Fethi Demim

Simultaneous localization and mapping algorithm for unmanned ground vehicle with SVSF filter

Filtering strategies play an important role in estimation theory, and are used to extract knowledge of the true states typically from noisy measurements or observations made of the system. This paper describes a novel approach that combines the information given by an odometer and a laser range finder sensors to efficiently solve the Simultaneous Localization and Mapping (SLAM) problem of the Unmanned Ground Vehicle (UGV) and reconstruct a

An adaptive SVSF-SLAM algorithm to improve the success and solving the UGVs cooperation problem

2D

Cooperative SLAM for multiple UGVs navigation using SVSF filter

representation of the environment. In recent years, to solve the SLAM problem, many solutions have been proposed. To resolve this problem, the most commonly used approaches are the EKF-SLAM and the FASTSLAM. An accurate process and a model of observation are needed for the first approach, which is suffering the linearization problem. While the second one is not convenient and is not suitable for real time implementation. Therefore, a new state and parameter estimation method is introduced based on the smooth variable structure filter (SVSF) is proposed in this paper to solve the UGV SLAM problem. The SVSF is a relatively new estimation strategy based on sliding mode concepts, formulated in a predictor-corrector format. It has been shown to be very robust to modeling errors and uncertainties. In this work the SVSF-SLAM algorithm is implemented to construct a map of the environment and localize the UGV within this map. The proposed algorithm is validated and compared to the EKF-SLAM algorithm. Good results are obtained.

A new approach to improve the success and solving the UGVs Cooperation for SLAM Problem, using a SVSF Filter

Abstract This paper aims to present a Decentralised Cooperative Simultaneous Localization and Mapping (DCSLAM) solution based on 2D laser data using an Adaptive Covariance Intersection (ACI). The ACI-DCSLAM algorithm will be validated on a swarm of Unmanned Ground Vehicles (UGVs) receiving features to estimate the position and covariance of shared features before adding them to the global map. With the proposed solution, a group of (UGVs) will be able to construct a large reliable map and localise themselves within this map without any user intervention. The most popular solutions to this problem are the EKF-SLAM, Nonlinear H-infinity SLAM and the FAST-SLAM. The former suffers from two important problems which are the poor consistency caused by the linearization problem and the calculation of Jacobian. The second solution is the which is a very promising filter because it doesn’t make any assumption about noise characteristics, while the latter is not suitable for real time implementation. Therefore, a new alternative solution based on the smooth variable structure filter (SVSF) is adopted. Cooperative adaptive SVSF-SLAM algorithm is proposed in this paper to solve the UGVs SLAM problem. Our main contribution consists in adapting the SVSF filter to solve the Decentralised Cooperative SLAM problem for multiple UGVs. The algorithms developed in this paper were implemented using two mobile robots Pioneer , equiped with 2D laser telemetry sensors. Good results are obtained by the Cooperative adaptive SVSF-SLAM algorithm compared to the Cooperative EKF/-SLAM algorithms, especially when the noise is colored or affected by a variable bias. Simulation results confirm and show the efficiency of the proposed algorithm which is more robust, stable and adapted to real time applications.

\(NH\infty \)-SLAM Algorithm for Autonomous Underwater Vehicle

ABSTRACT The aim of this paper is to present a cooperative simultaneous localization and mapping (CSLAM) solution based on a laser telemeter. The proposed solution gives the opportunity to a group of unmanned ground vehicles (UGVs) to construct a large map and localize themselves without any human intervention. Many solutions proposed to solve this problem, most of them are based on the sequential probabilistic approach, based around Extended Kalman Filter (EKF) or the Rao-Blackwellized particle filter. In our work, we propose a new alternative to avoid these limitations, a novel alternative solution based on the smooth variable structure filter (SVSF) to solve the UGV SLAM problem is proposed. This version of SVSF-SLAM algorithm uses a boundary layer width vector and does not require covariance derivation. The new algorithm has been developed to implement the SVSF filter for CSLAM. Our contribution deals with adapting the SVSF to solve the CSLAM problem for multiple UGVs. The algorithms developed in this work were implemented using a swarm of mobile robots Pioneer 3–AT. Two mapping approaches, point-based and line-based, are implemented and validated experimentally using 2D laser telemeter sensors. Good results are obtained by the Cooperative SVSF-SLAM algorithm compared with the Cooperative EKF-SLAM.

