Global Path Planning Research Articles

Development of Unmanned Aerial Vehicle Navigation and Warehouse Inventory System Based on Reinforcement Learning

In this paper, we present the exploration of indoor positioning technologies for UAVs, as well as navigation techniques for path planning and obstacle avoidance. The objective was to perform warehouse inventory tasks, using a drone to search for barcodes or markers to identify objects. For the indoor positioning techniques, we employed visual-inertial odometry (VIO), ultra-wideband (UWB), AprilTag fiducial markers, and simultaneous localization and mapping (SLAM). These algorithms included global positioning, local positioning, and pre-mapping positioning, comparing the merits and drawbacks of various techniques and trajectories. For UAV navigation, we combined the SLAM-based RTAB-map indoor mapping and navigation path planning of the ROS for indoor environments. This system enabled precise drone positioning indoors and utilized global and local path planners to generate flight paths that avoided dynamic, static, unknown, and known obstacles, demonstrating high practicality and feasibility. To achieve warehouse inventory inspection, a reinforcement learning approach was proposed, recognizing markers by adjusting the UAV’s viewpoint. We addressed several of the main problems in inventory management, including efficiently planning of paths, while ensuring a certain detection rate. Two reinforcement learning techniques, AC (actor–critic) and PPO (proximal policy optimization), were implemented based on AprilTag identification. Testing was performed in both simulated and real-world environments, and the effectiveness of the proposed method was validated.

A Multi-UAV cooperative mission planning method based on SA-WOA algorithm for three-dimensional space atmospheric environment detection

AbstractIn the application of rotorcraft atmospheric environment detection, to reflect the distribution of atmospheric pollutants more realistically and completely, the sampling points must be spread throughout the entire three-dimensional space, and the cooperation of multiple unmanned aerial vehicles (multi-UAVs) can ensure real-time performance and increase operational efficiency. In view of the problem of coordinated detection by multi-UAVs, the region division and global coverage path planning of the stereo space to be detected are studied. A whale optimization algorithm based on the simulated annealing-whale optimization algorithm (SA-WOA) is proposed, which introduces adaptive weights with the Levy flight mechanism, improves the metropolis criterion, and introduces an adaptive tempering mechanism in the SA stage. Path smoothing is subsequently performed with the help of nonuniform rational B-spline (NURBS) curves. The comparison of algorithms using the eil76 dataset shows that the path length planned by the SA-WOA algorithm in this paper is 10.15% shorter than that of the WOA algorithm, 13.25% shorter than the SA planning result, and only 0.95% difference from the optimal path length in the dataset. From the perspective of planning time, its speed is similar to WOA, with a relative speed increase of 27.15% compared to SA, proving that the algorithm proposed in this paper has good planning performance. A hardware system platform is designed and built, and environmental gas measurement experiments were conducted. The experimental results indicate that the multi-UAV collaborative environment detection task planning method proposed in this paper has certain practical value in the field of atmospheric environment detection.

A double‐layer crowd evacuation simulation method based on deep reinforcement learning

AbstractExisting crowd evacuation simulation methods commonly face challenges of low efficiency in path planning and insufficient realism in pedestrian movement during the evacuation process. In this study, we propose a novel crowd evacuation path planning approach based on the learning curve–deep deterministic policy gradient (LC‐DDPG) algorithm. The algorithm incorporates dynamic experience pool and a priority experience sampling strategy, enhancing convergence speed and achieving higher average rewards, thus efficiently enabling global path planning. Building upon this foundation, we introduce a double‐layer method for crowd evacuation using deep reinforcement learning. Specifically, within each group, individuals are categorized into leaders and followers. At the top layer, we employ the LC‐DDPG algorithm to perform global path planning for the leaders. Simultaneously, at the bottom layer, an enhanced social force model guides the followers to avoid obstacles and follow the leaders during evacuation. We implemented a crowd evacuation simulation platform. Experimental results show that our proposed method has high path planning efficiency and can generate more realistic pedestrian trajectories in different scenarios and crowd sizes.

