In recent years, unmanned aerial vehicles (UAVs) have been applied in underground mine inspection and other similar works depending on their versatility and mobility. However, accurate localization of UAVs in perceptually degraded mines is full of challenges due to the harsh light conditions and similar roadway structures. Due to the unique characteristics of the underground mines, this paper proposes a semantic knowledge database-based localization method for UAVs. By minimizing the spatial point-to-edge distance and point-to-plane distance, the relative pose constraint factor between keyframes is designed for UAV continuous pose estimation. To reduce the accumulated localization errors during the long-distance flight in a perceptual-degraded mine, a semantic knowledge database is established by segmenting the intersection point cloud from the prior map of the mine. The topological feature of the current keyframe is detected in real time during the UAV flight. The intersection position constraint factor is constructed by comparing the similarity between the topological feature of the current keyframe and the intersections in the semantic knowledge database. Combining the relative pose constraint factor of LiDAR keyframes and the intersection position constraint factor, the optimization model of the UAV pose factor graph is established to estimate UAV flight pose and eliminate the cumulative error. Two UAV localization experiments conducted on the simulated large-scale Edgar Mine and a mine-like indoor corridor indicate that the proposed UAV localization method can realize accurate localization during long-distance flight in degraded mines.

In order to resolve redundancy and path planning of a high DOF mobile manipulator using conventional approaches like Jacobian and a pseudoinverse method, researchers face the limitation of computational load and delay in response. If such kind of mobile manipulator is traversing the rough terrain, then conventional methods become too costly to implement due to the handling of redundant joints, obstacles, and wheel-terrain interaction. A few optimization-based redundancy resolution approaches try incorporating wheel-terrain interaction but fail in real-time response. This paper describes a 14 DOF Rover Manipulator System’s end-effector path-tracking approach using CG-Space framework to incorporate wheel-terrain interaction. CG-Space means the center of gravity (CG) locus of the Rover. The Rover’s CG is calculated while traversing over 3D terrain using a multivariable optimization method and a 3D point cloud image of the actual terrain and stored as CG-Space over the given terrain. First of all, we decide which part of the system moves to track the path, that is, arm or Rover, depending upon the manipulator’s work volume and manipulability measure restrictions. The next task is to obtain the Rover pose according to the end-effector path using a simple arm’s inverse kinematic solution between the CG-Space and end-effector task space without resolving redundancy. Meanwhile, obstacles and non-traversable regions are avoided in CG-Space. On diverse 3D terrains, simulation and experimental results support the suggested CG-Space framework for end-effector tracking.

This paper mainly studies an autonomous path-planning and real-time path-tracking optimization method for snake robot. Snake robots can perform search and rescue, exploration, and other tasks in a variety of complex environments. Robots with visual sensors such as LiDAR can avoid obstacles in the environment through autonomous navigation to reach the target point. However, in an unstructured environment, the navigation of snake robot is easily affected by the external environment, causing the robot to deviate from the planned path. In order to solve the problem that snake robots are easily affected by environmental factors in unstructured environments, resulting in poor path-following ability, this paper uses the Los algorithm combined with steering control to plan the robot in real time and control the robot’s steering parameters in real time, ensuring that the robot can stably follow the planned path.

Over decades of robotics research, cooperative object transportation has been studied as a meaningful model problem for robotic networks because it possesses a variety of crucial challenges. Although these challenges are demanding, the cooperation of multiple robots has the potential to solve automation problems that are beyond the scope of an individual robot. So far, the model problem has mostly been addressed by explicitly controlling the robots’ positions. However, the position-based approach suffers from some intrinsic detriments, for example, the lack of explicit feedback between robots and object. Moreover, it remains an open question how many robots shall be employed to ensure a successful transportation. This paper’s purpose is to overcome these challenges using a novel force-based approach taking into account the robots’ actual manipulation capabilities, that is, the exerted forces. Using cost-efficient hardware, the interaction forces are measured and, what is more, explicitly controlled by a highly responsive onboard controller. Employing a tailored software architecture, the novel force-based scheme, useful for robotic manipulation beyond the benchmark problem, is probably the most flexible of its kind regarding the number of robots and the object’s shape. The controller’s functionality and performance as well as the scheme’s versatility are demonstrated by several hardware experiments.

