dimension-by-dimension basis. Extensive simulations validate the effectiveness of the DLS-SMPSO algorithm, demonstrating its capability to consistently generate optimal paths. The proposed algorithm outperforms other metaheuristic optimization algorithms, achieving a feasibility ratio as high as 97%. The proposed solution is scalable, adaptable, and suitable for real-time implementation, making it an excellent choice for a broad range of cooperative multi-UAV applications.

Continuous fiber printing path generation based on Euler diagram division

Continuous fiber printed structures are widely used in aerospace applications because of their excellent performance and high design freedom. Existing path planning methods optimize the continuous fiber printing direction by stress lines or discrete angles, but these methods are far from perfect printing paths and lack planning for connectivity relations. In this study, a planning method for continuous fiber printing paths based on constructing Eulerian circuits from a weighted undirected graph is proposed. The principal stress lines are transformed into a weighted undirected graph, which divides the Eulerian subgraph by splitting the common nodes to plan the continuous fiber printing path circuit. Subsequently, the printing structure parameters are optimized based on simulation analysis. The experimental results, taking MBB (Messerschmitt-Bolkow-Blohm) beams as an example, show that the printing path designed in this paper improves the structural strength by 52.9% and the structural stiffness by 81.7% compared with the conventional printing path.

Chaos-based coverage path planning framework for mobile robots and its digital signal processing implementation

Abstract For special coverage path planning, chaos-based mobile robots present a promising solution. The robot can cover the area of interest rapidly with unpredictable trajectories. However, this unpredictability causes difficulties in trajectory control and the robot often makes sharp turns, affecting motion stability. To address these challenges, this paper proposes a universal chaos-based path planning framework for mobile robots. Firstly, a chaotic system that can generate multi-scroll and multi-wing attractors is designed to verify the effectiveness of the framework. Secondly, an integrated system consisting of mobile robots and chaos is proposed to generate chaotic trajectories. By the control parameters in the integrated system, the formation mechanism of continuous chaotic trajectories is shown, which makes the chaotic trajectory have the advantages of scaling, rotating, straightening, and bending, and the path planning no longer relies on the chaotic system only. Then, a regional path planning strategy is proposed to control the angular velocity and workspace of the robot, making its motion smooth and reducing trajectory redundancy. Experiments conducted under this framework have demonstrated its university, with various chaotic systems capable of generating efficient robot trajectories with high coverage rate. Compared with the state-of-the-art similar memoryless algorithms, the coverage task can be accomplished quickly and efficiently by our approach. Finally, the robot trajectory tracking control verifies the controllability of chaotic trajectories, and the implementation of chaotic trajectories with digital signal processing techniques further validates the feasibility of path planning frameworks.

ExAq-MSPP: An Energy-Efficient Mobile Sink Path Planning Using Extended Aquila Optimization Algorithm

Wireless sensor networks play a crucial role in gathering data from remote or hard-to-reach locations, enabling real-time monitoring and decision-making in a wide range of industries and applications. The mobile sink path planning (MSPP) enables mobile sinks (e.g., drones or rovers) to navigate through the environment, collecting data from different sensor nodes, ensuring comprehensive coverage, and adaptively addressing changing conditions. Still, the energy-efficient routing with minimal delay is the challenging aspect. This research focuses on improving data gathering in wireless sensor networks by introducing an efficient routing protocol. In this proposed protocol, sensor nodes are initially deployed using Voronoi diagrams to ensure uniform network coverage. The network is then divided into clusters using the low-energy adaptive clustering hierarchy (LEACH) algorithm for energy-efficient routing. To optimize the path planning of a mobile sink for data collection, we introduce the extended Aquila (ExAq) optimization algorithm, which uses a multi-objective fitness function considering factors such as delay, residual energy, link quality, priority, and distance. Simulation results demonstrate the effectiveness of the proposed ExAq-MSPP protocol in terms of reduced delay, improved network lifetime, higher packet delivery ratio, enhanced residual energy, and increased throughput compared to existing protocols with the values of 1.169, 99.857, 99.920, 0.997, and 255.306, respectively. Thus, the energy-efficient routing and optimizing path planning for mobile sinks, the proposed ExAq-MSPP protocol can extend network lifetime, increase data accuracy, and provide more robust performance under changing environmental conditions.

Sharp Curve Trajectory Tracking of a Universal Omni-Wheeled Mobile Robot Using a Sliding Mode Controller

Abstract In our previous works, Amarasiri et al. (2022, “Robust Dynamic Modeling and Trajectory Tracking Controller of a Universal Omni-Wheeled Mobile Robot,” ASME Lett. Dyn. Sys. Control 2(4), p. 040902) and Amarasiri et al. (2024, “Investigating Suitable Combinations of Dynamic Models and Control Techniques for Offline Reinforcement Learning Based Navigation: Application of Universal Omni-Wheeled Robots,” ASME Lett. Dyn. Sys. Control 4(2), p. 021007), two dynamic models of a universal omni-wheeled mobile robot (UOWMR), and trajectory-tracking controllers (three linear and one nonlinear) were developed and presented. The purpose of that work was to identify suitable combinations of dynamic models and trajectory-tracking controllers, choosing the combination with the highest tracking accuracy and the lowest solver execution time. The ultimate purpose is to utilize these physics-based tools in a reinforcement learning (RL) agent developed for path planning and navigation in an unstructured environment. Three trajectories were investigated including a smooth path, a sharp curved path, and a smooth path with disturbance forces. The sliding mode controller (SMC) following a trajectory with sharp (right-angled) curves was not investigated in that work. The sharp corners caused indeterminacy in the path derivatives required for the SMC algorithm. In this short article, we complete our studies of the SMC on sharp corner paths utilizing slight trajectory corner smoothing.

