Mobile Data-Mule Optimal Path Planning for Wireless Sensor Networks

This article is concerned with collecting stored sensor data from a static Wireless Sensor Network utilizing a group of mobile robots that act as data mules. In this scenario, the static sensor nodes’ locations are known a priori, and the overall optimization problem is formulated as a variation of the Traveling Salesman Subset-tour Problem (TSSP). The constraints that are taken into account include: (a) the pairwise distance between static nodes, (b) the maximum time interval between consecutive visits of each static node, (c) the service time that is required for the collection of the sensor data from the mobile element that visits this sensor node, and (d) the energy efficiency for the mobile nodes. The optimal mobile robot paths are computed using an enhanced Mobile Element Scheduling scheme. This scheme extracts the sequential paths of the mobile elements in an attempt to eliminate any sensor data loss.

Optimal path planning of a disinfection mobile robot against COVID-19 in a ROS-based research platform

Due to COVID-19 pandemic, there is an increasing demand for mobile robots to substitute human in disinfection tasks. New generations of disinfection robots could be developed to navigate in high-risk, high-touch areas. Public spaces, such as airports, schools, malls, hospitals, workplaces and factories could benefit from robotic disinfection in terms of task accuracy, cost, and execution time. The aim of this work is to integrate and analyse the performance of Particle Swarm Optimization (PSO) algorithm, as global path planner, coupled with Dynamic Window Approach (DWA) for reactive collision avoidance using a ROS-based software prototyping tool. This paper introduces our solution – a SLAM (Simultaneous Localization and Mapping) and optimal path planning-based approach for performing autonomous indoor disinfection work. This ROS-based solution could be easily transferred to different hardware platforms to substitute human to conduct disinfection work in different real contaminated environments.

Optimal Path Planning using Informed Probabilistic Road Map Algorithm

This study aims to propose a new path planning algorithm that can guarantee the optimal path solution. The method used is to hybridize the Probabilistic Road Map (PRM) algorithm with the Information Search Algorithm. This hybridization algorithm is called the Informed-PRM algorithm. There are two informed search methods used. The first method is the informed sampling through an ellipsoid subset whose eccentricity is dependent on the length of the shortest current solution that is successfully planned in that iteration. The second method is to use a local search algorithm. The basic PRM algorithm will be run in the first iteration. Since the second iteration, the generation of sample points in the PRM algorithm will be carried out based on information. The informed sampling method will be used to generate 50% of the sampling points. Meanwhile, the remaining number of sample points will be generated using a local search algorithm. Using several benchmark cases, we compared the performance of the Informed-PRM algorithm with the Rapidly Exploring Random Tree* (RRT*) and informed RRT* algorithm. The test results show that the Informed-PRM algorithm successfully constructs the nearly optimal path for all given cases. In producing the path, the time and path cost of the Informed-PRM algorithm is better than the RRT* and Informed RRT* algorithm. The Friedman test was then performed to check for the significant difference in performance between Informed-PRM with RRT* and Informed RRT*. Thus, the Informed-PRM algorithm can be implemented in various systems that require an optimal path planning algorithm, such as in the case of medical robotic surgery or autonomous vehicle systems.

Research on optimal path planning of indoor robot based on wireless sensor

Based on the work tasks and positioning characteristics of indoor robots, the environment is divided into grids, and wireless sensors are used to detect obstacles, and the density of obstacles in each grid is given. At the same time, the path planning algorithm is combined to realize the optimal path planning of indoor robot. The simulation results show that the wireless sensor network can realize the obstacle density detection, so that the robot can achieve fast optimal path planning and reach the target point.

Reinforcement learning-based radar-evasive path planning: a comparative analysis

This paper discusses the utilisation of deep reinforcement learning algorithms to obtain optimal paths for an aircraft to avoid or minimise radar detection and tracking. A modular approach is adopted to formulate the problem, including the aircraft kinematics model, aircraft radar cross-section model and radar tracking model. A virtual environment is designed for single and multiple radar cases to obtain optimal paths. The optimal trajectories are generated through deep reinforcement learning in this study. Specifically, three algorithms, namely deep deterministic policy gradient, trust region policy optimisation and proximal policy optimisation, are used to find optimal paths for five test cases. The comparison is carried out based on six performance indicators. The investigation proves the importance of these reinforcement learning algorithms in optimal path planning. The results indicate that the proximal policy optimisation approach performed better for optimal paths in general.