Crowd evacuation simulation based on hierarchical agent model and physics‐based character control

AbstractCrowd evacuation has gained increasing attention in recent years. The agent‐based method has shown a superior capability to simulate complex behaviors during crowd evacuation simulation. For agent modeling, most existing methods only consider the decision process but ignore the detailed physical motion. In this article, we propose a hierarchical framework for crowd evacuation simulation, which combines the agent decision model with the agent motion model. In the decision model, we integrate emotional contagion and scene information to determine global path planning and local collision avoidance. In the motion model, we introduce a physics‐based character control method and control agent motion using deep reinforcement learning. Based on the decision strategy, the decision model can use a signal to control the agent motion in the motion model. Compared with existing methods, our framework can simulate physical interactions between agents and the environment. The results of the crowd evacuation simulation demonstrate that our framework can simulate crowd evacuation with physical fidelity.

Dynamic 3D Point-Cloud-Driven Autonomous Hierarchical Path Planning for Quadruped Robots.

Aiming at effectively generating safe and reliable motion paths for quadruped robots, a hierarchical path planning approach driven by dynamic 3D point clouds is proposed in this article. The developed path planning model is essentially constituted of two layers: a global path planning layer, and a local path planning layer. At the global path planning layer, a new method is proposed for calculating the terrain potential field based on point cloud height segmentation. Variable step size is employed to improve the path smoothness. At the local path planning layer, a real-time prediction method for potential collision areas and a strategy for temporary target point selection are developed. Quadruped robot experiments were carried out in an outdoor complex environment. The experimental results verified that, for global path planning, the smoothness of the path is improved and the complexity of the passing ground is reduced. The effective step size is increased by a maximum of 13.4 times, and the number of iterations is decreased by up to 1/6, compared with the traditional fixed step size planning algorithm. For local path planning, the path length is shortened by 20%, and more efficient dynamic obstacle avoidance and more stable velocity planning are achieved by using the improved dynamic window approach (DWA).

OkayPlan: Obstacle Kinematics Augmented Dynamic real-time path Planning via particle swarm optimization

Existing Global Path Planning (GPP) algorithms predominantly presume planning in static environments. This assumption immensely limits their applications to Unmanned Surface Vehicles (USVs) that typically navigate in dynamic environments. To address this limitation, we present OkayPlan, a GPP algorithm capable of generating safe and short paths in dynamic scenarios at a real-time executing speed (125 Hz on a desktop-class computer). Specifically, we approach the challenge of dynamic obstacle avoidance by formulating the path planning problem as an Obstacle Kinematics Augmented Optimization Problem (OKAOP), which can be efficiently resolved through a PSO-based optimizer at a real-time speed. Meanwhile, a Dynamic Prioritized Initialization (DPI) mechanism that adaptively initializes potential solutions for the optimization problem is established to further ameliorate the solution quality. Additionally, a relaxation strategy that facilitates the autonomous tuning of OkayPlan’s hyperparameters in dynamic environments is devised. Comprehensive experiments, including comparative evaluations, ablation studies, and applications to 3D physical simulation platforms, have been conducted to substantiate the efficacy of our approach. Results indicate that OkayPlan outstrips existing methods in terms of path safety, length optimality, and computational efficiency, establishing it as a potent GPP technique for dynamic environments. The video and code associated with this paper are accessible at https://github.com/XinJingHao/OkayPlan.

Enhanced path planning algorithm via hybrid WOA-PSO for differential wheeled mobile robots

This study introduces an enhanced algorithm for global path planning of Differential Wheeled Mobile Robots (DWMRs) that merges the Whale Optimization Algorithm (WOA) and Particle Swarm Optimization (PSO). This hybrid strategy, termed HWPSO, is designed to leverage WOA's exploration strength with PSO's efficient exploitation, specifically targeting the challenges of non-holonomic constraints in complex terrains. To validate the effectiveness of the proposed algorithm, its performance is evaluated across five diverse environments and compared against PSO, WOA, and Grey Wolf Optimization which is widely used for mobile robot path planning. Moreover, the comparison broadens to encompass four established environments from the literature where algorithms based on firefly, ant colony, A*, and other PSO variants have previously exhibited optimal performance. Additionally, a new environment is introduced to analyze the efficacy of the proposed approach for path planning for two DWMRs. Simulation results consistently demonstrate the superiority of the proposed HWPSO, manifesting performance improvements of up to 19.3% for path length reduction and up to 12.7% for DWMR travel duration reduction when compared to other methods. This underscores the efficacy of the proposed hybrid approach in achieving enhanced path planning outcomes for DWMRs in diverse scenarios.

