Explore the vast range of titles available.

Simultaneous localization and mapping (SLAM), as one of the core prerequisite technologies for intelligent mobile robots, has attracted much attention in recent years. However, the traditional SLAM systems rely on the static environment assumption, which becomes unstable for the dynamic environment and further limits the real-world practical applications. To deal with the problem, this paper presents a dynamic-environment-robust visual SLAM system named YOLO-SLAM. In YOLO-SLAM, a lightweight object detection network named Darknet19-YOLOv3 is designed, which adopts a low-latency backbone to accelerate and generate essential semantic information for the SLAM system. Then, a new geometric constraint method is proposed to filter dynamic features in the detecting areas, where dynamic features can be distinguished by utilizing the depth difference with Random Sample Consensus (RANSAC). YOLO-SLAM composes the object detection approach and the geometric constraint method in a tightly coupled manner, which is able to effectively reduce the impact of dynamic objects. Experiments are conducted on the challenging dynamic sequences of TUM dataset and Bonn dataset to evaluate the performance of YOLO-SLAM. The results demonstrate that the RMSE index of absolute trajectory error can be significantly reduced to 98.13% compared with ORB-SLAM2 and 51.28% compared with DS-SLAM, indicating that YOLO-SLAM is able to effectively improve stability and accuracy in the highly dynamic environment.

Owing to the advantages of cost-effectiveness, compactness, and the avoidance of complicated camera synchronization, single-camera three-dimensional (3D) digital image correlation (DIC) techniques have gained increasing attention for deformation measurement of materials and structures. In the traditional single-camera 3D-DIC system, the left and right view images can be recorded by a single camera using diffraction grating, a bi-prism, or a set of planar mirrors. To further improve the measurement accuracy of single-camera 3D-DIC, this paper introduces a single-camera four-view imaging technique by installing a pyramidal prism in front of the camera. The 3D reconstruction of the measured points before and after deformation is realized with eight governing equations induced by four views, and the strong geometric constraints of four views can help to improve the measurement accuracy. A static experiment, a rigid body translation experiment, and a four-point bending experiment show that the proposed single-camera 3D-DIC method can achieve higher measurement accuracy than the dual-view single-camera 3D-DIC techniques and that the single-camera 3D-DIC method has advantages in reducing both random error and systematic error.

This paper proposes a density-based topology optimization method for the three-dimensional design of fluid diodes considering wall-connected structures based on the fictitious physical modeling approach. The optimum design problem of fluid diodes is formulated as maximizing the energy dissipation in the reverse flow subject to the upper bound constraint of the energy dissipation in the forward flow. A fictitious physical model and a geometric constraint are constructed to detect and restrict the “floating” solid domains, which are not connected to the outer boundaries. The sensitivities of cost functions are derived and computed based on the continuous adjoint method. The finite volume method is employed to discretize the governing and adjoint equations to mitigate the huge computational costs of three-dimensional fluid analysis. Numerical investigations are presented to validate the fictitious physical model and the geometric constraint for excluding “floating” islands. Finally, topology optimization for fluid diodes with and without the geometric constraint is performed, and the result demonstrates that the proposed method is capable of generating fluid diodes with wall connectivity, while maintaining a good functional performance.

Outlier removal is a crucial step in local feature-based unmanned aerial vehicle (UAV) image matching. Inspired by our previous work, this paper proposes a method for reliable and efficient outlier removal in UAV image matching. The inputs of the method are only two images without any other auxiliary data. The core idea is to design local geometric constraints within the neighboring structure via the Delaunay triangulation and use a two-stage method for outlier removal and match refinement. In the filter stage, initial matches are first organized as the Delaunay triangulation (DT) and its corresponding graph, and their dissimilarity scores are computed from the affine-invariant spatial angular order (SAO), which is used to achieve hierarchical outlier removal. In addition, by using the triangle constraint between the refined Delaunay triangulation and its corresponding graph, missed inliers are resumed from match expansion. In the verification stage, retained matches are refined using the RANSAC-based global geometric constraint. Therefore, the two-stage algorithm is termed DTSAO-RANSAC. Finally, using four datasets, DTSAO-RANSAC is comprehensively analyzed and compared with other methods in feature matching and image orientation tests. The experimental results demonstrate that compared with the LO-RANSAC algorithm, DTSAO-RANSAC can achieve efficient outlier removal with speedup ratios ranging from 4 to 16 and, it can provide reliable matching results for image orientation of UAV datasets.

Coordinate transformation is a fundamental issue in the related studies of measurement. However, existing methodologies often need to pay more attention to the available spatial information, leading to suboptimal results. This paper addresses this issue by incorporating geometric constraints into the symmetric coordinate transformation. We propose the so-called geo-constrained transformation method based on the joint adjustment of the coordinate transformation in conjunction with the geometric constraints over a set of points. By formulating the geometric constraints as the conditional model, we analyze the effects of geometric constraints on the estimated transformation parameters and point locations. By removing such effects during the symmetric transformation algorithm, the results show better statistical performance and satisfy geometric constraints. Two numerical examples are given to demonstrate the expected improvement in the statistical accuracy. It is shown that the improvement of the point determination accuracy can go beyond 50%.

