As a kind of lower-limb motor assistance device, the intelligent walking aid robot plays an essential role in helping people with lower-limb diseases to carry out rehabilitation walking training. In order to enhance the safety performance of the lower-limb walking aid robot, this study proposes a deep vision-based abnormal lower-limb gait prediction model construction method for the problem of abnormal gait prediction of patients’ lower limbs. The point cloud depth vision technique is used to acquire lower-limb motion data, and a multi-posture angular prediction model is trained using long and short-term memory networks to build a model of the user’s lower-limb posture characteristics during normal walking as well as a real-time lower-limb motion prediction model. The experimental results indicate that the proposed lower-limb abnormal behavior prediction model is able to achieve a 97.4% prediction rate of abnormal lower-limb movements within 150 ms. Additionally, the model demonstrates strong generalization ability in practical applications. This paper proposes further ideas to enhance the safety performance of lower-limb rehabilitation robot use for patients with lower-limb disabilities.

This paper introduces a novel bipedal robot model designed for adaptive transition between walking and running gaits solely through changes in locomotion speed. The bipedal robot model comprises two sub-components: a mechanical model for the legs that accommodates both walking and running and a continuous state model that does not explicitly switch states. The mechanical model employs a structure combining a linear cylinder with springs, dampers, and stoppers, designed to have mechanistic properties of both the inverted pendulum model used for walking and the spring-loaded inverted pendulum model used for running. The state model utilizes a virtual leg representation to abstractly describe the actual support leg, capable of commonly representing both a double support leg in walking and a single support leg in running. These models enable a simple gait controller to determine the kick force and the foot touchdown point based solely on the parameter of the target speed, thus allowing a robot to walk and run stably. Hence, simulation validation demonstrates the adaptive robot transition to an energy-efficient gait depending on locomotion speed without explicit gait-type instructions and maintaining stable locomotion across a wide range of speeds.

The virtual model control (VMC) method establishes a direct correlation model between the end-effector and the main body by selecting appropriate virtual mechanical components. This approach facilitates direct force control while circumventing the necessity for complex dynamic modeling. However, the simplification inherent in this modeling can result in inaccuracies in the calculation of joint driving torques, ultimately diminishing control precision. Moreover, VMC typically depends on predefined models for control, which constrains its adaptability in dynamically complex environments and under varying movement conditions. To address these limitations, this paper proposes the BP-VMC method, which is based on a backpropagation neural network (BPNN). Initially, a quadruped robot model was established through kinematic analysis. Subsequently, a decomposed VMC model was developed, and BPNN was introduced to facilitate the adaptive tuning of virtual parameters. This approach resulted in the creation of a virtual mechanical component model with adaptive capabilities, compensating for errors arising from simplified modeling. Finally, a simulation control system was constructed based on the BP-VMC control framework to validate the optimization of control performance. Simulation experiments demonstrated that, in comparison to traditional VMC methods, the BP-VMC method exhibits enhanced control accuracy and stability, achieving a 30% reduction in trajectory tracking error, a 40% reduction in velocity tracking error, and a 20–30% improvement in instability indices across various working conditions. This evidence underscores the BP-VMC method’s robust adaptability in dynamic environments.

In order to make a fast and accurate response to gas leakage event, e.g. gas leakage in hydrogen storage station, it is very important to identify and locate the leakage source accurately and quickly. Due to the flexibility and the adaptability of robots to harsh environments, leakage source tracing based on mobile robots has attracted more and more attention. However, the existing ground robots are limited by the ground environment and thus it is difficult to trace and locate the leakage in the complex environment with ground robots. Although unmanned aerial vehicle (UAV) can overcome the limitation of ground obstacles, there are still some problems in the accuracy and reliability of gas sampling due to the interference of flow field caused by UAV rotors to the surrounding gases. Based on computational fluid dynamic simulation, a simulation model of UAV with four rotors was established. Combined with test experiments, the influence of flow field around UAV on gas sampling under different UAV speeds, rotors assembly structures, leakage, and sampling conditions was analyzed and investigated. The optimized UAV assembly structure and gas sensor installation position were determined and verified by the simulations and experiments. The results showed that the sensor was less affected by the rotor airflow when the UAV rotor was reversely assembled and the gases were sampled above the UAV. This research can provide a guidance for gas sampling for emission source tracing with UAV for process safety management of energy gas storage.

This paper presents a general approach to synthesizing closed-loop robots for machining and manufacturing of complex quadric surfaces, such as toruses, helicoids, and helical tubes. The proposed approach begins by employing finite screw theory to describe the motion sets generated by prismatic, rotational, and helical joints. Subsequently, generatrices and generating lines are put forward and combined for type synthesis of serial kinematic limbs capable of generating single-DoF translations along spatial curves and two-DoF translations on complex quadric surfaces. Following this manner, the two-DoF translational motion patterns on these complex quadric surfaces are algebraically defined and expressed as finite screw sets. Type synthesis of close-loop robots having the newly defined motion patterns can thus be carried out based upon analytical computations of finite screws. As application of the presented approach, closed-loop robots for machining toruses are synthesized, resulting in four-DoF and five-DoF standard and derived limbs together with their corresponding assembly conditions. Additionally, brief descriptions of robots for machining helicoids and helical tubes are provided, along with a comprehensive list of all the feasible limbs for these kinds of robots. The robots synthesized in this paper have promised applications in machining and manufacturing of spatial curves and surfaces, enabling precise control of machining trajectories ensured by mechanism structures and achieving high precision with low cost.