This study proposes a novel hybrid learning approach for developing a visual path-following algorithm for industrial robots. The process involves three steps: data collection from a simulation environment, network training, and testing on a real robot. The actor network is trained using supervised learning for 500 epochs. A semitrained network is then obtained at the $250^{th}$ epoch. This network is further trained for another 250 epochs using reinforcement learning methods within the simulation environment. Networks trained with supervised learning (500 epochs) and the proposed hybrid learning method (250 epochs each of supervised and reinforcement learning) are compared. The hybrid learning approach achieves a significantly lower average error (30.9 mm) compared with supervised learning (39.3 mm) on real-world images. Additionally, the hybrid approach exhibits faster processing times (31.7 s) compared with supervised learning (35.0 s). The proposed method is implemented on a KUKA Agilus KR6 R900 six-axis robot, demonstrating its effectiveness. Furthermore, the hybrid approach reduces the total power consumption of the robot’s motors compared with the supervised learning method. These results suggest that the hybrid learning approach offers a more effective and efficient solution for visual path following in industrial robots compared with traditional supervised learning.

Diabetic retinopathy (DR) is a complication of diabetes that causes blindness and the early detection of diabetics using retinopathy images remains a challenging task. Hence, a novel, earlier smart prediction of diabetic retinopathy from fundus image under Innovative ResNet Optimization is introduced to effectively detect the earlier stage of DR from Fundus image. Initially, the fundus image is scaled during preprocessing and converted into a grayscale format. As the existing studies neglect some deserving unique features that are crucial for predicting the earliest signs of DR, a novel Fractional Radon Transform with Visibility Graph is introduced for extracting the novel features such as microaneurysms count, dot and blot hemorrhages count, statistical measures, and retinal layer thickness, in which a Generalized Cosine Fractional Radon Transform is used to capture the image’s fine-scale texture information thereby effectively capturing the statistical measures, while a weighted Horizontal Visibility Graph is made to examine the apparent spatial relationships between pixel pairs in the image based on the values of the pixels’ gray levels. Further, the existing works failed to identify the small fine dark areas that were ignored throughout the morphological opening process. In order to overcome this issue, a Morphological Black Hat Transform with Optimized ResNet Algorithm is implemented, where segmentation is made through Enriched Black Hat Transform-based Morphological operation to identify fine dark regions among the pixels inside the eye samples, and the classification is done by using ResNet-driven S-GOA (Socio Grasshopper Optimization Algorithm), to optimally predict the stages of DR. The result obtained showed that the proposed model outperforms existing techniques with high performance and accuracy.

The concept of distance between two rigid-body poses is important in path planning, positioning precision, mechanism synthesis, and in many other applications. In the definition of such a distance, two approaches mainly prevail, which lead to a number of formulas devised to match the needs of motion tasks. Despite the different approaches and formulas, some important theoretical results, which drive toward distance-metrics definitions useful for design and application purposes, have been stated. This paper summarizes the two different approaches together with a critical review of the literature on the distance metrics they generated, and, then, it illustrates a technique, previously proposed by the author, for combining different metrics to obtain novel distance-metric definitions that are tailored to specific applications.

Simultaneous localization and mapping systems based on rigid scene assumptions cannot achieve reliable positioning and mapping in a complex environment with many moving objects. To solve this problem, this paper proposes a novel dynamic multi-object lidar odometry (MLO) system based on semantic object recognition technology. The proposed system enables the reliable localization of robots and semantic objects and the generation of long-term static maps in complex dynamic scenes. For ego-motion estimation, the proposed system extracts environmental features that take into account both semantic and geometric consistency constraints. Then, the filtered features can be robust to the semantic movable and unknown dynamic objects. In addition, we propose a new least-squares estimator that uses geometric object points and semantic box planes to realize the multi-object tracking (SGF-MOT) task robustly and precisely. In the mapping module, we implement dynamic semantic object detection using the absolute trajectory tracking list. By using static semantic objects and environmental features, the system eliminates accumulated localization errors and produces a purely static map. Experiments on the public KITTI dataset show that the proposed MLO system provides more accurate and robust object tracking performance and better real-time localization accuracy in complex scenes compared to existing technologies.

The venous blood test is a prevalent auxiliary medical diagnostic method. Venous blood collection equipment can improve blood collection’s success rate and stability, reduce the workload of medical staff, and improve the efficiency of diagnosis and treatment. This study proposed a rigid-flexible composite puncture (RFCP) strategy, based on which a small 7-degree-of-freedom (DOF) auxiliary venipuncture blood collection (VPBC) robot using a trocar needle was designed. The robot consists of a position and orientation adjustment mechanism and a RFCP end-effector, which can perform RFCP to avoid piercing the blood vessel’s lower wall during puncture. The inverse kinematics solution and validation of the robot were analyzed based on the differential evolution algorithm, after which the quintic polynomial interpolation algorithm was applied to achieve the robot trajectory planning control. Finally, the VPBC robot prototype was developed for experiments. The trajectory planning experiment verified the correctness of the inverse kinematics solution and trajectory planning, and the composite puncture blood collection experiment verified the feasibility of the RFCP strategy.

