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.

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.

The early applications of Visual Simultaneous Localization and Mapping (VSLAM) technology were primarily focused on static environments, relying on the static nature of the environment for map construction and localization. However, in practical applications, we often encounter various dynamic environments, such as city streets, where moving objects are present. These dynamic objects can make it challenging for robots to accurately understand their own position. This paper proposes a real-time localization and mapping method tailored for dynamic environments to effectively deal with the interference of moving objects in such settings. Firstly, depth images are clustered, and they are subdivided into sub-point clouds to obtain clearer local information. Secondly, when processing regular frames, we fully exploit the structural invariance of static sub-point clouds and their relative relationships. Among these, the concept of the sub-point cloud is introduced as novel idea in this paper. By utilizing the results computed based on sub-poses, we can effectively quantify the disparities between regular frames and reference frames. This enables us to accurately detect dynamic areas within the regular frames. Furthermore, by refining the dynamic areas of keyframes using historical observation data, the robustness of the system is further enhanced. We conducted comprehensive experimental evaluations on challenging dynamic sequences from the TUM dataset and compared our approach with state-of-the-art dynamic VSLAM systems. The experimental results demonstrate that our method significantly enhances the accuracy and robustness of pose estimation. Additionally, we validated the effectiveness of the system in dynamic environments through real-world scenario tests.

This article designs a robotic Chinese character writing system that can resist random human interference. Firstly, an innovative stroke extraction method of Chinese characters was devised. A basic Chinese character stroke extraction method based on cumulative direction vectors is used to extract the components that make up the strokes of Chinese characters. The components are then stitched together into strokes based on the sequential base stroke joining method. To enable the robot to imitate handwriting Chinese character skills, we utilised stroke information as the demonstration and modelled the skills using dynamic movement primitives (DMPs). To suppress random human interference, this article combines improved DMPs and conductance control to adjust robot trajectories based on real-time visual measurements. The experimental results show that the proposed method can accurately extract the strokes of most Chinese characters. The designed trajectory adjustment method offers better smoothness and robustness than direct rotating and translating curves. The robot is able to adjust its posture and trajectory in real time to eliminate the negative impacts of human interference.

Hyper-redundant manipulators (HRMs) exhibit promising adaptability and superior dexterity in cavity detection tasks, owing to their snake-like segmented backbones. Due to the safety concern in contactless operating tasks, reliable motion planning in a confined environment for HRMs is very challenging. However, existing expanding-based obstacle avoidance methods are not feasible in narrow environments, as they will excessively occupy free spaces required for maneuvering. In this work, a local collision-free motion planning strategy based on dynamic safety envelope (DSE) is proposed for HRMs. First, the local motion of HRMs is analyzed in detail, and DSE is proposed for the first time to describe the boundary of the collision-free area. Then, to maximize the efficient utilization of narrow spaces, a reference trajectory for HRM is roughly planned without expanding obstacles. Further, a tip-guided trajectory tracking method based on configuration prediction is proposed by considering the discrete characteristics of rigid links to avoid obstacles. During the tracking process, DSEs are applied to evaluate collision risk and optimize the configuration. Finally, to validate the effectiveness of our proposed method, simulations are conducted, followed by experiments by using a 18-degrees of freedom mobile HRM prototype system.

In an effort to alleviate the issue of knee joint fatigue and injury during lower limb ambulation, a novel passive assisted exoskeleton robot with human–machine interaction is investigated to assist the movement of the human knee joint. The design of the exoskeleton configuration takes into consideration the physiological structure and gait function of the knee joint, ensuring that it satisfies the requirements for motion, force, and gait function of the knee joint. To explore the interaction between the wearer and the exoskeleton, a human–machine kinematic model after wearing exoskeleton is established, which is instrumental in analyzing the integration motion of the wearer and exoskeleton. In addition, the dynamic and static models of the knee joint after wearing the exoskeleton are established, utilizing the Newton–Euler method and force polygon method, respectively, to evaluate the effectiveness of the exoskeleton. Moreover, the size parameters and spring stiffness of the exoskeleton are optimized, using both human body kinematic model and mechanic model. Furthermore, the effectiveness of the exoskeleton in proving assistance is evaluated through human body simulation, using OpenSim. The results indicate that the exoskeleton significantly reduces the knee joint torque by 48.42%.

