Multi-robot Collaborative Mapping and Localization Based on Cross-Validation Global Matching

Loop closure detection is crucial for simultaneous localization and mapping (SLAM), as it can effectively correct the accumulated errors. Complex scenarios put forward high requirements on the robustness of loop closure detection. Traditional feature-based loop closure detection methods often fail to meet these challenges. To solve this problem, this paper proposes a robust and efficient deep-learning-based loop closure detection approach. We employ MixVPR to extract global descriptors from keyframes and construct a global descriptor database. For local feature extraction, SuperPoint is utilized. Then, the constructed global descriptor database is used to find the loop frame candidates, and LightGlue is subsequently used to match the most similar loop frame and current keyframe with the local features. After matching, the relative pose can be computed. Our approach is first evaluated on several public datasets, and the results prove that our approach is highly robust to complex environments. The proposed approach is further validated on a real-world dataset collected by a drone and achieves accurate performance and shows good robustness in challenging conditions. Additionally, an analysis of time and memory costs is also conducted and proves that our approach can maintain accuracy and have satisfactory real-time performance as well.

Hand-crafted point descriptors have been traditionally used for visual loop closure detection. However, in low-textured environments, it is usually difficult to find enough point features and, hence, the performance of such algorithms degrade. Under this context, this paper proposes a loop closure detection method that combines lines and learned points to work, particularly, in scenarios where hand-crafted points fail. To index previous images, we adopt separate incremental binary Bag-of-Words (BoW) schemes for points and lines. Moreover, we adopt a binarization procedure for features’ descriptors to benefit from the advantages of learned features into a binary BoW model. Furthermore, image candidates from each BoW instance are merged using a novel query-adaptive late fusion approach. Finally, a spatial verification stage, which integrates appearance and geometry perspectives, allows us to enhance the global performance of the method. Our approach is validated using several public datasets, outperforming other state-of-the-art solutions in most cases, especially in low-textured scenarios.

Simultaneous localization and mapping (SLAM) is mainly used to solve the problem of mobile robot navigation in an unknown environment. The loop closure detection is a key step in visual SLAM and plays an important role in building consistent maps and reducing pose cumulative errors. A new loop closure detection method based on the bag of semantic word (BOSW) is proposed in this paper, extracting semantic descriptors by using a neural network pre-trained on the scene recognition data set. Traditionally, the visual bag of word (BoW) model adopts the features such as ORB and SURF which is easily affected by the environment. With advantages of better ability to deal with changes in lighting, the convolutional neural network can extract the abstract features of the image. For these reasons, we proposed a new algorithm that combines the bag of word model and the convolutional neural network. The feature maps, extracted by the VGG16 neural network which is trained on the dataset named Places365 (VGG16-Places365), are used as the semantic descriptors instead of ORB descriptors. The workflow of building the vocabulary of the semantic words, extracting the feature vector of the image and computing the similarity score is presented. The performance of BOSW is evaluated by a comparison study with the traditional visual bag of word model and Inception-based deep learning method which use Inception's fully connected layer output as the feature vector of the picture. Overall, the experiments on New College datasets verified that our mode show stronger generalization and can achieve higher accuracy in the loop closure detection.

Loop closure detection is the core part of the visual simultaneous localization and mapping (VSLAM) for autonomous robots. In the dynamic environments, loop closure detection turns to be a very difficult problem compared to the static scenario. This paper proposes a novel approach based on convolutional autoencoder neural network (CAENN) architecture for extracting images features, and then uses Euclidean loss for minimizing the difference between the extracted feature and the gist feature which has the ability of scene recognition. In order to improve the accuracy and recall rate for loop closure detection in the dynamic scenario, the perspective transformation and dynamic object are applied in the process of the construction of the training set. And by calculating the Manhattan distance between the two image feature vectors, the loop closure is accepted when the distance is smaller than the threshold. The experimental results demonstrate that the proposed method obtains better accuracy and recall rate compared to the commonly used gist feature method and has a lower cost on time and space compared to the BOW method and AlexNet method in loop closure detection.

