Towards Design of an Efficient Sensing Data Acquisition scheme for UAVs-assisted Wireless Sensor Networks

2022 ◽  
Vol 13 (2) ◽  
pp. 0-0
Keyword(s):  
Path Planning ◽  
Data Acquisition ◽  
Large Scale ◽  
Cluster Formation ◽  
Optimal Path ◽  
Research Work ◽  
Planning Problem ◽  
Sensing Data ◽  
Planning Algorithm ◽  
Load Balanced

This paper investigates sensing data acquisition issues from large-scale hazardous environments using UAVs-assisted WSNs. Most of the existing schemes suffer from low scalability, high latency, low throughput, and low service time of the deployed network. To overcome these issues, we considered a clustered WSN architecture in which multiple UAVs are dispatched with assigned path knowledge for sensing data acquisition from each cluster heads (CHs) of the network. This paper first presents a non-cooperative Game Theory (GT)-based CHs selection algorithm and load balanced cluster formation scheme. Next, to provide timely delivery of sensing information using UAVs, hybrid meta-heuristic based optimal path planning algorithm is proposed by combing the best features of Dolphin Echolocation and Crow Search meta-heuristic techniques. In this research work, a novel objective function is formulated for both load-balanced CHs selection and for optimal the path planning problem. Results analyses demonstrate that the proposed scheme significantly performs better than the state-of-art schemes.

Optimal Path Planning Using Swarm Intelligence Based Hybrid Techniques

2019 ◽  
Vol 16 (9) ◽  
pp. 3717-3727
Author(s):  
Monica Sood ◽  
Sahil Verma ◽  
Vinod Kumar Panchal ◽  
Kavita
Keyword(s):  
Path Planning ◽  
Swarm Intelligence ◽  
Optimal Path ◽  
Research Work ◽  
Bat Algorithm ◽  
Cuckoo Search ◽  
Planning Problem ◽  
Optimal Path Planning ◽  
Hybrid Techniques ◽  
Different Types

The planning of optimal path is an important research domain due to vast applications of optimal path planning in the robotics, simulation and modeling, computer graphics, virtual reality estimation and animation, and bioinformatics. The optimal path planning application demands to determine the collision free shortest and optimal path. There can be numerous possibilities that to find the path with optimal length based on different types of available obstacles during the path and different types of workspace environment. This research work aims to identify the optimum path from the initial source-point to final point for the unknown workspace environment consists of static obstacles. For this experimentation, swarm intelligence based hybrid concepts are considered as the work collaboration and intelligence behavior of swarm agents provides the resourceful solution of NP hard problems. Here, the hybridization of concepts makes the solution of problem more efficient. Among swarm intelligence concepts, cuckoo search (CS) algorithm is one of the efficient algorithms due to clever behavior and brood parasitic property of cuckoo birds. In this research work, two hybrid concepts are proposed. First algorithm is the hybridized concept of cuckoo search with bat algorithm (BA) termed as CS-BAPP. Another algorithm is the hybridized concept of cuckoo search with firefly algorithm (FA) termed as CS-FAPP. Both algorithms are initially tested on the benchmarks functions and applied to the path planning problem. For path planning, a real time dataset area of Alwar region situated at Rajasthan (India) is considered. The selected region consists of urban and dense vegetation land cover features. The results for the optimal path planning on Alwar region are assessed using the evaluation metrics of minimum number of iterations, error rate, success rate, and simulation time. Moreover, the results are also compared with the individual FA, BA, and CS along with the comparison of hybrid concepts.

scholarly journals Review on path planning algorithm for unmanned aerial vehicles

2021 ◽  
Vol 24 (2) ◽  
pp. 1017
Author(s):  
Nurul Saliha Amani Ibrahim ◽  
Faiz Asraf Saparudin
Keyword(s):  
Path Planning ◽  
Unmanned Aerial Vehicles ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Optimal Path ◽  
Computation Time ◽  
Planning Problem ◽  
Aerial Vehicles ◽  
Planning Algorithm ◽  
Path Planning Algorithm