The current LiDAR-inertial odometry is prone to cumulative Z-axis error when it runs for a long time. This error can easily lead to the failure to detect the loop-closing in the correct scenario. In this paper, a ground-constrained LiDAR-inertial SLAM is proposed to solve this problem. Reasonable constraints on the ground motion of the mobile robot are incorporated to limit the Z-axis drift error. At the same time, considering the influence of initial positioning error on navigation, a keyframe selection strategy is designed to effectively improve the flatness and accuracy of positioning and the efficiency of loop detection. If GNSS is available, the GNSS factor is added to eliminate the cumulative error of the trajectory. Finally, a large number of experiments are carried out on the self-developed robot platform to verify the effectiveness of the algorithm. The results show that this method can effectively improve location accuracy in outdoor environments, especially in environments of feature degradation and large scale.

The authors‘ previous research has demonstrated that parallel mechanisms (PMs) with hybrid branch chains (i.e., branch chains containing planar or spatial loops) can possess symbolic forward position (SFP) solutions and motion decoupling (MD). In order to further study the conditions of a three-chain six degrees of freedom (DOF) parallel mechanism with SFP and MD, this paper proposes one 6-DOF branch chain A and two 5-DOF branch chains B and C. Based on these, a class of four 6-DOF PMs with three branch chains is devised. The symbolic position analysis of three of four such PMs is performed consequently, featuring partial MD and SFPs, which reveals that if the position or orientation of a point on the moving platform can be determined by the position of the hybrid branch chain, the PM exhibits partial MD and SFP. Finally, the accuracy of the symbolized forward and inverse solution algorithms is verified through numerical examples. This research brings a new insight into the design and position analysis of 6-DOF PMs, particularly those with SFP and partial MD.

Motion and constraint identification are the fundamental issue throughout the development of parallel mechanisms. Aiming at meaningful result with heuristic and visualizable process, this paper proposes a machine learning-based method for motions and constraints modeling and further develops the automatic software for mobility analysis. As a preliminary, topology of parallel mechanism is characterized by recognizable symbols and mapped to the motion of component limb through programming algorithm. A predictive model for motion and constraint with their nature meanings is constructed based on neural network. An increase in accuracy is obtained by the novel loss function, which combines the errors of network and physical equation. Based on the predictive model, an automatic framework for mobility analysis of parallel mechanisms is constructed. A software is developed with WebGL interface, providing the result of mobility analysis as well as the visualizing process particularly. Finally, five typical parallel mechanisms are taken as examples to verify the approach and its software. The method facilitates to attain motion/constraint and mobility of parallel mechanisms with both numerical and geometric features.

Aiming at the problems of small good workspace, many singular configurations, and limited carrying capacity of non-redundant parallel mechanisms, a full-redundant drive parallel mechanism is designed and developed, and its performance evaluation, good workspace identification, and scale optimization design are studied. First, the kinematics analysis of the planar 6R parallel mechanism is completed. Then, the motion/force transmission performance evaluation index of the mechanism is established, and the singularity analysis of the mechanism is completed. Based on this, the fully redundant driving mode of the mechanism is determined, and the good transmission workspace of the mechanism in this mode is identified. Then, the mapping relationship between the performance and scale of the mechanism is established by using the space model theory, and the scale optimization of the mechanism is completed. Finally, the robot prototype is made according to the optimal scale, and the performance verification is carried out based on the research of dynamics and control strategy. The results show that the fully redundant actuation parallel mechanism obtained by design optimization has high precision and large bearing capacity. The position repeatability and position accuracy are 0.053 mm and 0.635 mm, respectively, and the load weight ratio can reach 15.83%. The research results of this paper complement and improve the performance evaluation and scale optimization system of redundantly actuated parallel mechanisms.

In this paper, we propose a novel vision-based adaptive leakage-type (LT) sliding mode admittance control for actuator-constrained collaborative robots to realize the synchronous control of the precise path following and compliant interaction force. Firstly, we develop a vision-admittance-based model to couple the visual feedback and force sensing in the image feature space so that a reference image feature trajectory can be obtained concerning the contact force command and predefined trajectory. Secondly, considering the system uncertainty, external disturbance, and torque constraints of collaborative robots in reality, we propose an adaptive sliding mode controller in the image feature space to perform precise trajectory tracking. This controller employs a leakage-type (LT) adaptive control law to reduce the side effects of system uncertainties without knowing the upper bound of system uncertainties. Moreover, an auxiliary dynamic is considered in this controller to overcome the joint torque constraints. Finally, we prove the convergence of the tracking error with the Lyapunov stability analysis and operate various semi-physical simulations compared to the conventional adaptive sliding mode and parallel vision/force controller to demonstrate the efficacy of the proposed controller. The simulation results show that compared with the controller mentioned above, the path following accuracy and interaction force control precision of the proposed controller increased by 50% and achieved faster convergence.