3D Polynomial Interpolation Based Local Binary Descriptor

This paper aims to present a Decentralized Cooperative Simultaneous Localization and Mapping (DC-SLAM) solution based on a laser telemeter using a Covariance Intersection (CI). The CI will run in the UGVs receiving features to estimate the position and covariance of shared features before adding them to the global map. With the proposed solution, a group of Unmanned Ground Vehicles (UGVs) will be able to construct a large reliable map and localize themselves within this map without any user intervention. The most popular solutions of this problem are the EKF-SLAM and the FAST-SLAM, the former suffers from two important problems, which are the calculation of Jacobeans and the linear approximations to the nonlinear models, and the latter is not suitable for real time implementation. Therefore, a new alternative solution based on the smooth variable structure filter (SVSF). Cooperative SVSF-SLAM algorithm is proposed in this paper to solve the UGVs SLAM problem. Our main contribution consists in adapting the SVSF filter to solve the Decentralized Cooperative SLAM problem for multiple UGV. The algorithms developed in this paper were implemented using two mobile robots Pioneer 3-AT, using 2D laser telemeter sensors. Good results are obtained by the Cooperative Adaptive SVSF-SLAM comparing to the Cooperative EKF-SLAM especially when the noise is colored or affected by a variable bias. Simulation results confirm and show the efficiency of our proposed approaches.1

Visual SVSF-SLAM Algorithm Based on Adaptive Boundary Layer Width

This paper describes an approach that combines the navigation data given by a Doppler Velocity Logs (DVL), the MTi Motion Reference Unit (MRU) and a Mechanically Scanned Imaging Sonar (MSIS) as a principal sensor to efficiently solve underwater Simultaneous Localization and Mapping (SLAM) problem in structured environments such as marine platforms, harbors, or dams, etc. The MSIS has been chosen of its capacity to produce a rich representation of the environment. In recent years, to solve the SLAM Autonomous Underwater Vehicle (AUV) problem, very few solutions have been proposed. Our contribution has introduced a method based on the Nonlinear H-infinity filter \((NH\infty )\) to solve the SLAM-AUV problem. In this work, the \(NH\infty \)-SLAM algorithm is implemented to construct a map in partially structured environments and localize the AUV within this map. The data-set used in this paper are taken from the experiments carried out in a marina located in the Costa Brava (Spain) with the Ictineu AUV which is necessary to test different SLAM algorithms. The validation of the proposed algorithm through simulation in offline is presented and compared to the EKF-SLAM algorithm. The \(NH\infty \)-SLAM algorithm provides an accurate estimate than EKF-SLAM and good results were obtained.

Robust SVSF-SLAM for Unmanned Vehicle in Unknown Environment

Many efforts are devoted to develop binary descriptors due to their low complexity, and flexibility in case of embedded systems. Almost all works on binary descriptor conception didn’t exploit all information of a given patch; they just involved pixels intensities into binary test process. This kind of solution lack efficiency on patch description. In this paper, we propose to design a new descriptor based on 3D polynomial interpolation by used pixels intensities. We must take into account geometric positions of pixels. We suggest to divide the patch into equal grid cells (sub patches). Each sub patch undergoes a dimension augmentation. It becomes a 3-dimensional vector by considering intensities values as the third dimension. Based on 3D polynomial interpolation, we approximate the point cloud by a surface. This step is followed by a binary tests between all coefficients of polynomials situated in neighborhoods. Our method shows a considerable discrimination in case of high similarity. The results of our approach are evaluated on a well-known benchmark dataset exhibit a considerable robustness and reliability in front of severe changes. A computation costing is reported in the end of results section.

A new adaptive smooth variable structure filter SLAM algorithm for unmanned vehicle

This work presents a solution to the Simultaneous Localization and Mapping (SLAM) problem of Unmanned Ground Vehicle (UGV) supported by a stereovision camera. There are many ways to approach this problem, mostly based on the sequential probabilistic process. The EKF-SLAM algorithm is one popular solution based on Extended Kalman Filter (EKF) to solve this problem that struggles with Jacobians’ calculation. FAST-SLAM is another popular algorithm based on the Rao-Blackwellized particle filter that has issues with real-time implementation. As a means to ameliorate the SLAM solution limitations, especially when the process and observation models contain uncertain parameters, a new adaptive Boundary Layer With algorithm based on the Smooth Variable Structure Filter (ASVSF) is proposed to solve the UGV visual SLAM problem. Hence, the adaptive SVSF-SLAM algorithm is proposed with an original formulation. This algorithm was implemented on Pioneer 3-AT mobile robot, using a stereo vision sensor in 3D. Simulation results show efficiency and give an advantage face modeling uncertainties and noises and it has significantly improved the performance of the estimation process.