The path planning problem has been a crucial topic to be solved in autonomous vehicles. Path planning consists operations to find the route that passes through all of the points of interest in a given area. Several algorithms have been proposed and outlined in the various literature for the path planning of autonomous vehicle especially for unmanned aerial vehicles (UAV). The algorithms are not guaranteed to give full performance in each path planning cases but each one of them has their own specification which makes them suitable in sophisticated situation. This review paper evaluates several possible different path planning approaches of UAVs in terms optimal path, probabilistic completeness and computation time along with their application in specific problems.

scholarly journals Local path planning for mobile robots based on intermediate objectives

Robotica ◽  
2014 ◽  
Vol 33 (4) ◽  
pp. 1017-1031 ◽  
Author(s):  
Yingchong Ma ◽  
Gang Zheng ◽  
Wilfrid Perruquetti ◽  
Zhaopeng Qiu
Keyword(s):  
Path Planning ◽  
Mobile Robots ◽  
Autonomous Navigation ◽  
Optimal Path ◽  
Kinematic Model ◽  
Planning Problem ◽  
Planning Algorithm ◽  
Local Path ◽  
Velocity Constraints ◽  
Horizon Planning

SUMMARYThis paper presents a path planning algorithm for autonomous navigation of non-holonomic mobile robots in complex environments. The irregular contour of obstacles is represented by segments. The goal of the robot is to move towards a known target while avoiding obstacles. The velocity constraints, robot kinematic model and non-holonomic constraint are considered in the problem. The optimal path planning problem is formulated as a constrained receding horizon planning problem and the trajectory is obtained by solving an optimal control problem with constraints. Local minima are avoided by choosing intermediate objectives based on the real-time environment.

An Advanced Quantum Optimization Algorithm for Robot Path Planning

2019 ◽  
Vol 29 (08) ◽  
pp. 2050122
Author(s):  
Liming Gao ◽  
Rong Liu ◽  
Fei Wang ◽  
Weizong Wu ◽  
Baohua Bai ◽  
...  
Keyword(s):  
Path Planning ◽  
Large Scale ◽  
Optimization Problems ◽  
Dynamic Environment ◽  
Planning Problem ◽  
Robot Path Planning ◽  
Computationally Efficient ◽  
Planning Algorithm ◽  
Scale Optimization ◽  
Robot Path

In this paper, a new robot path planning algorithm based on Quantum-inspired Evolutionary Algorithm (QEA) is proposed. QEA is an advanced evolutionary computing scheme with the quantum computing features such as qubits and superposition. It is suitable for solving large scale optimization problems. The proposed QEA algorithm works in the discretized environment, and approximates the optimal robot planing path in a highly computationally efficient fashion. The simulation results indicate that the proposed QEA algorithm is suitable for both complex static and dynamic environment and considerably outperforms the conventional genetic algorithm (GA) for solving the robot path planning problem. Our algorithm runs in only about 2[Formula: see text]s, which demonstrates that it can well tackle the optimization problem in robot path planning.

scholarly journals An Efficient Path Planning Algorithm for Networked Robots using Modified Optimization Algorithm

2019 ◽  
Vol 8 (12) ◽  
pp. 2738-2743
Keyword(s):  
Path Planning ◽  
Optimization Algorithm ◽  
Optimal Path ◽  
Object Identification ◽  
Planning Problem ◽  
Networked Robots ◽  
Design Choice ◽  
Planning Algorithm ◽  
3D Cnn ◽  
Path Planning Algorithm

Path planning has played a significant role in major numerous decision-making techniques through an automatic system involved in numerous military applications. In the last century, pathfinding and generation were carried out by multiple intelligent approaches. It is very difficult in pathfinding to reduce energy. Besides suggesting the shortest path, it has been found that optimal path planning. This paper introduces an efficient path planning algorithm for networked robots using modified optimization algorithms in combination with the η3 -splines. A new method has employed a cuckoo optimization algorithm to handle the mobile robot path planning problem. At first, η3 - splines are combined so an irregular set of points can be included alongside the kinematic parameters chosen to relate with the development and the control of mobile robots. The proposed algorithm comprises of adaptive random fluctuations (ARFs), which help to deal with the very much manageable neighborhood convergence. This algorithm carries out the process of accurate object identification along with analyzing the influence of different design choice by developing a 3D CNN architecture to determine its performance. Besides offering classification in real-time applications, the proposed algorithm outperforms the performance of state of the art in different benchmarks

