This paper investigates the filtering techniques to enhance the accuracy of indoor localization for Autonomous Guided Vehicles (AGVs) using Ultra-Wideband (UWB) technology. A comprehensive comparative analysis of various filtering approaches, including the Kalman Filter (KF), Moving Average Filter (MA), Savitzky-Golay Filter (SG), Weighted Average Filter (WAF), and their combinations, are conducted. The primary focus of this paper is the integration of a Moving Average-Kalman Filter (MAKF) with an extended window size of 201. Experimental findings reveal significant performance differences among these filtering techniques. The most effective approach is the MAKF technique, achieving an accuracy of 85.13% and the lowest path deviation of 0.17 meters. Convers

Over recent decades, the field of mobile robot path planning has evolved significantly, driven by the pursuit of enhanced navigation solutions. The need to determine optimal trajectories within complex environments has led to the exploration of diverse path planning methodologies. This paper focuses on a specific subset: Bio-inspired Population-based Optimization (BPO) methodologies. BPO methods play a pivotal role in generating efficient paths for path planning. Amidst the abundance of optimization approaches over the past decade, only a fraction of studies has effectively integrated these methods into path planning strategies. This paper’s focus is on the years 2014-2023, reviewing BPO techniques applied to mobile robot path planning challenges. Contributions include a comprehensive review of recent BPO methods in mobile robot path planning, along with an experimental methodology to compare them under consistent conditions. This encompasses the same environment, initial conditions, and replicates. A multi-objective function is incorporated to evaluate optimization methods. The paper delves into key concepts, mathematical models, and algorithm implementations of examined optimization techniques. The experimental setup, methodology, and benchmarking performance results are discussed. Based on the proposed experimental methodology, Improved Sparrow Search Algorithm (ISpSA) shows the best cost improvement percentage (7.87%), but suffers in terms of optimization time. On the other hand, Whale Optimization Algorithm (WOA) has lesser improvement percentage of 6.05% but better optimization time. In conclusion, the standardized approach for benchmarking BPO algorithms provides useful insights into their strengths and challenges in mobile robot path planning.

This research analyses Pure-pursuit algorithm parameters for nonholonomic mobile robot navigation in unstructured and constrained space. The simulation-based experiment is limited to the mobile robot arrangement. The Look Ahead Distance parameter is adjusted so the mobile robot can navigate the predefined map closely following the waypoints. The optimal Look Ahead Distance value is combined with the VFH+ algorithm for obstacle avoidance. The method is enhanced by adding the λ weight so the robot returns to its waypoints after avoiding an obstacle. The investigation reveals that λ influences the mobile robot’s capacity to return to it

This paper presents a real-time simulation of a frontier exploration robot using a nonholonomic mobile robot’s kinematic model. In MATLAB, three heuristic-based frontier selection methods, namely Randomized Histogram Sector (RHS), Informed Randomized Point (IRP), and Histogram Clustering (HC), were simulated within two constrained space maps, one of which (Map 1) contained more obstacles than the other (Map 2). For the suggested frontier detection, the percentage of successfully mapped area against the ground truth map was determined to be 97.5% for Map 1 and 98.3% for Map 2. These results indicate that the proposed method yields great results. The HC approach is the most effective of the three proposed methods for both maps in terms of the time required to explore the maps and the efficiency of navigation inside the maps.

Indoor localization is important for robot navigation because it allows for robots to accurately determine their location and movement within a space. This is especially important for robots that are used in confined areas, like warehouses or homes, where there is not as much open space to navigate. Indoor localization gives robots the ability to plan their paths strategically and navigate around obstacles in a timely and efficient manner. Therefore, it is crucial for the indoor positioning system (IPS) to be stable and accurate. In this paper, we presented a fusion of non-complex filtering algorithms which combines Kalman filter with Moving Average (MA) filter in order to reduce localization error using Ultra-Wideband (UWB). The performance of the technique was measured against the conventional method of Kalman filtering, and it was found that the average error was reduced even more by the proposed strategy compared to the standard Kalman filtering approach.

This paper reviews the recent mobile robot application of Visual Simultaneous Localization and Mapping (V-SLAM) in GNSS-denied environments. V-SLAM is a heavily researched topic over the past two decades, and many of its algorithms have been adapted and applied on mobile robotics platforms. In a situation where GNSS signals are weak, the V-SLAM technique allows mobile robots to localize its’ position and resume navigation. This paper highlights the common usage of visual sensors in V-SLAM techniques and its corresponding mobile robot applications.

This research analyses Pure-pursuit algorithm parameters for nonholonomic mobile robot navigation in unstructured and constrained space. The simulation-based experiment is limited to the mobile robot arrangement. The Look Ahead Distance parameter is adjusted so the mobile robot can navigate the predefined map closely following the waypoints. The optimal Look Ahead Distance value is combined with the VFH+ algorithm for obstacle avoidance. The method is enhanced by adding the λ weight so the robot returns to its waypoints after avoiding an obstacle. The investigation reveals that λ influences the mobile robot’s capacity to return to its predetermined waypoints after avoiding an obstacle. Based on the simulation experiment, the optimal LAD value is 0.2 m, and the optimal λ value is 0.8.

Nowadays, indoor localization is an attractive topic for researchers since it can contribute a lot of benefit to manufacturing industry. Wireless communication unit is the most popular technology for localization. In this paper, the performance for training algorithm Levenberg-Marquardt and Bayesian Regularization was compared through neural network. The signal strength value of WLAN, which is one of the technologies for wireless communication, was measured according to their known coordinates. The input, which is the signal strength reading was then trained using neural network. The system then produced output, which is the predicted coordinates. By finding the difference between the predicted coordinates and the actual coordinates, the performance for both training algorithms can be determined.