Safe and socially compliant navigation in a crowded environment is essential for social robots. Numerous research efforts have shown the advantages of deep reinforcement learning techniques in training efficient policies, while most of them ignore fast-moving pedestrians in the crowd. In this paper, we present a novel design of safety measure, named Risk-Area, considering collision theory and motion characteristics of different robots and humans. The geometry of Risk-Area is formed based on the real-time relative positions and velocities of the agents in the environment. Our approach perceives risk in the environment and encourages the robot to take safe and socially compliant navigation behaviors. The proposed method is verified with three existing well-known deep reinforcement learning models in densely populated environments. Experiment results demonstrate that our approach combined with the reinforcement learning techniques can efficiently perceive risk in the environment and navigate the robot with high safety in the crowds with fast-moving pedestrians.

Evolution has shown that legged locomotion is most adequate for tasks requiring versatile movement on land, allowing animals to traverse a wide variety of environments ranging from natural terrain to artificial, man-made landscapes with great ease. By employing well-designed control schemes, this ability could be replicated for legged robots, enabling them to be used in critical situations that still pose great danger to human integrity, such as search and rescue missions, inspection of hazardous areas, and even space exploration. This work characterizes the quadruped robot and contact dynamics that will compose our in-house simulator to be used for prototyping locomotion control schemes applied to quadruped robots. The proposed simulator computes the robot dynamics using the Recursive Newton-Euler and Composite-Rigid-Body algorithms with a few modifications to make certain aspects relevant for contact detection and control more easily accessible; furthermore, a compliant contact force method alongside stick-slip friction modeled the contact dynamics. To allow the robot to move, a simple PD-independent joint controller was implemented to track a desired leg trajectory. With the same robot and controller implemented using the MuJoCo simulation software, this work evaluates the proposed simulator by comparing characteristic locomotion signals such as the trunk pose and the ground reaction forces. Results showed similar behavior for both simulators, especially with regard to the contact detection, despite the significantly different contact models. Lastly, final remarks to enhance our simulator’s performance are suggested to be explored in future works.

Due to the flexibility obtained through both materials and structures, soft robots have wide potential applications in complicated internal and external environments. This paper presents a new soft crawling robot with multiple locomotion patterns that integrate inchworm motion and various turning motions. First, the conceptual design of the proposed robot is presented by introducing thick-panel origami into the synthesis of a crawling robot, resulting in a Waterbomb-structure-inspired hybrid mechanism. Second, all locomotion patterns of the robot are precisely described and analyzed by screw theory in an algebraic manner, which include inchworm motion, restricted planar motion, quantitative turning motion, and marginal exploration motion. Then, the output motion parameter for each locomotion pattern is analytically modeled as a function of the robotic dimensional parameters, and the robot can thus be designed and controlled in a customized way for the expected output motion. Finally, the theoretical analysis and derivations are validated by simulation and physical prototype building, which lay the foundations for the design and manufacture of small-scale soft crawling robots with precise output motions in a complex planar environment.

This paper deals with generally routed, pre-bent cable-driven continuum robots (CCR). A CCR consists of a flexible backbone to which multiple disks are attached. Cables are passed through holes in the disk, and when pulled, the flexible backbone and the CCR can attain different shapes based on their routing and backbone configuration. An optimization-based approach, using minimization of strain energy, is shown to give good results for the pose and motion of the CCR and to determine contact with external objects. The pose, motion, and the contact obtained from the model are shown to match very well with experimental results obtained from a 3D-printed CCR. An algorithm is proposed to generate the pre-bent backbone for a CCR which on actuation can attain the desired shape. Using the algorithm, three 3D-printed CCRs with pre-bent backbones are fabricated and these are used to demonstrate a compliant gripper that can grip a spherical object similar to that done by tentacles, and another three-fingered gripper with straight backbone CCRs is used to orient a square object gripped at the end.

This paper presents a decentralized, cooperative, real-time avoidance control strategy for robotic manipulators. The proposed avoidance control law builds on the concepts of artificial potential field functions and provides tighter bounds on the minimum safe distance when compared to traditional potential-based controllers. Moreover, the proposed avoidance control law is given in analytical, continuous closed form, avoiding the use of optimization techniques and discrete algorithms, and is rigorously proven to guarantee collision avoidance at all times. Examples of planar and 3D manipulators with cylindrical links under the proposed avoidance control are given and compared with the traditional approach of modeling links and obstacles with multiple spheres. The results show that the proposed avoidance control law can achieve, in general, faster convergence, smaller tracking errors, and lower control torques than the traditional approach. Furthermore, we provide extensions of the avoidance control to robotic manipulators with bounded control torques.

