In this paper, a generic multi-sensor fusion framework is developed for the localization of intelligent vehicles and mobile robots. The localization framework is based on moving horizon estimation (MHE). Unlike the commonly used probabilistic filtering algorithms – for example, extended Kalman filter (EKF) and unscented Kalman filter (UKF) – MHE relies on solving successive least squares optimization problems over the innovation of multiple sensors’ measurements and a specific estimation horizon. In this paper, we present an efficient and generic multi-sensor fusion scheme, based on MHE. The proposed multi-sensor fusion scheme is capable of operating with different sensors’ rates, missing measurements, and outliers. Moreover, the proposed scheme is based on a multi-threading architecture to reduce its computational cost, making it more feasible for practical applications. The MHE fusion method is tested using simulated data as well as real experimental data sequences from an intelligent vehicle and a mobile robot combining measurements from different sensors to get accurate localization results. The performance of MHE is compared against that of UKF, where the MHE estimation results show superior performance.

Localization and Simultaneous Localization and Mapping (SLAM) is a fundamental module in any Autonomous vehicle or Autonomous Mobile Robot. In order for an autonomous system to be able to plan, navigate and perform tasks in its environment, it has to be able to localize itself in this environment. This led to a huge amount of research during the past few years in the field of localization and SLAM algorithms. These algorithms are composed of two main parts, a front-end responsible for extracting important features from the sensors data as well as data association. The second part, namely, the back-end is responsible for the probabilistic estimation step. The back-end of these algorithms is heavily dependent on the estimation theory and almost all the related work utilizes one estimation algorithms or another. Throughout this paper we review the most popular estimation algorithms used in localization and SLAM, we show the relations between different estimation methodologies and state some of the advantages and disadvantages for each of them.

The Unmanned Aerial Vehicles (UAVs) are receiving more focus in order to execute a wide variety of applications. Recently, several investigations are carried-on for the idea of Air Transportation System (ATSys). ATSys governs the elements and services that are correlated to the transportation of either passengers or cargo. Accordingly, in this paper, a novel UAV research platform is introduced, with the capabilities of air navigation and air transportation. The platform is called SkyOnyx, it has several on-board sensors for the environment perception, micro-controller for the navigation, and embedded computer for the overall control and processing all acquisition data. SkyOnyx is able to perform several localization techniques, multiple perception solutions, and robust high-level control. Furthermore, for functionality validation, several experiments were carried-out to verify the proposed Extended H∞ -based fusion algorithm for multiple input odometries. The obtained results prove the high performance of the proposed approach, along with the efficiency of the research platform.

Localization is the fundamental problem of intelligent vehicles. For a vehicle to autonomously operate, it first needs to locate itself in the environment. A lot of different odometries (visual, inertial, wheel encoders) have been introduced through the past few years for autonomous vehicle localization. However, such odometries suffers from drift due to their reliance on integration of sensor measurements. In this paper, the drift error in an odometry is modeled and a Drift Covariance Estimation (DCE) algorithm is introduced. The DCE algorithm estimates the covariance of an odometry using the readings of another on-board sensor which does not suffer from drift. To validate the proposed algorithm, several real-world experiments in different conditions as well as sequences from Oxford RobotCar Dataset and EU long-term driving dataset are used. The effect of the covariance estimation on three different fusion-based localization algorithms (EKF, UKF and EH-infinity) is studied in comparison with the use of constant covariance, which were calculated based on the true variance of the sensors being used. The obtained results show the efficacy of the estimation algorithm compared to constant covariances in terms of improving the accuracy of localization.

The accuracy of pose estimation from feature-based Visual Odometry (VO) algorithms is affected by several factors such as lighting conditions and outliers in the matched features. In this paper, a generic image processing pipeline is proposed to enhance the accuracy and robustness of feature-based VO algorithms. The pipeline consists of three stages, each addressing a problem that affects the performance of VO algorithms. The first stage tackles the lighting condition problem, where a filter called Contrast Limited Adaptive Histogram Equalization (CLAHE) is applied to the images to overcome changes in lighting in the environment. The second stage uses the Suppression via Square Covering (SSC) algorithm to ensure the features are distributed properly over the images. The last stage proposes a novel outliers rejection approach called the Angle-based Outlier Rejection (AOR) algorithm to remove the outliers generated in the feature matching process. The proposed pipeline is generic and modular and can be integrated with any type of feature-based VO (monocular, RGB-D, or stereo). The efficiency of the proposed pipeline is validated using sequences from KITTI (for stereo VO) and TUM (for RGB-D VO) datasets, as well as experimental sequences using an omnidirectional mobile robot (for monocular VO). The obtained results showed the performance gained by enhancing the accuracy and robustness of the VO algorithms without compromising on the computational cost using the proposed pipeline. The results are substantially better as opposed to not using the pipeline.

Localization system is considered one of the main components of an intelligent vehicle, and it presents a criticality from the safety and performance point of view, which requires high accuracy and precision. However, the performance of these systems is affected by sensor limitations and, more importantly, noise. The localization problem can be solved by fusing the information from multiple sensors, and the multisensor fusion problem is typically solved using probabilistic methods. Among these methods, Kalman filters are the most widely used. Although Kalman filters are the most widely used, the noise models of the sensors fused are assumed to be Gaussian, and the noise statistics must be known beforehand, leading to a sub-optimal performance in systems with unknown noise characteristics. Accordingly, this paper presents a robust localization system, based on the extended $\mathcal{H}_{\infty}$ filter, in order to solve the localization problem in intelligent self-driving vehicles by fusing different localization sources. The proposed approach is validated through several real-world experiments under different scenarios, and the performance of the proposed method is compared with the Extended Kalman filter under the same conditions. The obtained results demonstrate that the proposed approach outperforms the Extended Kalman filter, and validates the use of the extended $\mathcal{H}_{\infty}$ filter as a multisensor fusion approach for localization systems.