Mapping under changing trajectory estimates

Position estimation based on scan matching is a type of popular approaches for mobile robot localization in indoor office-like environments. Global scan matching and local scan matching are two basic position estimation problems. Global scan matching is subject to global localization for mobile robot and local scan matching is used to deal with tracking mobile robot position over time. Global localization based on scan matching is represented in this paper. A global map is built to represent whole environment feature and a local map is built to represent current range scan. Global map and local map consist of a lot of line segments. Complete line segment that represents a complete environment object is singled out and used to match between local map and global map. Line segments are sorted counterclockwise in two maps. This type of ordinal map improves the searching efficiency of matching and localization algorithm is timesaving. In addition, matching between current range scan and global map is based on relative position relationships of line segments in local and global map. Global localization based on relative position relationship avoids frequent coordinates transformation and lowers computational cost. All these techniques have been implemented on our mobile robot ATRVII equipped with 2D laser range scanner SICK.

In a multi-robot system, in which each of the robots constructs its own local map, it is necessary to perform the fusion of these maps into a global one. This task is normally performed in two different steps: by aligning the maps and then merging the data. This paper focusses on the first step: Map Alignment, which consists in obtaining the transformation between the local maps built independently. In this way, these local maps will have a common reference frame. In this paper, a collection of algorithms for solving the map alignment are analyzed under different conditions of noise in the data and intersection between local maps. This study is performed in a visual SLAM context, in which the robots construct landmark-based maps. The landmarks consist in 3D points captured from the environment and characterized by a visual descriptor.

Local Map Building for Mobile Robot Autonomous Navigation by Using a 2D Laser Range Sensor

H-SLAM: Hybrid direct–indirect visual SLAM

Indoor reconnaissance missions for unmanned aerial vehicles (UAVs) pose significant challenges in scene reconstruction, mapping, and environmental feature extraction. Relying on a single type of sensor often results in limited accuracy, increased susceptibility to environmental noise, and a lack of comprehensive spatial information. To address these issues, this study proposes a mapping method that combines light detection and ranging (LiDAR) and depth camera data. The method collects data from both LiDAR and a depth camera integrated on the UAV, then performs preprocessing on both data sources to construct local 3D maps using the real-time appearance-based mapping (RTAB-Map) algorithm. Subsequently, the local maps are merged using a filtering method to generate a detailed and complete global map. Real-time experiments conducted on Ubuntu 20.04 using the robot operating system (ROS) Noetic libraries demonstrate that this multi-sensor fusion approach provides richer and more comprehensive environmental information, thereby enhancing the effectiveness of mapping tasks in unknown indoor environments.

RGB-D cameras have become a popular sensor for Simultaneous Localization and Mapping (SLAM) because they can provide RGB and depth information at the same time. The spatial location of feature points of SLAM is obtained by its corresponding depth information from RGB-D sensors. However, the depth information of the feature at the edge of the object is very noisy, and the measurement is often inaccurate. At the same time, there is poor real-time performance, low accuracy, and much difficulties of dense construction in ORB-based Visual SLAM (visual SLAM, VSLAM). Therefore, an improved ORB features based SLAM framework with corresponding method using RGB-D data is proposed in this paper. We extract and match features with improved ORB. Then the local map is used to perform local optimization for pose estimation, and an efficient key frame screening method is designed. The proposed method effectively reduces errors, enhances robustness, and builds a dense map of the environment.

Simultaneous Localization and Mapping (SLAM) is one of the fundamental functionalities for intelligent mobile robots. Over the last few decades, numerous impressive SLAM systems have been developed, demonstrating commendable performance in specific scenarios. However, some challenges still remain unsolved, such as how to handle moving objects in complex environments and how to enable robots to gain a true understanding of their surroundings and perform advanced tasks. This paper proposes a visual SLAM system, YOLOv7-SLAM, designed for complex environments with strong robustness. YOLOv7-SLAM employs a multi-threaded approach with five parallel threads: tracking, semantic segmentation, local mapping, loop closure, and dense semantic mapping creation. YOLOv7-SLAM employs the YOLO object detection method to remove obstacles in complex scenes, reducing the impact of obstacles in the environment and significantly enhancing localization accuracy in complex environments. We conducted experiments using the TUM RGB-D dataset. The results show that YOLOv7-SLAM achieves an order of magnitude improvement in absolute trajectory accuracy compared to ORB-SLAM2, making it one of the most advanced SLAM systems for complex environments. Our experiments were validated using the TUM RGB-D dataset. The results showcase a notable enhancement in the absolute trajectory accuracy of YOLOv7-SLAM in comparison to ORB-SLAM2 [1]. It performs well in complex obstacle-rich environments.

Autonomous and safe robot navigation requires the capability to simultaneously building a map of the environment and a selflocalization of the robot itself. This is known as the SLAM (Simultaneous Localization and Mapping) problem. In such a context, omnidirectional camera looks like a very interesting sensor since it allows a full 360 degrees field of vision. Complexity of the SLAM methods dramatically increases when the size of the environment grows up. Conversely, accuracy and integrity of the estimation process cannot be guaranteed any more. In this paper, we present an efficient way to reduce the complexity of the algorithms thanks to the definition of local submaps. In contrast with other papers dealing with local maps, our main purpose is not only to reduce the computational cost but also to keep the global map correlated. A method to consistently share information between local maps is also provided. These methods are used in the context of the omnidirectional bearing-only SLAM. Due to the specificity of the model of projection, images provided by the omnidirectional cameras cannot be used in a SLAM method without taking some precaution. In this paper, we provide an original method for computing the covariance matrix taking into account this specificity. Finally, we provide a validation with real data in an indoor environment subject to large illumination changes.