LIFNS: Design of a novel Lidar-IMU fusion navigation system for AGVs in smart factories

Traditional Automated Guided Vehicle (AGV) robots commonly employ 2D plane navigation systems. However, with the expansion of AGV application scenarios and the increasing complexity of structures, the limitations of existing 2D navigation systems have become more pronounced, rendering them inadequate for addressing these challenges. To tackle this issue, this paper proposes a novel navigation system suitable for AGV robots composed of fused Lidar and Inertial Measurement Unit (IMU), named as Lidar-IMU Fusion Navigation System (LIFNS). LIFNS primarily comprises mapping, localization, and fused path planning modules. In the mapping module, a 3D point cloud map for precise 3D localization and a 2D grid map for path planning are constructed using multiple-line Lidar and IMU. For the localization module, a fusion localization approach is introduced, combining IMU data with Normal Distributions Transform (NDT) point cloud registration through Unscented Kalman Filtering (UKF). Finally, global path planning is executed using the A* algorithm on the grid map, while local path planning utilizes the Timed-Elastic Band (TEB) algorithm. The effectiveness and universality of LIFNS are validated through simulation experiments and real-world deployment tests. The experimental results demonstrate that LIFNS achieves centimeter-level accuracy in both mapping and localization, effectively alleviating the issues of low precision and significant limitations present in traditional AGV robots. This positions LIFNS with promising applications in enclosed settings such as smart factories, industrial parks, and healthcare facilities.

Research on A Global Path-Planning Algorithm for Unmanned Arial Vehicle Swarm in Three-Dimensional Space Based on Theta*–Artificial Potential Field Method

The current challenge in drone swarm technology is three-dimensional path planning and adaptive formation changes. The traditional A* algorithm has limitations, such as low efficiency, difficulty in handling obstacles, and numerous turning points, which make it unsuitable for complex three-dimensional environments. Additionally, the robustness of drone formations under the leader–follower mode is low, and effectively handling obstacles within the environment is challenging. To address these issues, this study proposes a virtual leader mode for drone formation flight and introduces a new Theta*–APF method for three-dimensional space drone swarm path planning. This algorithm optimizes the A* algorithm by transforming it into an omnidirectional forward Theta* algorithm. It also enhances the heuristic function by incorporating artificial potential field methods in a three-dimensional environment. Formation organization and control of UAVs is achieved using speed-control modes. Compared to the conventional A* algorithm, the Theta*–APF algorithm reduces the search time by about 60% and the trip length by 10%, in addition to the safer flight of the UAV formation, which is subject to artificial potential field repulsion by about 42%.

Improved genetic algorithm for mobile robot path planning in static environments

The genetic algorithm (GA) is a well-known meta-heuristic technique for addressing the static mobile robot global path planning (MRGPP) issue. Current GA, however, has certain shortcomings, such as inefficient population initialization and low-quality solutions. As an enhanced GA, a Linear Rank-based, or Clearance-based Probabilistic Road Map (CBPRM), technique is proffered to overcome these difficulties. The new model guides the population initialization process by using the fitness score of each cell in the environment, lowering the number of infeasible pathways created. Furthermore, a genetic operator combination is proposed to balance the global and local search and increase the quality of the optimum path created in terms of path length and safety. Two experiments were carried out to assess the suggested GA. The novel population initialization strategy was compared to two current models in the first experiment, and the findings revealed that the suggested approach greatly decreases the number of infeasible pathways created and the time required for the process. The ideal genetic operator combination was determined in the second experiment, and the results revealed that the suggested combination improves the quality of the optimal path created in fewer iterations. In summary, the proposed GA improves on previous models by proposing a novel population initialization method and combining numerous genetic operators. These alterations improve the quality of the optimum path and indicate the suggested model’s potential for solving the MRGPP challenge.

Global Dynamic Path Planning of AGV Based on Fusion of Improved A* Algorithm and Dynamic Window Method.