In recent years, many microrobots have been developed for search applications using swarms in places where humans cannot enter, such as disaster sites. Hexapod robots are suitable for moving over uneven terrain. In order to use micro-hexapod robots for swarm exploration, it is necessary to reduce the robot’s size while maintaining its rigidity. Herein, we propose a micro-hexapod with an SU-8 rigid frame that can be assembled from a single sheet. By applying the SU-8 coating as a structure to the hexapod and increasing the rigidity, the substrate size can be reduced to within 40 mm × 40 mm and the total length when assembled to approximately 30 mm. This enables the integration of the micro electromechanical systems (MEMS) process into small and inexpensive hexapod robots. In this study, we assembled the hexapod with a rigid frame from a sheet created using the MEMS process and evaluated the leg motion.

This paper proposes a virtual reality-based dual-mode teleoperation architecture to assist human operators in remotely operating robotic manipulation systems in a safe and flexible way. The architecture, implemented via a finite state machine, enables the operator to switch between two operational modes: the Approach mode, where the operator indirectly controls the robotic system by specifying its target configuration via the immersive virtual reality (VR) interface, and the Telemanip mode, where the operator directly controls the robot end-effector motion via input devices. The two independent control modes have been tested along the task of reaching a glass on a table by a sample population of 18 participants. Two working groups have been considered to distinguish users with previous experience with VR technologies from the novices. The results of the user study presented in this work show the potential of the proposed architecture in terms of usability, both physical and mental workload, and user satisfaction. Finally, a statistical analysis showed no significant differences along these three metrics between the two considered groups demonstrating ease of use of the proposed architecture by both people with and with no previous experience in VR.

The recognizing underwater targets is a crucial component of autonomous underwater vehicle patrols and detection efforts. In the process of visual image recognition in real underwater environment, the spatial and semantic features of the target often appear to different degrees of loss, and the scarcity of specific types of underwater samples leads to unbalanced data on categories. This kind of problem makes the target features appear weak and seriously affects the accuracy of underwater target recognition. Traditional deep learning methods based on data and feature enhancement cannot achieve ideal recognition effect. Based on the above difficulties, this paper proposes an improved feature enhancement network for weak feature target recognition. Firstly, a multi-scale spatial and semantic feature enhancement module is constructed to extract the feature information of the extraction target accurately. Secondly, this paper solves the influence of target feature distortion on classification through multi-scale feature comparison of positive and negative samples. Finally, the Rank & Sort Loss function was used to train the depth target detection to solve the problem of recognition accuracy under highly unbalanced sample data. Experimental results show that the recognition accuracy of the proposed method is 2.28% and 3.84% higher than that of the existing algorithms in the recognition of underwater fuzzy and distorted target images, which demonstrates the effectiveness and superiority of the proposed method.

Currently, there is an increasing demand for parallel mechanisms with fewer inputs and more outputs in aerospace, antennas, and recreational facilities. Therefore, this paper proposes a new parallel mechanism (PM) with a separation of constraints and drives, facilitating centralized drive management. Based on screw theory, the type synthesis of new parallel mechanisms with 3T (T representing translation), 3R (R representing revolute), 2T1R, and 2R1T is proposed. Three-degree-of-freedom (3-DOF) parallel mechanisms with fewer inputs and multiple outputs are proposed. Taking the 3RPS-PPPS parallel mechanism as an example, the closed-loop vector method is employed to solve for the lengths of actuated branches. A complete Jacobi matrix is constructed. The motion/force transmission performance of the 3RRS/PPPS parallel mechanism is better than the 3RRS parallel mechanism. Centralized management of drive branches greatly reduces the number of drives, making maintenance and repair easier. It has many application scenarios in antennas, recreational facilities, and other occasions.

Hyper-redundant manipulators are produced by cascading several mechanisms on top of each other as modules. The discrete actuation makes their control easier because discrete actuators usually do not need any feedback to control. So far, several methods have been proposed to solve the inverse kinematic problem of discretely actuated, hyper-redundant manipulators. The two-by-two searching method is better than the other methods in terms of CPU time and error. In this article, the mentioned method is generalized by choosing an arbitrary number of modules as pending modules in each step of the solution instead of the necessary two. For validation, the proposed method is compared with nine meta-heuristic searching algorithms: simulated annealing, genetic algorithm, particle swarm optimization, ant colony optimization, gray wolf optimizer, stochastic fractal search, whale optimization algorithm, Giza pyramid construction, and flying fox optimization. Furthermore, the effect of the number of pending modules on CPU time and error is investigated. All the numerical problems have been solved for two case studies, one is planar and the other is spatial.