Path Planning Approach Research Articles

Goal distance-based UAV path planning approach, path optimization and learning-based path estimation: GDRRT*, PSO-GDRRT* and BiLSTM-PSO-GDRRT*

The basic conditions for mobile robots to be autonomous are that the mobile robot localizes itself in the environment and knows the geometric structure of the environment (map). After these conditions are met, this mobile robot is given a specific task, but how the robot will navigate for this task is an important issue. Especially for Unmanned Aerial Vehicles (UAV), whose application has increased recently, path planning in a three-dimensional (3D) environment is a common problem. This study performs three experimental applications to discover the most suitable path for UAV in 3D environments with large and many obstacles. Inspired by Rapidly Random-Exploring Tree Star (RRT*), the first implementation develops the Goal Distance-based RRT* (GDRRT*) approach, which performs intelligent sampling taking into account the goal distance. In the second implementation, the path discovered by GDRRT* is shortened using Particle Swarm Optimization (PSO) (PSO-GDRRT*). In the final application, a network with a Bidirectional Long/Short Term Memory (BiLSTM) layer is designed for fast estimation of optimal paths found by PSO-GDRRT* (BiLSTM-PSO-GDRRT*). As a result of these applications, this study provides important novelties: GDRRT* converges to the goal faster than RRT* in large and obstacle-containing 3D environments. To generate groundtruth paths for training the learning-based network, PSO-GDRRT* finds the shortest paths relatively quickly. Finally, BiLSTM-PSO-GDRRT* provides extremely fast path planning for real-time UAV applications. This work is valuable for real-time autonomous UAV applications in a complex and large environment, as the new methods it offers have fast path planning capability.

A new approach for mobile robot path planning based on RRT algorithm

A novel route planning method based on the RRT algorithm is proposed in this study. To enhance the structure of the state tree, a general-purpose pseudorandom number generator is inserted into RRT. In addition, the proposed method includes a distance restriction that helps reduce the number of possible candidate nodes. MATLAB has been utilized to examine the efficacy of the proposed technique using three different types of maps. The simulation results demonstrate that the revised method is advantageous for route planning due to its superior convergence and efficacy over the original.

Path-Planning for Unmanned Aerial Vehicles with Environment Complexity Considerations: A Survey

Unmanned aerial vehicles (UAVs) have the potential to make a significant impact in a range of scenarios where it is too risky or too costly to rely on human labour. Fleets of autonomous UAVs, which complete tasks collaboratively while managing their basic flight and related tasks independently, present further opportunities along with research and regulatory challenges. Improvements in UAV construction and components, along with developments in embedded computing hardware, communication mechanisms and sensors which may be mounted on-board a UAV, are nearing the point where commercial deployment of fleets of autonomous UAVs will be technically possible. To fulfil this potential, UAVs will need to operate safely and reliably in complex and potentially dynamically changing environments with path-planning, obstacle sensing and collision avoidance paramount. This survey presents an original environment complexity classification and critically analyses the current state of the art in relation to UAV path-planning approaches. Moreover, it highlights the existing challenges in environment complexity modelling and representation, as well as path-planning approaches, and outlines open research questions together with future directions.

A path planning approach for unmanned surface vehicles based on dynamic and fast Q-learning

Path planning is a critical issue for unmanned surface vehicles (USVs), and an effective path-planning algorithm enables USVs to accomplish the mission. In this paper, a novel algorithm called dynamic and fast Q-learning (DFQL) to solve the path planning problem for USV in partially known maritime environments is proposed, which combines Q-learning with artificial potential field (APF) to initialize the Q-table to provide a priori knowledge from the environment to USV. To accelerate the convergence of Q-learning to the optimal solution and avoid USV's behavior of walking randomly in the early stage of exploration, the static and dynamic rewards are proposed to motivate the USV to move toward the target. Moreover, the performance of the proposed algorithm is verified with offline and online modes for USV in different environmental conditions. By comparing with the existing methods, it shows that the proposed approach is effective for path planning of USV.

Warehouse Path Planning Using Low-order Bézier Curves with Minimum-Time Optimization*

In this paper, low-order Bézier motion primitives are proposed for motion planning in corridor-constrained spaces, which is illustrated on a warehouse application. The proposed primitives are easily computed for given requirements (initial and final position, orientation and curvature). A new parametrization of the motion primitives is provided which allows an intuitive geometric interpretation. The combined path constructed from these primitives has a minimal number of turns, as third-order Bezier curves are used. At the same time, the combined path has continuous curvature. A path planning approach is proposed that finds the optimal combination of primitives that results in a minimum travel time while satisfying constraints on velocity, acceleration, and free space. To illustrate the applicability of the approach, a comparison with a typical predefined warehouse path and an existing advanced optimisation planner is provided and evaluated.