A Multi-Objective Path Planning Algorithm for Mobile Robots Based on Cellular Automata

2015 ◽  
Author(s):  
Yousef Naranjani ◽  
Jian-Qiao Sun
Keyword(s):  
Path Planning ◽  
Optimization Problems ◽  
Optimal Path ◽  
Planning Problem ◽  
Robot Path Planning ◽  
Maximum Slope ◽  
Multi Objective ◽  
Planning Algorithm ◽  
Elevation Changes ◽  
Robot Path

Many real-world applications of robot path planning involves not only finding the shortest path, but also achieving some other objectives such as minimizing fuel consumption or avoiding danger areas. This paper introduces a 2D path planning scheme that solves a multi-objective path planning problem on a 3D terrain. This allows the controller to pick the most suitable path among a set of optimal paths. The algorithm generates a cellular automaton for the terrain based on the objectives by applying various weighting factors via an evolutionary algorithm and finds the optimal path between the start point and the goal for each set of parameters considering static obstacles and maximum slope constraints. All the final trajectories share the same characteristic that they are non-dominated with respect to the rest of the set in the Multi-Objective Optimization Problems (MOP) context. The objectives considered in this study includes the path length, the elevation changes and avoiding the radars. Testing the algorithm on several problems showed that the method is very promising for mobile robot path planning applications.

A Geometric Path-Planning Algorithm in Cluttered Planar Environments Using Convex Hulls

2018 ◽  
Author(s):  
Nafiseh Masoudi ◽  
Georges Fadel
Keyword(s):  
Path Planning ◽  
Optimal Path ◽  
Visibility Graph ◽  
Convex Hulls ◽  
Planning Problem ◽  
Wire Routing ◽  
Visibility Algorithm ◽  
Planning Algorithm ◽  
Global Optimal ◽  
Path Planning Algorithm

The problem of finding a collision free path in an environment occupied by obstacles, known as path planning, has many applications in design of complex systems such as wire routing in automobile assemblies or motion planning for robots. Developing the visibility graph of the workspace is among the first techniques to address the path-planning problem. The visibility algorithm is efficient in finding the global optimal path. However, it is computationally expensive as it explores the entire workspace of the problem to create all non-intersecting segments of the graph. In this paper, we propose an algorithm based on the notion of convex hulls to generate the partial visibility graph from a given start point to a goal point in a 2D workspace cluttered with a number of disjoint polygonal convex or concave obstacles. The algorithm facilitates the attainment of the shortest path in a planar workspace while reducing the size of the visibility graph to explore.

scholarly journals Autonomous Vehicle Path Planning using Q-Learning

2021 ◽  
Vol 2128 (1) ◽  
pp. 012018
Author(s):  
Mohammed M S Ibrahim ◽  
Mostafa Rostom Atia ◽  
MW Fakhr
Keyword(s):  
Path Planning ◽  
Autonomous Vehicle ◽  
Optimal Path ◽  
Lookup Table ◽  
Planning Problem ◽  
Training Time ◽  
Q Learning ◽  
Starting Position ◽  
Planning Algorithm ◽  
Path Planning Problem

Abstract Path planning is vital in autonomous vehicle technology, from robots to self-driving cars and driverless trucks, it is impossible to navigate without a proper path planning algorithm, various algorithms exist Q-learning being one of them. Q-learning is used extensively in discrete applications as it is effective in finding solutions to these problems. This research investigates the possibility of using Q-learning for solving the local path planning problem with obstacle avoidance. Q-learning is split into two phases, the first being the training phase, and the second being the application phase. During training, Q-learning requires exponentially increasing training time based on the system’s state space. However, when Q-learning is applied it becomes as simple as a lookup table which allows it to run on even the simplest microcontrollers. Two simulations are conducted with varying environments. One to showcase the ability to learn the optimal path, the other to showcase the ability for learning navigation in variable environments. The first simulation was run on a static environment with one obstacle, with enough training episodes, Q-learning could solve the path planning problem with minimal movement steps. The second simulation focuses on a randomized environment, obstacles and the agent’s starting position are randomly chosen at the start of every episode. During testing, Q-learning was able to find a path to the target when a path did exist, as It was possible in certain configurations for the vehicle to be stuck in between obstacles with no feasible path or solution.