Simultaneous Localization and Mapping (SLAM) is the core technology enabling mobile robots to autonomously explore and perceive the environment. However, dynamic objects in the scene significantly impact the accuracy and robustness of visual SLAM systems, limiting its applicability in real-world scenarios. Hence, we propose a real-time RGB-D visual SLAM algorithm designed for indoor dynamic scenes. Our approach includes a parallel lightweight object detection thread, which leverages the YOLOv7-tiny network to detect potential moving objects and generate 2D semantic information. Subsequently, a novel dynamic feature removal strategy is introduced in the tracking thread. This strategy integrates semantic information, geometric constraints, and feature point depth-based RANSAC to effectively mitigate the influence of dynamic features. To evaluate the effectiveness of the proposed algorithms, we conducted comparative experiments using other state-of-the-art algorithms on the TUM RGB-D dataset and Bonn RGB-D dataset, as well as in real-world dynamic scenes. The results demonstrate that the algorithm maintains excellent accuracy and robustness in dynamic environments, while also exhibiting impressive real-time performance.

Inspired by the driving muscles of the human arm, a 4-Degree of Freedom (DOF) concentrated driving humanoid robotic arm is proposed based on a spatial double parallel four-bar mechanism. The four-bar mechanism design reduces the inertia of the elbow-driving unit and the torque by 76.65% and 57.81%, respectively. Mimicking the human pose regulation strategy that the human arm picks up a heavy object by adjusting its posture naturally without complicated control, the robotic arm features an integrated position-level closed-form inverse solution method considering both geometric and load capacity limitations. This method consists of a geometric constraint model incorporating the arm angle ( φ ) and the Global Configuration (GC) to avoid joint limits and singularities, and a load capacity model to constrain the feasible domain of the arm angle. Further, trajectory tracking simulations and experiments are conducted to validate the feasibility of the proposed inverse solution method. The simulated maximum output torque, maximum output power and total energy consumption of the robotic arm are reduced by up to 2.0%, 13.3%, and 33.3%, respectively. The experimental results demonstrate that the robotic arm can bear heavy loads in a human-like posture, effectively reducing the maximum output torque and energy consumption of the robotic arm by 1.83% and 5.03%, respectively, while avoiding joints beyond geometric and load capacity limitations. The proposed design provides a high payload–weight ratio and an efficient pose control solution for robotic arms, which can potentially broaden the application spectrum of humanoid robots.

Visual–inertial SLAM algorithms empower robots to autonomously explore and navigate unknown scenes. However, most existing SLAM systems heavily rely on the assumption of static environments, making them ineffective when confronted with dynamic objects in the real world. To enhance the robustness and localization accuracy of SLAM systems in dynamic scenes, this paper introduces a visual–inertial SLAM framework that integrates semantic and geometric information, called D-VINS. This paper begins by presenting a method for dynamic object classification based on the current motion state of features, enabling the identification of temporary static features within the environment. Subsequently, a feature dynamic check module is devised, which utilizes inertial measurement unit (IMU) prior information and geometric constraints from adjacent frames to calculate dynamic factors. This module also validates the classification outcomes of the temporary static features. Finally, a dynamic adaptive bundle adjustment module is developed, utilizing the dynamic factors of the features to adjust their weights during the nonlinear optimization process. The proposed methodology is evaluated using both public datasets and a dataset created specifically for this study. The experimental results demonstrate that D-VINS stands as one of the most real-time, accurate, and robust systems for dynamic scenes, showcasing its effectiveness in challenging real-world scenes.

Simultaneous localization and mapping (SLAM) is the technological basis of environmental sensing, and it has been widely applied to autonomous navigation. In combination with deep learning methods, dynamic SLAM algorithms have emerged to provide a certain stability and accuracy in dynamic scenes. However, the robustness and accuracy of existing dynamic SLAM algorithms are relatively low in dynamic scenes, and their performance is affected by potential dynamic objects and fast-moving dynamic objects. To solve the positioning interference caused by these dynamic objects, this study proposes a geometric constraint algorithm that utilizes a bidirectional scoring strategy for the estimation of a transformation matrix. First, a geometric constraint function is defined according to the Euclidean distance between corresponding feature points and the average distance of the corresponding edges. This function serves as the basis for determining abnormal scores for feature points. By utilizing these abnormal score values, the system can identify and eliminate highly dynamic feature points. Then, a transformation matrix estimation based on the filtered feature points is adopted to remove more outliers, and a function for evaluating the similarity of key points in two images is optimized during this process. Experiments were performed based on the TUM dynamic target dataset and Bonn RGB-D dynamic dataset, and the results showed that the added dynamic detection method effectively improved the performance compared to state of the art in highly dynamic scenarios.

In this paper, dynamic modeling of a reconfigurable wheel-legged robot is proposed using a geometric constraint based on independent coordinates. The main contribution of this research is the use of a geometric constraint for the body's rotational angle and using the Gibbs–Appell method instead of traditional modeling approaches to avoid complex constraint equations, significant computational burden, and simulation time. This study necessitates some assumptions in order to develop constraint equations and calculate Gibbs functions due to the presence of nonholonomic constraints on the wheels and the requirement for the robot to move simultaneously in x- and z-directions to execute distinct tasks. With the proposed approach, dynamic equations are obtained without determining the Lagrangian coefficients. In addition, because of the particular form of the Gibbs equations, fewer partial derivatives are necessary to derive the equations from which the joints torques are calculated in terms of the quasi-coordinates. In addition to spatial vector relations, a geometric constraint is used to construct kinematic modeling, requiring other coordinates to be explicitly obtained in terms of quasi-coordinates in the dynamic formulation. Simulation results in various modes of motion to change the height of the robot while proceeding in its course and the associated motor torques, are verified experimentally using a WLRIUST robot. Finally, simulation results for several test scenarios are presented, demonstrating the overall performance of the robot with four double-link legs. Relevant simulation results are also compared to those obtained with the Adams software. The performance of the robot's movements and the torques applied to the motors by relevant changes in the quasi-coordinates are also examined. The results show MATLAB and Adams modeling differ nearly 1%, and with experimental tests differ about 5 to 10%.