Hybrid Particle Swarm Optimization Approach for 3D Path Planning of UAV

Hybrid Particle Swarm Optimization Approach for 3D Path Planning of UAV

2D LiDAR Based Reinforcement Learning for Multi-Target Path Planning in Unknown Environment

Global path planning techniques have been widely employed in solving path planning problems, however they have been found to be unsuitable for unknown environments. Contrarily, the traditional Q-learning method, which is a common reinforcement learning approach for local path planning, is unable to complete the task for multiple targets. To address these limitations, this paper proposes a modified Q-learning method, called Vector Field Histogram based Q-learning (VFH-QL) utilized the VFH information in state space representation and reward function, based on a 2D LiDAR sensor. We compared the performance of our proposed method with the classical Q-learning method (CQL) through training experiments that were conducted in a simulated environment with a size of 400 square pixels, representing a 20-meter square map. The environment contained static obstacles and a single mobile robot. Two experiments were conducted: experiment A involved path planning for a single target, while experiment B involved path planning for multiple targets. The results of experiment A showed that VFH-QL method had 87.06% less training time and 99.98% better obstacle avoidance compared to CQL. In experiment B, VFH-QL method was found to have an average training time that was 95.69% less than that of the CQL method and 83.99% better path quality. The VFH-QL method was then evaluated using a benchmark dataset. The results indicated that the VFH-QL exhibited superior path quality, with efficiency of 94.89% and improvements of 96.91% and 96.69% over CQL and SARSA in the task of path planning for multiple targets in unknown environments.

Hybrid particle swarm optimisation approach for 3D path planning of UAV

Hybrid particle swarm optimisation approach for 3D path planning of UAV

Using a multi-robot system for improved path planning

Numerous terrestrial robotic platforms use computational power for path planning. These platforms typically use a vision system to identify obstacles and perform path planning. In cases where the vision systems are unable to function due to larger obstacles in the area, the paths are chosen as random functions of the given terrain to explore the environment and often results in missteps and moving away from the target location. In this research, we present a multi-robot system comprised of a terrestrial robot with a tethered aerial drone. By making use of the additive overhead view, the target location can be identified, and the exploration and path planning algorithms biased, subsequently reducing the computational cost, and creating a more efficient path planning approach. Focus has been placed on the control architecture of the system.

AFP tool path planning for manufacture of variable stiffness composites

Variable stiffness composites (VSC) demonstrate enhanced mechanical properties compared to conventional carbon fiber reinforced plastics (CFRP). Finite element analysis (FEA) is used to optimize layup directions, which need to be transformed into viable tool paths for automated fiber placement (AFP) processes. Manufacturing defects such as wrinkles, gaps, and overlaps should be handled. In this study, a novel path planning algorithm is developed for variable steering in AFP. The fiber directions are clustered and for each cluster a reference curve is fitted as B-Spline, where manufacturing constraints are considered. The proposed tool path planning approach is successfully demonstrated in a case study.

Noble Approach on Sensor Fused Bio Intelligent Path Optimisation and Single Stage Obstacle Recognition in Customized Mobile Agent

Optimized PTP (Point to Point) Navigation by customized mobile agent constitutes extensive research domain in Machine Intelligence. Distinct Literature survey confirms the proposal of SLAM (Simultaneous Localization And Mapping) mediated sensor usage for visual data collection in a particular GPS (Global Positioning System) - denied indoor environment. This has been further followed by fused data collection using multi sensor for obtaining long time and high precision localization and obstacle detection in MRN (Mobile Robot Navigation). This paper proposes an idea to incorporate machine learning module for data modeling so that the obstacle detection and identification results in relatively more precise, accurate and efficient. The comparative numerical analysis has been presented to establish the proposed methodology. Along with this, Fusion SLAM algorithm has been created and proposed which combines features of both 2D LiDAR (Light Detection And Ranging) and RGB-D (Red, Green, Blue Depth) SLAM, resulting in visual reference of combined detected periphery and reconstructed 3D depth of on-path obstacles. The aforesaid procedure is further extended with integration of Bio Intelligent path planning approach. Experimental analysis carried out with sample candidate functions with respect to concerned mobile robot and considered indoor environment has been presented which would prove to be important citation for further research in the domain of collision-free optimum MRN.