scholarly journals Deep Reinforcement Learning-Based Path Planning for Multi-Arm Manipulators with Periodically Moving Obstacles

2021 ◽  
Vol 11 (6) ◽  
pp. 2587
Author(s):  
Evan Prianto ◽  
Jae-Han Park ◽  
Ji-Hun Bae ◽  
Jung-Su Kim
Keyword(s):  
Path Planning ◽  
Optimal Path ◽  
Training Data ◽  
Planning Problem ◽  
Position Information ◽  
Moving Obstacles ◽  
Dimensional Property ◽  
Experience Replay ◽  
Planning Algorithm ◽  
Finite Time Horizon

In the workspace of robot manipulators in practice, it is common that there are both static and periodic moving obstacles. Existing results in the literature have been focusing mainly on the static obstacles. This paper is concerned with multi-arm manipulators with periodically moving obstacles. Due to the high-dimensional property and the moving obstacles, existing results suffer from finding the optimal path for given arbitrary starting and goal points. To solve the path planning problem, this paper presents a SAC-based (Soft actor–critic) path planning algorithm for multi-arm manipulators with periodically moving obstacles. In particular, the deep neural networks in the SAC are designed such that they utilize the position information of the moving obstacles over the past finite time horizon. In addition, the hindsight experience replay (HER) technique is employed to use the training data efficiently. In order to show the performance of the proposed SAC-based path planning, both simulation and experiment results using open manipulators are given.

scholarly journals A 2D Optimal Path Planning Algorithm for Autonomous Underwater Vehicle Driving in Unknown Underwater Canyons

2021 ◽  
Vol 9 (3) ◽  
pp. 252
Author(s):  
Yushan Sun ◽  
Xiaokun Luo ◽  
Xiangrui Ran ◽  
Guocheng Zhang
Keyword(s):  
Path Planning ◽  
Obstacle Avoidance ◽  
Autonomous Underwater Vehicles ◽  
Optimal Path ◽  
Small Scale ◽  
Target Point ◽  
Safe Driving ◽  
Policy Gradient ◽  
Planning Algorithm ◽  
Path Planning Algorithm

This research aims to solve the safe navigation problem of autonomous underwater vehicles (AUVs) in deep ocean, which is a complex and changeable environment with various mountains. When an AUV reaches the deep sea navigation, it encounters many underwater canyons, and the hard valley walls threaten its safety seriously. To solve the problem on the safe driving of AUV in underwater canyons and address the potential of AUV autonomous obstacle avoidance in uncertain environments, an improved AUV path planning algorithm based on the deep deterministic policy gradient (DDPG) algorithm is proposed in this work. This method refers to an end-to-end path planning algorithm that optimizes the strategy directly. It takes sensor information as input and driving speed and yaw angle as outputs. The path planning algorithm can reach the predetermined target point while avoiding large-scale static obstacles, such as valley walls in the simulated underwater canyon environment, as well as sudden small-scale dynamic obstacles, such as marine life and other vehicles. In addition, this research aims at the multi-objective structure of the obstacle avoidance of path planning, modularized reward function design, and combined artificial potential field method to set continuous rewards. This research also proposes a new algorithm called deep SumTree-deterministic policy gradient algorithm (SumTree-DDPG), which improves the random storage and extraction strategy of DDPG algorithm experience samples. According to the importance of the experience samples, the samples are classified and stored in combination with the SumTree structure, high-quality samples are extracted continuously, and SumTree-DDPG algorithm finally improves the speed of the convergence model. Finally, this research uses Python language to write an underwater canyon simulation environment and builds a deep reinforcement learning simulation platform on a high-performance computer to conduct simulation learning training for AUV. Data simulation verified that the proposed path planning method can guide the under-actuated underwater robot to navigate to the target without colliding with any obstacles. In comparison with the DDPG algorithm, the stability, training’s total reward, and robustness of the improved Sumtree-DDPG algorithm planner in this study are better.

Sign in / Sign up

Export Citation Format

Share Document