Path planning strategy for unmanned aerial manipulators in pick-and-place applications

Path planning strategy for unmanned aerial manipulators in pick-and-place applications

End-to-end deep learning-based framework for path planning and collision checking: bin-picking application – ERRATUM

End-to-end deep learning-based framework for path planning and collision checking: bin-picking application – ERRATUM

A Hybrid ARO Algorithm and Key Point Retention Strategy Trajectory Optimization for UAV Path Planning

Path planning is a fundamental research issue for enabling autonomous flight in unmanned aerial vehicles (UAVs). An effective path planning algorithm can greatly improve the operational efficiency of UAVs in complex environments like urban and mountainous areas, thus offering more extensive coverage for various tasks. However, existing path planning algorithms often encounter problems such as high computational costs and a tendency to become trapped in local optima in complex 3D environments with multiple constraints. To tackle these problems, this paper introduces a hybrid multi-strategy artificial rabbits optimization (HARO) for efficient and stable UAV path planning in complex environments. To realistically simulate complex scenarios, we introduce spherical and cylindrical obstacle models. The HARO algorithm balances exploration and exploitation phases using a dual exploration switching strategy and a population migration memory mechanism, enhancing search performance and avoiding local optima. Additionally, a key point retention trajectory optimization strategy is proposed to reduce redundant path points, thus lowering flight costs. Experimental results confirm the HARO algorithm’s superior search performance, planning more efficient and stable paths in complex environments. The key point retention strategy effectively reduces flight costs during trajectory optimization, thereby enhancing adaptability.

Research on the A* Algorithm for Automatic Guided Vehicles in Large-Scale Maps

The traditional A* algorithm faces the challenges of low search efficiency and large node extension range in the field of path planning. These directly restrict the overall performance of the algorithm. In this study, we aimed to improve the search efficiency and path planning quality of the A* algorithm in complex and large-scale environments through a series of optimisation measures, including the innovation of weight design, flexible adjustment of the search neighbourhood, improvement of the heuristic function, and optimisation of the node selection strategy. Specifically, this study innovatively introduces the local obstacle rate as the core index of weight design, and it dynamically adjusts the weights according to the change of the obstacle rate during the node movement process, which effectively reduces the search space and significantly improves the search speed. At the same time, according to the real-time change of the local obstacle rate, this study dynamically adjusts the range of the search neighbourhood, so that the algorithm can choose the optimal search strategy according to different environmental information. In terms of the improvement of the heuristic function, this study adopted the diagonal distance as the benchmark for cost estimation, and it innovatively introduces the angle coefficient to reflect the complexity of path turning, thus providing the algorithm with a more accurate guidance for the search direction. In addition, this study optimises the node selection method by drawing on the idea of simulated annealing, which eliminates the need to calculate and compare all possible surrogate values during the node selection process, thus significantly reducing the running time of the algorithm. The results of the simulation experiments fully verify the effectiveness and practicality of the improved algorithm. Compared with the traditional A* algorithm, the improved algorithm achieved significant optimisation in terms of the average running time, the number of expansion nodes, and the path length, with the average running time shortened by 84%, the number of expansion nodes reduced by 94%, and the path length also shortened by 2.3%.

Deep Learning-Assisted Label-Free Parallel Cell Sorting with Digital Microfluidics.

Sorting specific cells from heterogeneous samples is important for research and clinical applications. In this work, a novel label-free cell sorting method is presented that integrates deep learning image recognition with microfluidic manipulation to differentiate cells based on morphology. Using an Active-Matrix Digital Microfluidics (AM-DMF) platform, the YOLOv8 object detection model ensures precise droplet classification, and the Safe Interval Path Planning algorithm manages multi-target, collision-free droplet path planning. Simulations and experiments revealed that detection model precision, concentration ratios, and sorting cycles significantly affect recovery rates and purity. With HeLa cells and polystyrene beads as samples, the method achieved 98.5% sorting precision, 96.49% purity, and an 80% recovery over three cycles. After a series of experimental validations, this method can also be used to sort HeLa cells from red blood cells, cancer cells from white blood cells (represented by HeLa and Jurkat cells), and differentiate white blood cell subtypes (represented by HL-60 cells and Jurkat cells). Cells sorted using this method can be lysed directly on chip within their hosting droplets, ensuring minimal sample loss and suitability for downstream bioanalysis. This innovative AM-DMF cell sorting technique holds significant potential to advance diagnostics, therapeutics, and fundamental research in cell biology.

Efficient generation of grids and traversal graphs in compositional spaces towards exploration and path planning

AbstractDiverse disciplines across science and engineering deal with problems related to compositions, which exist in non-Euclidean simplex spaces, rendering many standard tools inaccurate or inefficient. This work explores such spaces conceptually in the context of materials discovery, quantifies their computational feasibility, and implements several essential methods specific to simplex spaces through a new high-performance open-source library . Most significantly, we derive and implement an algorithm for constructing a novel n-dimensional simplex graph data structure, containing all discretized compositions and possible neighbor-to-neighbor transitions. Critically, no distance or neighborhood calculations are performed, instead leveraging pure combinatorics and order in procedurally generated simplex grids, keeping the algorithm $${\mathcal{O}}(N)$$ O ( N ) , with minimal memory, enabling rapid construction of graphs with billions of transitions in seconds. Additionally, we demonstrate how such graph representations can be combined to homogeneously express complex path-planning problems, while facilitating efficient deployment of existing high-performance gradient descent, graph traversal, and other optimization algorithms.