EFFECTIVE SOLUTIONS FOR COMMON PROBLEMS OF ARTIFICIAL POTENTIAL FIELD BASED PATH PLANNING ALGORITHMS FOR MOBILE ROBOTS

Abstract
 Autonomous Path Planning (APP) capability is one of the main factors determining the autonomous level of a mobile robot. Although different methods are used for APP in the literature, the path planning approach based on Artificial Potential Fields (APF) has a very common usage area with its modeling ease and computational performance. APF-based APP, which is a grid-based path planning approach, is usually performed by combining a repulsive and attractive component that models many basic motions with a certain equation and calculating the gradient of this potential field to obtain the vector field. In this study, the basic models used for APF-based APP are examined, and how they are realized and how the resultant potential field is produced are mentioned. Although APF-based APP approaches have advantages, they also have problems such as local minimum, obstacles positioned too close, oscillation, and targets positioned too close to obstacles. Within the scope of the study, these problems were defined one by one and the approaches suggested in the literature for the solution of these problems were mentioned in detail. As a result, it has been seen that to obtain an effective APF-based APP solution, it is necessary to generate a convolutional vector field, limit the fundamental potential fields with exponential functions, use virtual potential fields and perform models with harmonic functions.

Path Planning of Autonomous 3-D Scanning and Reconstruction for Robotic Multi-Model Perception System

Applying a three-dimensional (3-D) reconstruction from mapping-oriented offline modeling to intelligent agent-oriented environment understanding and real-world environment construction oriented to agent autonomous behavior has important research and application value. Using a scanner to scan objects is a common way to obtain a 3-D model. However, the existing scanning methods rely heavily on manual work, fail to meet efficiency requirements, and are not sufficiently compatible with scanning objects of different sizes. In this article, we propose a creative visual coverage path planning approach for the robotic multi-model perception system (RMMP) in a 3-D environment under photogrammetric constraints. To realize the 3-D scanning of real scenes automatically, we designed a new robotic multi-model perception system. To reduce the influence of image distortion and resolution loss in 3-D reconstruction, we set scanner-to-scene projective geometric constraints. To optimize the scanning efficiency, we proposed a novel path planning method under photogrammetric and kinematics constraints. Under the RMMP system, a constraints-satisfied coverage path could be generated, and the 3-D reconstruction from the images collected along the way was carried out. In this way, the autonomous planning of the pose of the end scanner in scanning tasks was effectively solved. Experimental results show that the RMMP-based 3-D visual coverage method can improve the efficiency and quality in 3-D reconstruction.

An indoor service area determination approach for pedestrian navigation path planning

ABSTRACT Indoor navigation has been studied for many years, but it still has many limitations. In current navigation, pedestrians need to tell navigation systems the destination, because it is one of the preconditions for path planning. However, in some indoor cases, pedestrians cannot specify a destination because they have no information about where it is or even cannot be sure if there is a desired one. We believe that determining a service area is a possible way to handle such cases. For example, a service area that can be reached within a 2-min walk. In this paper, we propose an indoor service area determination approach for pedestrian navigation path planning. We demonstrate this approach in a shopping mall with multi-floors. The results show that it can successfully compute the reachable spaces and thereby helping people to select and arrive at the most appropriate destination. This approach is also useful for other indoor navigation applications within public buildings like offices, airports, theaters, hospitals, and museums where pedestrians would like to make a choice between multiple facilities of the same type, such as printers, registration desks, ATMs, AED, garbage bins, even exits.

Humanoid robot path planning using memory-based gravity search algorithm and enhanced differential evolution approach in a complex environment

The present work focuses on the optimal path planning of humanoid robots in a rugged terrain using a hybrid-based improved gravitational search algorithm (IGSA) tuned with a differentially perturbed velocity (DV) approach. The primary IGSA suffers from the disadvantage of a lower convergence rate and the risk of getting trapped in optimal local conditions. The drawbacks are eliminated by employing a hybrid IGSA-DV path planning approach, which improves the memory and velocity updating scheme. The algorithm is designed to minimize the overall path length of the humanoid, from source to goal, in the minimal time possible. The humanoids, during their locomotion, coordinate with each other to avoid collisions in their journey. The robots make decisions based on the position of the various obstacles within the search space. So, path smoothness is also considered to ensure stability during the locomotion. The work is further focussed on optimizing the energy efficiency of the different joints of the humanoid while walking on even and uneven surfaces. The path planning is performed in real-world and simulation environments, and the results are then compared with the different existing, individual, and hybrid techniques. The comparison of the above approach revealed that the IGSA-DV algorithm showed an optimal outcome in terms of path length and time taken. Moreover, the percentage deviation in the path length and time in both the simulation and experimental environment was within 6%. The Petri-Net approach is implemented along with the proposed technique to avoid confusion among the robots during multiple robot navigations.