Differentially flat under-actuated robots are characterized by more degrees of freedom (DOF) than actuators: this makes possible the design of lightweight cheap robots with high dexterity. The main issue of such robots is the control of the passive joint, which requires accurate dynamic modeling of the robot.

Friction is usually discarded to simplify the models, especially in the case of low-speed trajectories. However, this simplification leads to oscillations of the end-effector about the final position, which are incompatible with fast and accurate motions.

This paper focuses on planar $n$-DOF serial robotic arms with $n-1$ actuated rotational joints plus one final passive rotational joint with stiffness and friction properties. These robots, if properly balanced, are differentially flat. When the non-actuated joint can be considered frictionless, differentially flat robots can be controlled in open loop, calculating the motor torques demanded by point-to-point motions. This paper extends the open-loop control to robots with a passive joint with viscous friction adopting a Laplace transform method. This method can be adopted by exploiting the particular structure of the equations of motion of differentially flat under-actuated robots in which the last equations are linear. Analytical expressions of the motor torques are obtained. The work is enriched by an experimental validation of a $2$-DOF under-actuated robot and by numerical simulations of the $2$- and $4$-DOF robots showing the suppression of unwanted oscillations.

Autonomous fabric manipulation is a challenging task due to complex dynamics and potential self-occlusion during fabric handling. An intuitive method of fabric-folding manipulation first involves obtaining a smooth and unfolded fabric configuration before the folding process begins. However, the combination of quasi-static actions like pick & place and dynamic action like fling proves inadequate in effectively unfolding long-sleeved T-shirts with sleeves mostly tucked inside the garment. To address this limitation, this paper introduces an enhanced quasi-static action called pick & drag, specifically designed to handle this type of fabric configuration. Additionally, an efficient dual-arm manipulation system is designed in this paper, which combines quasi-static (including pick & place and pick & drag) and dynamic fling actions to flexibly manipulate fabrics into unfolded and smooth configurations. Subsequently, once it is confirmed that the fabric is sufficiently unfolded and all fabric keypoints are detected, the keypoint-based heuristic folding algorithm is employed for the fabric-folding process. To address the scarcity of publicly available keypoint detection datasets for real fabric, we gathered images of various fabric configurations and types in real scenes to create a comprehensive keypoint dataset for fabric folding. This dataset aims to enhance the success rate of keypoint detection. Moreover, we evaluate the effectiveness of our proposed system in real-world settings, where it consistently and reliably unfolds and folds various types of fabrics, including challenging situations such as long-sleeved T-shirts with most parts of sleeves tucked inside the garment. Specifically, our method achieves a coverage rate of 0.822 and a success rate of 0.88 for long-sleeved T-shirts folding. Supplemental materials and dataset are available on our project webpage at https://sites.google.com/view/fabricfolding.

Collaborative robotics is a field of growing industrial interest, within which understanding the energetic behavior of manipulators is essential. In this work, we present the electro-mechanical modeling of the UR5 e-series robot through the identification of its dynamics and electrical parameters. By means of the identified robot model, it is then possible to compute and optimize the energy consumption of the robot during prescribed trajectories. The proposed model is derived from data acquired from the robot controller during bespoke experimental tests, using model identification procedures and datasheet provided by manipulator, motors, and gearbox manufacturers. The entire procedure does not require the use of any additional sensor, so it can be easily replicated with an off-the-shelf manipulator, and applied to other robots of the same family.

This paper presents a concurrent optimization approach for the design and motion of a quadruped in order to achieve energy-efficient cyclic behaviors. Computational techniques are applied to improve the development of a novel quadruped prototype. The scale of the robot and its actuators are optimized for energy efficiency considering the complete actuator model including friction, torque, and bandwidth limitations. This method and the optimal bounding trajectories are tested on the first (non-optimized) prototype design iteration showing that our formulation produces a trajectory that (i) can be easily replayed on the real robot and (ii) reduces the power consumption w.r.t. hand-tuned motion heuristics. Power consumption is then optimized for several periodic tasks with co-design. Our results include, but are not limited to, a bounding and backflip task. It appears that, for jumping forward, robots with longer thighs perform better, while, for backflips, longer shanks are better suited. To explore the tradeoff between these different designs, a Pareto set is constructed to guide the next iteration of the prototype. On this set, we find a new design, which will be produced in future work, showing an improvement of at least 52% for each separate task.