Designed to meet the demands of AGV global optimal path planning and dynamic obstacle avoidance, this paper proposes a combination of an improved A* algorithm and dynamic window method fusion algorithm. Firstly, the heuristic function is dynamically weighted to reduce the search scope and improve the planning efficiency; secondly, a path-optimization method is introduced to eliminate redundant nodes and redundant turning points in the path; thirdly, combined with the improved A* algorithm and dynamic window method, the local dynamic obstacle avoidance in the global optimal path is realized. Finally, the effectiveness of the proposed method is verified by simulation experiments. According to the results of simulation analysis, the path-planning time of the improved A* algorithm is 26.3% shorter than the traditional A* algorithm, the search scope is 57.9% less, the path length is 7.2% shorter, the number of path nodes is 85.7% less, and the number of turning points is 71.4% less. The fusion algorithm can evade moving obstacles and unknown static obstacles in different map environments in real time along the global optimal path.

An enhanced ant colony optimization algorithm for global path planning of deep-sea mining vehicles

Due to the complex variations in slope within deep-sea mining areas, effective path planning for mining vehicle operations is crucial for minimizing energy consumption. However, traditional ant colony algorithms (ACO) neglect the effect of a terrain slope in mining areas. Additionally, these algorithms exhibit limitations such as slow convergence and susceptibility to local optima. To address these issues, this study proposes an enhanced ant colony algorithm, called DYACO, for mining vehicle path optimization. This algorithm dynamically adjusts heuristic information, pheromone volatilization factor, pheromone update strategy, and state transition probability during the iterative process to enhance traditional ACO. Simulation experiments were conducted to comprehensively assess the proposed model, revealing that DYACO not only generates optimal solutions but also demonstrates significant advantages in terms of convergence speed and turning times. Furthermore, DYACO converts the time required for mining vehicles to traverse different slope regions into distances, then incorporating slope effects to path planning for deep-sea mining vehicles. In comparison to ACO, DYACO achieves a 15.3% reduction in the length of an optimal path and a 70.0% decrease in the number of turn times.

Traversable map construction and robust localization for unstructured road environments1

Intelligent vehicles require accurate identification of traversable road areas and the ability to provide precise and real-time localization data in unstructured road environments. To address these issues, we propose a system for traversable map construction and robust localization in unstructured road environments based on a priori knowledge. The proposed method performs traversable area segmentation on the LiDAR point cloud and employs a submap strategy to jointly optimize multiple frames of data to obtain a reliable and accurate point cloud map of the traversable area, which is then rasterized and combined with the vehicle kinematic model for global path planning. Then, it integrates priori map information and real-time sensor information to provide confidence and priori constraints to ensure the robustness of localization, and it fuses multi-sensor heterogeneous data to improve real-time localization. Experiments are conducted in a mining environment to evaluate the performance of the proposed method on an unstructured road. The experimental results demonstrate that the traversable map and localization results based on the proposed method can meet the requirements for autonomous vehicle driving on unstructured roads and provide reliable priori foundation and localization information for autonomous vehicle navigation.

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.

Research on dual robot collaboration method based on improved double ant colony algorithm

Purpose This study aims to propose an efficient dual-robot task collaboration strategy to address the issue of low work efficiency and inability to meet the production needs of a single robot during construction operations. Design/methodology/approach A hybrid task allocation method based on integer programming and auction algorithms, with the aim of achieving a balanced workload between two robots has been proposed. In addition, while ensuring reasonable workload allocation between the two robots, an improved dual ant colony algorithm was used to solve the dual traveling salesman problem, and the global path planning of the two robots was determined, resulting in an efficient and collision-free path for the dual robots to operate. Meanwhile, an improved fast Random tree rapidly-exploring random tree algorithm is introduced as a local obstacle avoidance strategy. Findings The proposed method combines randomization and iteration techniques to achieve an efficient task allocation strategy for two robots, ensuring the relative optimal global path of the two robots in cooperation and solving complex local obstacle avoidance problems. Originality/value This method is applied to the scene of steel bar tying in construction work, with the workload allocation and collaborative work between two robots as evaluation indicators. The experimental results show that this method can efficiently complete the steel bar banding operation, effectively reduce the interference between the two robots and minimize the interference of obstacles in the environment.

