Received signal strength indicator (RSSI)-based fingerprinting is a widely used technique for indoor localization, but these methods suffer from high error rates due to various reflections, interferences, and noises. The use of disturbances in the magnetic field in indoor localization methods has gained increasing attention in recent years, since this technology provides stable measurements with low random fluctuations. In this paper, a novel fingerprinting-based indoor 2D positioning method, which utilizes the fusion of RSSI and magnetometer measurements, is proposed for mobile robots. The method applies multilayer perceptron (MLP) feedforward neural networks to determine the 2D position, based on both the magnetometer data and the RSSI values measured between the mobile unit and anchor nodes. The magnetic field strength is measured on the mobile node, and it provides information about the disturbance levels in the given position. The proposed method is validated using data collected in two realistic indoor scenarios with multiple static objects. The magnetic field measurements are examined in three different combinations, i.e., the measurements of the three sensor axes are tested together, the magnetic field magnitude is used alone, and the Z-axis-based measurements are used together with the magnitude in the X-Y plane. The obtained results show that significant improvement can be achieved by fusing the two data types in scenarios where the magnetic field has high variance. The achieved results show that the improvement can be above 35% compared to results obtained by utilizing only RSSI or magnetic sensor data.
Nowadays, an increasing usage of autonomous mobile robots in outdoor applications can be noticed. Identification of the terrain type is very important for efficient navigation. In this paper, a novel method is proposed for terrain classification in the case of wheeled mobile robots. The classification algorithm uses frequency domain features, which are extracted in fixed-size windows, and Multi-Layer Perceptron (MLP) neural networks as classifiers. Data from inertial sensors were collected for different outdoor terrain types using a prototype measurement system. The data of the accelerometer and the gyroscope were tested separately and together, and different processing window sizes were also applied. The achieved results show that above 99% classification efficiency can be achieved using the collected data.
Localization aims to provide the best estimate of the robot pose. It is a crucial algorithm in every robotics application, since its output directly determines the inputs of the robot to be controlled in its configuration space. In real world of engineering, the robot dynamics related measurements are subject to both uncertainties and disturbances. These error sources yield unreliable inferences of the robot state, which inherently result in wrong consensus about the appropriate control strategy to be applied. This outcome may drive the system out of stability and damage both the physical system and its environment. The localization algorithm captures the uncertainties with probabilistic approaches. Namely, the measurement processes are modelled along with their unreliability, moreover, the synergy of multiple information sources is formulated with the aim to calculate the most probable estimate of the robot pose. In essence, this algorithm is composed of two main parts, i.e., first the dynamics of the system is derived, and the corresponding uncertainties are initially predicted, next the additional sensor information is incorporated in the algorithm to refine the posterior estimate. This approach provides the state-of-the-art solution for the derivation of mobile robot poses in real applications.
Terrain classification provides valuable information for both control and navigation algorithms of wheeled mobile robots. In this paper, a novel online outdoor terrain classification algorithm is proposed for wheeled mobile robots. The algorithm is based on only time-domain features with both low computational and low memory requirements, which are extracted from the inertial and magnetic sensor signals. Multilayer perceptron (MLP) neural networks are applied as classifiers. The algorithm is tested on a measurement database collected using a prototype measurement system for various outdoor terrain types. Different datasets were constructed based on various setups of processing window sizes, used sensor types, and robot speeds. To examine the possibilities of the three applied sensor types in the application, the features extracted from the measurement data of the different sensors were tested alone, in pairs and fused together. The algorithm is suitable to operate online on the embedded system of the mobile robot. The achieved results show that using the applied time-domain feature set the highest classification efficiencies on unknown data can be above 98%. It is also shown that the gyroscope provides higher classification rates than the widely used accelerometer. The magnetic sensor alone cannot be effectively used but fusing the data of this sensor with the data of the inertial sensors can improve the performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.