This paper presents a modified version of HybridSLAM (HS) method using unscented Kalman filter to solve simultaneous localization and mapping problem. Instead of applying extended Kalman filter for SLAM (EKF-SLAM) to build the map of the environment, an unscented Kalman filter (UKF) was added to the HS algorithm. This would allow including higher order of non-linearity of the motion. The new method called Unscented HybridSLAM (UHS) is constructing the global map more accurately compare to the original HS and by employing the same constraint of local sub-map fusion technique, a more reliable solution to SLAM problem is achieved. The unscented Kalman filter takes advantage of both statistical and analytical linearization techniques to estimate the global map. The local map in the vicinity of the robot is estimated using FastSLAM and the local map is fused to the map using constrained local sub-map fusion technique. Unscented HybridSLAM uses a minimal set of chosen samples to approximate the posterior mean and covariance for a nonlinear system. The unscented HybridSLAM performance is compared to the original HybridSLAM and FastSLAM algorithms and it is shown that in case of severe nonlinearity, the proposed unscented HybridSLAM is outperforming current filters in terms of estimation of the path and map building.

This paper presents a laser-based pedestrian tracking system employing a group of mobile robots. Each robot detects pedestrians in its own laser scan images using an occupancy-grid-based method. It then tracks the pedestrians using Kalman filter and global-nearest-neighbor (GNN)-based data association. It also generates a local map using EKF-SLAM. Using inter-robot communication, the robots located near each other exchange information on tracked pedestrians and local maps. Tracking data are fused using the covariance intersection (CI) method, and a global map is built by merging the local maps. In our tracking method, all robots share the information with each other; hence, they can always recognize pedestrians who are invisible to another robot. The method is validated by the results of both indoor and outdoor experiments in which two pedestrians are tracked by three mobile robots. Our tracking system functions in a decentralized manner without any central server.

Multi-camera visual SLAM for autonomous navigation of micro aerial vehicles

This paper deals with the generation of safe tasks for displacement missions of a nonholonomic mobile robot in a mapped indoor environment. The goal of this study is to plan safe actions (path-following) as well as observations (we call it local maps federation [LMF]), leading the robot to configurations where pertinent features can be sensed, thus attaining best localization relative to its environment. A path-planning method dealing with uncertainties is proposed, where both uncertainties in localization and in control of a nonholonomic mobile robot are managed. Maps uncertainties are handled using the local map concept, which is introduced as a set of the best landmarks used for planning and executing robust motion movements. The safeness of the proposed method is due to the mixing between the planning phase and the navigation phase.

Traditional visual SLAM methods are built on the strong assumption that the system operates in static environments, with limited consideration of moving objects. This assumption often leads to significant performance degradation when dynamic elements are present. To mitigate the impact of moving objects and enhance both localization accuracy and mapping quality, we propose a visual SLAM framework that explicitly removes dynamic object interference from the visual odometry and mapping modules. First, we refine the data association process in visual odometry by introducing motion consistency constraints, which reduce incorrect feature matches and thereby improve pose estimation accuracy. At the same time, depth information from RGB-D sensors is used to validate potentially dynamic feature points. Second, within the mapping module, we formulate keyframe selection as a vertex cover problem to ensure the local representativeness of keyframes. This approach not only reduces mapping artifacts but also enables the comprehensive detection and removal of dynamic objects. Finally, experiments conducted on the TUM RGB-D dataset demonstrate that our system achieves higher accuracy, robustness, and stability compared to baseline methods.

Map building and localization are essential to an autonomous mobile robot system. A global topological map is commonly constructed from a global grid map using a Voronoi diagram. In this hierarchical method, however, the advantage of a topological map such as compactness may not be fully utilized. In this paper sensor data are used to build a local grid map from which a local topological map is created using a thinning method. The thinning method is an alternative of the Voronoi diagram. The local topological map is then updated to the global one. Localization based on the topological map is usually difficult, but additional nodes created by the thinning method can improve localization performance. Various experiments with a laser scanner demonstrate validity and feasibility of the proposed algorithms for map building and localization.

Current visual simultaneous localization and mapping (SLAM) systems have demonstrated commendable efficacy in static environments. However, the presence of dynamic objects in real-world settings frequently leads to system discrepancies, significantly impairing the accuracy and robustness of SLAM systems. Conventional visual SLAM approaches typically utilize epipolar constraints to mitigate the impact of outliers; nevertheless, they encounter limitations when confronted with a substantial number of dynamic or planar moving objects. To tackle these issues, this paper introduces a novel dynamic visual SLAM system, termed DEG-SLAM. Initially, the system employs the YOLOv5 object detection network to identify dynamic objects, subsequently relaying the semantic information to the tracking module. During the tracking phase, both semantic information and epipolar constraints are leveraged to filter out dynamic feature points. To address the challenges posed by the malfunctioning of epipolar constraints in degenerate scenes, DEG-SLAM incorporates a degenerate constraint mechanism aimed at further eliminating dynamic feature points. Furthermore, a reprojection constraint has been introduced to enhance the filtering of absent dynamic feature points that lie outside the detection boxes. Experimental findings reveal that DEG-SLAM significantly improves accuracy and robustness when compared to traditional ORB-SLAM3 in dynamic environments. The performance benefits of DEG-SLAM are particularly evident in degenerate scenarios, thereby affirming its practicality and reliability in complex settings.