Path-Planning Strategy: Adaptive Ant Colony Optimization Combined with an Enhanced Dynamic Window Approach

Aiming to resolve the problems of slow convergence speed and inability to plan in real time when ant colony optimization (ACO) performs global path planning, we propose a path-planning method that improves adaptive ant colony optimization (IAACO) with the dynamic window approach (DWA). Firstly, the heuristic information function is modified, and the adaptive adjustment factor is added to speed up the algorithm’s convergence rate; secondly, elite ants and max–min ants systems are implemented to enhance the global pheromone updating process, and an adaptive pheromone volatilization factor is aimed at preventing the algorithm from enhancing its global search capabilities; then, the path optimization and withdrawal mechanism is utilized to enable smoother functioning and to avoid the deadlocks; finally, a new distance function is introduced in the evaluation function of DWA to the enhance real-time obstacle-avoidance ability. The simulation experiment results reveal that the path length of the IAACO can be shortened by 10.1% and 13.7% in contrast to the ACO. The iteration count can be decreased by 63.3% and 63.0%, respectively, leading to an enhanced optimization performance in global path planning and achieving dynamic real-time obstacle avoidance for local path planning.

Research on path planning technology of mobile robot in the restaurant scene based on A* and D* algorithm

Intelligent robots have found widespread applications in various fields including medical treatment, industrial production, and social services. These robots are specifically designed to fulfill diverse tasks in different environments, the design and control of these robots play a crucial role in ensuring their efficiency and security. In response to the high demand for fast and convenient service, the catering field is a crucial and promising application field for intelligent robots. This article is primarily focused on the robot in the restaurant scene where the robot could automatically deliver food to the customers, thus reducing the burden on human service providers. In this special environment, the delivery robot must possess the capability to identify its surroundings within the restaurant and autonomously calculate an obstacle-free path from the starting point to the desired destination without colliding with either obstacles or individuals. In this article, the restaurant scene is built in the Gazebo, and map scanning and conversion methods are utilized to enable the robots to recognize the environment effectively. Furthermore, A* and D* algorithms are employed in Python to achieve global and local path planning, respectively, thus validating the feasibility of the methods. The combination of these two algorithms demonstrates a successful path-planning application within the context of a restaurant scene.

A Deep Learning Approach to Lunar Rover Global Path Planning Using Environmental Constraints and the Rover Internal Resource Status

A Deep Learning Approach to Lunar Rover Global Path Planning Using Environmental Constraints and the Rover Internal Resource Status

Global Path Planning for Autonomous Ship Navigation Considering the Practical Characteristics of the Port of Ulsan

This study introduces global path planning for autonomous ships in port environments, with a focus on the Port of Ulsan, where various environmental factors are modeled for analysis. Global path planning is considered to take place from departure to berth, specifically accounting for scenarios involving a need to navigate via anchorage areas as waypoints due to unexpected increases in port traffic or when direct access to the berth is obstructed. In this study, a navigable grid for autonomous ships was constructed using land, breakwater, and water depth data. The modeling of the Port of Ulsan’s traffic lanes and anchorage areas reflects the port’s essential maritime characteristics for global path planning. In this study, an improved A* algorithm, along with grid-based path planning, was utilized to determine a global path plan. We used smoothing algorithms to refine the global paths for practical navigation, and the validation of these paths was achieved through conducting ship maneuvering simulations from model tests, which approximate real-world navigation in navigational simulation. This approach lays the groundwork for enhanced route generation studies in complex port environments.

Multi-Autonomous Mobile Robot traffic Management Based on Layered Costmaps and a modified Dijkstra's Algorithm

In recent times, the use of autonomous mobile robots (AMRs) has increased in many industries. As more AMRs roam the same area, traffic management becomes essential to prevent congestion and deadlocks. In related work, traffic management is often achieved using sophisticated, centralised planning approaches, albeit this often suffers from scalability issues. This paper therefore explores an approach where multi-AMR traffic management is achieved with layered costmaps and a modified Dijkstra's algorithm. This keeps the global path planner in the individual AMRs, thus not suffering scalability issues. To achieve multi-AMR coordination, traffic lanes and restricted areas are added to the AMRs’ global costmaps. Furthermore, the AMRs also use a modified Dijkstra's algorithm that supports implementation of traffic directions. A proof-of-concept solution is implemented in Robot Operating System 2 with Nav2 and Gazebo. The implemented solution was tested against a standard solution without any traffic management in three scenarios designed to provoke collisions. The results indicate that the implemented solution can prevent a set of collisions better than one without traffic management.