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.

Humans maintain good memory and recognition capability of previous environments when they are learning about new ones. Thus humans are able to continually learn and increase their experience. It is also obvious importance for autonomous mobile robot. The simultaneous localization and mapping system plays an important role in localization and navigation of robot. The loop-closure detection method is an indispensable part of the relocation and map construction, which is critical to correct mappoint errors of simultaneous localization and mapping. Existing visual loop-closure detection methods based on deep learning are not capable of continual learning in terms of cross-scene environment, which bring a great limitation to the application scope. In this article, we propose a novel end-to-end loop-closure detection method based on continual learning, which can effectively suppress the decline of the memory capability of simultaneous localization and mapping system by introducing firstly the orthogonal projection operator into the loop-closure detection to overcome the catastrophic forgetting problem of mobile robot in large-scale and multi-scene environments. Based on the three scenes from public data sets, the experimental results show that the proposed method has a strong capability of continual learning in the cross-scene environment where existing state-of-the-art methods fail.

Modest-vocabulary loop-closure detection with incremental bag of tracked words

Ground texture localization using a downward-facing camera offers a low-cost, high-precision localization solution that is robust to dynamic environments and requires no environmental modification. We present a significantly improved bag-of-words (BoW) image retrieval system for ground texture localization, achieving substantially higher accuracy for global localization and higher precision and recall for loop closure detection in SLAM. Our approach leverages an approximate <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex>-means (AKM) vocabulary with soft assignment, and exploits the consistent orientation and constant scale constraints inherent to ground texture localization. Identifying the different needs of global localization vs. loop closure detection for SLAM, we present both high-accuracy and high-speed versions of our algorithm. We test the effect of each of our proposed improvements through an ablation study and demonstrate our method's effectiveness for both global localization and loop closure detection. With numerous ground texture localization systems already using BoW, our method can readily replace other generic BoW systems in their pipeline and immediately improve their results.

Loop closure detection is essential for simultaneous localization and mapping systems to decrease accumulating drift of trajectory estimations. Robust loop closure detection is specifically important in large-scale mapping, but it gets more challenging as the mapping environment grows. This paper proposes a SLAM system utilizing a two-pass loop closure detection method to improve mapping accuracy in large-scale environments. The proposed system finds loop closure candidates by employing global and local image features together. After selecting a group of candidates by similarity of global features, the system applies keypoint matching on this group to improve scene matching accuracy and determines loop closure candidates. We extensively evaluate the system on the widely used TUM RGB-D dataset, which contains sequences of small to large-scale indoor environments, with respect to different parameter combinations. The results show that the proposed method increases accuracy substantially and achieves large-scale mapping with acceptable overhead.

It is important to improve the localization accuracy of the unmanned surface vehicle (USV) for ensuring safe navigation in an inland waterway scenario. However, the localization accuracy of the USV is affected by the limited availability of global navigation satellite system signals, the sparsity of feature points, and the high scene similarity in inland waterway scenarios. Therefore, this paper proposes a laser-based simultaneous localization and mapping (SLAM) algorithm for accurate localization and mapping in inland waterway scenarios. Inertial measurement unit (IMU) data are integrated with lidar data to address motion distortion caused by the frequent motion of the USV. Subsequently, a generalized iterative closest point (GICP) algorithm incorporating rejection sampling is integrated to enhance the accuracy of point cloud matching, involving a two-phase filtering process to select key feature points for matching. Additionally, a mixed global descriptor is constructed by combining point cloud intensity and distance information to improve the accuracy of loop closure detection. Experiments are conducted on the USV-Inland datasets to evaluate the performance of the proposed algorithm. The experimental results show that the proposed algorithm generates accurate mapping and significantly improves localization accuracy by 25.6%, 18.5%, and 23.6% compared to A-LOAM, LeGO-LOAM, and ISC-LOAM, respectively. These results demonstrate that the proposed algorithm achieves accurate localization and mapping in an inland waterway scenario.