Perception, Path Planning, and Flight Control for a Drone-Enabled Autonomous Pollination System

The decline of natural pollinators necessitates the development of novel pollination technologies. In this work, we propose a drone-enabled autonomous pollination system (APS) that consists of five primary modules: environment sensing, flower perception, path planning, flight control, and pollination mechanisms. These modules are highly dependent upon each other, with each module relying on inputs from the other modules. In this paper, we focus on approaches to the flower perception, path planning, and flight control modules. First, we briefly introduce a flower perception method from our previous work to create a map of flower locations. With a map of flowers, APS path planning is defined as a variant of the Travelling Salesman Problem (TSP). Two path planning approaches are compared based on mixed-integer programming (MIP) and genetic algorithms (GA), respectively. The GA approach is chosen as the superior approach due to the vast computational savings with negligible loss of optimality. To accurately follow the generated path for pollination, we develop a convex optimization approach to the quadrotor flight control problem (QFCP). This approach solves two convex problems. The first problem is a convexified three degree-of-freedom QFCP. The solution to this problem is used as an initial guess to the second convex problem, which is a linearized six degree-of-freedom QFCP. It is found that changing the objective of the second convex problem to minimize the deviation from the initial guess provides improved physical feasibility and solutions similar to a general-purpose optimizer. The path planning and flight control approaches are then tested within a model predictive control (MPC) framework where significant computational savings and embedded adjustments to uncertainty are observed. Coupling the two modules together provides a simple demonstration of how the entire APS will operate in practice.

Obstacle-Avoidance Path-Planning Algorithm for Autonomous Vehicles Based on B-Spline Algorithm

To solve the problem of the real-time path-planning of autonomous vehicles for obstacle avoidance on structured roads, a path-planning approach based on the B-spline algorithm is proposed in this paper. Firstly, the mechanism of driver path planning is analyzed, and a dynamic risk-identification model based on the support vector machine is proposed. It combines the driver’s risk perception characteristics and a risk model. Then, the B-spline algorithm model is improved based on the risk-identification model. Furthermore, road features, road constraints and dynamic constraints are considered to further optimize the planning algorithm. To verify the path-planning approach proposed in this paper, a co-simulation experiment based on CarSim/Simulink is conducted. Results show that the improved algorithm is effective in static and dynamic obstacles avoidance. The algorithm can generate collision-free obstacle avoidance paths, and the paths meet the real-time requirements and dynamic constraints of obstacle avoidance scenarios. In addition, the proposed algorithm optimizes the path according to the driver’s operating characteristics, which can further improve the safety and comfort of autonomous vehicles.

Helix-HPSO approach for UAV path planning in a multi-building environment

Helix-HPSO approach for UAV path planning in a multi-building environment

Bale Collection Path Planning Using an Autonomous Vehicle with Neighborhood Collection Capabilities

This research was mainly focused on the evaluation of path planning approaches as a prerequisite for the automation of bale collection operations. A comparison between a traditional bale collection path planning approach using traditional vehicles such as tractors, and loaders with an optimized path planning approach using a new autonomous articulated concept vehicle with neighborhood reach capabilities (AVN) was carried out. Furthermore, the effects of carrying capacity on reduction in the working distance of the bale collection operation was also studied. It was concluded that the optimized path planning approach using AVN with increased carrying capacity significantly reduced the working distance for the bale collection operation and can thus improve agricultural sustainability, particularly within forage handling.

Risk-based path planning for autonomous underwater vehicles in an oil spill environment

Autonomous underwater vehicles (AUVs) are advanced platforms for detecting and mapping oil spills in deep water. However, their applications in complex spill environments have been hindered by the risk of vehicle loss. Path planning for AUVs is an effective technique for mitigating such risks and ensuring safer routing. Yet previous studies did not address path searching problems for AUVs based on probabilistic risk reasoning. This study aims to propose an offboard risk-based path planning approach for AUVs operating in an oil spill environment. A risk model based on the Bayesian network was developed for probabilistic reasoning of risk states given varied environmental observations. This risk model further assisted in generating a spatially-distributed risk map covering a potential mission area. An A*-based searching algorithm was then employed to plan an optimal-risk path through the constructed risk map. The proposed planner was applied in a case study with a Slocum G1 Glider in a real-world spill environment around Baffin Bay. Simulation results proved that the optimal-risk planner outperforms in risk mitigation while achieving competitive path lengths and mission efficiency. The proposed method is not constrained to AUVs but can be adapted to other marine robotic systems.