Localization is one of the most important issues in mobile robotics, especially when an autonomous mobile robot performs a navigation task. The current and popular occupancy grid map, based on 2D LiDar simultaneous localization and mapping (SLAM), is suitable and easy for path planning, and the adaptive Monte Carlo localization (AMCL) method can realize localization in most of the rooms in indoor environments. However, the conventional method fails to locate the robot when there are similar and repeated geometric structures, like long corridors. To solve this problem, we present Text-MCL, a new method for robot localization based on text information and laser scan data. A coarse-to-fine localization paradigm is used for localization: firstly, we find the coarse place for global localization by finding text-level semantic information, and then get the fine local localization using the Monte Carlo localization (MCL) method based on laser data. Extensive experiments demonstrate that our approach improves the global localization speed and success rate to 96.2% with few particles. In addition, the mobile robot using our proposed approach can recover from robot kidnapping after a short movement, while conventional MCL methods converge to the wrong position.

The spatial index structure is one of the most important research topics for organizing and managing massive 3D Point Cloud. As a point in Point Cloud consists of Cartesian coordinates $(x,y,z)$, the common method to explore geometric information and features is nearest neighbor searching. An efficient spatial indexing structure directly affects the speed of the nearest neighbor search. Octree and kd-tree are the most used for Point Cloud data. However, octree or KD-tree do not perform best in nearest neighbor searching. A highly balanced tree, 3D R*-tree is considered the most effective method so far. So, a hybrid spatial indexing structure is proposed based on octree and 3D R*-tree. In this paper, we discussed how thresholds influence the performance of nearest neighbor searching and constructing the tree. Finally, an adaptive way method adopted to set thresholds. Furthermore, we obtained a better performance in tree construction and nearest neighbor searching than octree and 3D R*-tree.

Simultaneous localization and mapping (SLAM) plays a crucial role in the field of intelligent mobile robots. However, the traditional Visual SLAM (VSLAM) framework is based on strong assumptions about static environments, which are not applicable to dynamic real-world environments. The correctness of re-localization and recall of loop closure detection are both lower when the mobile robot loses frames in a dynamic environment. Thus, in this paper, the re-localization and loop closure detection method with a semantic topology graph based on ORB-SLAM2 is proposed. First, we use YOLOv5 for object detection and label the recognized dynamic and static objects. Secondly, the topology graph is constructed using the position information of static objects in space. Then, we propose a weight expression for the topology graph to calculate the similarity of topology in different keyframes. Finally, the re-localization and loop closure detection are determined based on the value of topology similarity. Experiments on public datasets show that the semantic topology graph is effective in improving the correct rate of re-localization and the accuracy of loop closure detection in a dynamic environment.

Visual simultaneous localization and mapping (VSLAM) is pivotal for intelligent mobile robots. VSLAM systems can be used to identify scenes by obtaining massive amounts of redundant texture information from the environment. However, VSLAM faces a major challenge in dynamic low-light environments, in which the extraction of feature points is often difficult, leading to tracking failure with mobile robots. Therefore, we developed a method to improve the feature point extraction method used for VSLAM. We first used the contrast limited adaptive histogram equalization (CLAHE) method to increase the contrast in low-light images, allowing for the extraction of more feature points. Second, in order to increase the effectiveness of the extracted feature points, the redundant feature points were removed. We developed three conditions to filter the feature points. Finally, the proposed method was tested on popular datasets (e.g., TUM and OpenLORIS-Scene), and the results were compared with those of several traditional methods. The results of the experiments showed that the proposed method is feasible and highly robust in dynamic low-light environments.

The pose estimation can be effectively solved according to the feature point matching relationship in RGB-D. However, the extraction and matching process based on the whole image’s feature point is very computationally intensive and lacks robustness, which is the bottleneck of the traditional ICP algorithm. This paper proposes representing the whole image’s feature points by the salient objects’ robustness SIFT feature points through the salient preprocessing, and further solving the pose estimation. The steps are as follows: (1) salient preprocessing; (2) salient object’s SIFT feature extraction and matching; (3) RANSAC removes mismatching salient feature points; (4) ICP pose estimation. This paper proposes salient preprocessing aided by RANSAC processing based on the SIFT feature for pose estimation for the first time, which is a coarse-to-fine method. The experimental results show that our salient preprocessing algorithm can coarsely reduce the feature points’ extractable range and interfere. Furthermore, the results are processed by RANSAC good optimization, reducing the calculation amount in the feature points’ extraction process and improving the matching quality of the point pairs. Finally, the calculation amount of solving R, t based on all the matching feature points is reduced and provides a new idea for related research.

Semantic mapping can help robots better understand the environment and is extensively studied in robotics. However, it is a challenge for semantic mapping that calibrates all the obstacles with semantics. We propose integrating two network models to realize the salient semantic segmentation used for mobile robot mapping, which differs from traditional segmentation methods. Firstly, we detected salient objects. The detection result was the grayscale image form, which was recognized and annotated by our trained model. Then, we projected the salient objects’ contour with semantics to the corresponding RGB image, which realized the salient objects’ semantic segmentation. We treated the salient objects instead of all the obstacles as semantic segmentation objects that could reduce the background consideration. The neural network model trained based on the salient object’s shape information was stable for object recognition and easy for model training. We only used the shape feature for training, which could reduce the calculation amount of feature details. Experiments demonstrated that the algorithm could quickly realize the model’s training and provide a semantic landmark in the point cloud map as the relative position reference for robot repositioning when the map needs to be used again and exist in a similar environment.