Loop closure detection (LCD) is an important module of visual SLAM (Simultaneous Localization and Mapping), which can be regarded as an image retrieval task. The correct LCD can effectively reduce the cumulative errors during visual SLAM localization and obtain a globally consistent map. The currently common approach to LCD is based on a bag-of-words (BoW) and traditional manually designed features. However, The BoW-based method ignores the spatial location information and semantic information of visual features, and image aliasing will affect the detection accuracy of the algorithm. Meanwhile, the artificially designed features are very sensitive to light changes. This paper proposes a LCD algorithm based on convolutional neural networks (CNN) to extract global and local features. Extensive experiments on six publicly available datasets have shown that the method provides high recall with 100% accuracy in most of the evaluated datasets relative to traditional algorithms and some deep learning-based methods.

Sparse code multiple access (SCMA) is an up-and-coming non-orthogonal multiple access technology. The message passing algorithm (MPA) is utilized for multi-user signal detection in the SCMA system to achieve a performance close to the maximum a posterior algorithm. However, higher iterations will lead to the higher computational complexity of the MPA. In this paper, a dynamic threshold and stability judgment based MPA scheme (DTS-MPA) is proposed to reduce the computational complexity by simplifying the factor graph and reducing the number of iterations. Firstly, an adaptive dynamic threshold is set to minimize the number of iterations in the different channel state information. Secondly, an additional iteration is proposed to determine whether the variable nodes that meet the dynamic threshold reach stable convergence to improve the decoding reliability. Variable nodes that meet the above conditions will be decoded in advance. Numerical results show that the DTS-MPA can significantly reduce the computational complexity of the MPA and achieve a significant trade-off between bit error rate performance and computational complexity.

Visual Simultaneous Localization and Mapping (SLAM) algorithms relying on cameras have gained significant attention with advancements in computer vision. However, existing approaches often depend on high-performance hardware, limiting their applicability in resource-constrained scenarios. This study addresses indoor planar motion applications, such as service robots and automated guided vehicles (AGV), by proposing a cost-effective Visual-Inertial SLAM(VI-SLAM) framework tailored for low-performance platforms using a low-cost binocular camera and an inertial measurement unit (IMU). A localization module is developed to enhance feature stability through inertial prediction and reprojection cross validation, using grayscale images, depth images, and IMU data. A map correction module is introduced to integrate backend optimized poses, loop closure detection, and depth information, enabling the generation of globally consistent probability grid maps via submap stitching and multi-state depth image conversion. Comprehensive evaluations are conducted on public datasets and real-world environments. The results demonstrate the accuracy, robustness, and feasibility of our approach for low-performance and low-cost devices, highlighting its potential for commercialization and practical applications.

Loop closure detection with patch-level local features and visual saliency prediction

This paper introduces a novel globally consistent dense RGB-D SLAM system designed to address the challenges of online dense reconstruction under fast camera motion. To achieve robust pose tracking and globally consistent map building, we present a random optimization pose estimation framework that integrates both geometric and photometric information. Furthermore, we propose a voxel revisitation-based loop closure detection scheme that relies solely on depth maps. Innovatively, we introduce a local curvature feature, to address loop closure detection when photometric information is unavailable, efficiently extracting 3D geometric information directly from 2D images. In addition, we leverage voxel revisitation observations to accelerate the search for potential loop closures. This is achieved by maintaining a dynamic active map and detecting voxel outflow or revisits, thereby enhancing loop closure detection efficiency. This method is the first voxel revisitation-based loop closure detection scheme that relies entirely on depth information. Combined with a random optimization pose estimation framework utilizing both geometric and photometric features, it adapts well to fast camera motion, enabling accurate and globally consistent dense map construction. Extensive evaluations on public datasets demonstrate the effectiveness of our method under fast camera motion and highlight its significant advantages over existing methods.