Gripping devices for harvesting fruits have such types of work as cutting, tearing and unscrewing. For apples, it is preferable to use slicing or unscrewing, while the fruit leg should not remain, damaging the apple during storage. In this article, we are developing a grab for harvesting apples. The gripper is used both for holding the fruit and for jamming, followed by unscrewing. One of the advantages is that the proposed method of collecting apples allows you not to waste time moving the manipulator from the tree to the basket, but only to grab and tear them off. The fruit enters the gripper device; after which it enters the fruit collection container through a rigid or flexible pipe. The gripper device is built on the basis of a ball-screw transmission, which is supplemented by a gear drive along the helical surface. This allows for rotation and rectilinear movement of the held fruit. The gripping device has a ratchet mechanism that allows you to fix the fruit. A mathematical model of the gripper device has been developed, which allows determining the torque of the engine depending on the position of the fingers. The parameters of the mechanism were optimized using a genetic algorithm, and the results are presented in the form of a Pareto set. A 3D model of the gripper device has been built and a layout has been developed using 3D printing. Experimental laboratory and field tests of the gripping device were carried out.

Trajectory optimization is a critical research area in robotics and automation, especially in manufacturing industries where mechanical systems are often required to minimize the execution time or the consumed energy. In this context, the most common mechanical systems are those with a single degree of freedom because of their simplicity and ease of control. In this paper, we present an approach for the online optimization of minimum-time and minimum-energy trajectories for a robotic system with one degree of freedom. Point-to-point motions of the considered linear axis are planned online, without idle times, by leveraging a verified dynamic model of the robotic system, which also includes an accurate identification of friction parameters. Both minimum-time and minimum-energy trajectories are considered, and the performance of the online optimization using a selected open-source optimization tool is verified in different dynamic conditions of the system. The results of extensive experiments on a belt-driven robotic axis demonstrate the feasibility and the energy-saving capabilities of the proposed approach, as well as the flexibility of the online trajectory optimization in different scenarios, while meeting the kinematics and dynamics limits of the system and guaranteeing low computational time.

Among various deep learning-based SLAM systems, many exhibit low accuracy and inadequate generalization on non-training datasets. The deficiency in generalization ability can result in significant errors within SLAM systems during real-world applications, particularly in environments that diverge markedly from those represented in the training set. This paper presents a methodology to enhance the generalization capabilities of deep learning SLAM systems. It leverages their superior performance in feature extraction and introduces Exponential Moving Average (EMA) and Bayes online learning to improve generalization and localization accuracy in varied scenarios. Experimental validation, utilizing Absolute Trajectory Error (ATE) metrics on the dataset, has been conducted. The results demonstrate that this method effectively reduces errors by $20\%$ on the EuRoC dataset and by $35\%$ on the TUM dataset, respectively.

This paper introduces an equivalent series mechanism model to improve ankle rehabilitation robots’ ability to recurrence the complex movements of the anthropo-ankle and enhance human-machine locomotion compatibility. The model emulates the true anatomical architecture of the ankle joint and is integrated with a parallel rehabilitative mechanism. The rehabilitative robot includes dual virtual motion centers to mimic the ankle joint’s intricate motion, accommodate individual patient variations, and address the rehabilitation requirements of both right and left feet. Firstly, a serial equivalence model of anthropo-ankle is developed based on the kinematic and anatomical characteristics of the human ankle. The type design for the 4-degree of freedom (4-DOF) parallel ankle rehabilitative robot is then conducted on the basis of the kinematical and restrictive properties of the anthropo-ankle equivalence kinematic model. Secondly, the mechanism’s motion properties allow it to be equivalent to a series branch chain, enabling the establishment of an inverse kinematics model. The kinematical performance of the mechanisms is analyzed using the transmissibility and constrainability indices, followed by workspace analysis and dimensional optimization of the rehabilitative mechanism. Finally, a human-machine coupled rehabilitative simulation model is developed using OpenSim biomechanics software to evaluate the recovery effect.

Aiming at the problems of many path inflection points, unsmooth paths, and poor local obstacle avoidance in path planning of inspection robots in static-dynamic scenes under complex geological conditions in coal mine roadways, a hybrid path planning method based on the improved A* algorithm and dynamic window approach (DWA) algorithm is proposed. First, the inspection robot platform and system model are constructed. An improved heuristic function that incorporates target weight information is proposed based on the A* global path planning algorithm. Additionally, redundant nodes are eliminated, and the path is smoothed using the Floyd algorithm and B-spline curves. Second, the global path planning A* algorithm and the local path planning DWA algorithm are fused. The dynamic path planning is carried out by setting the key node information of the global path extracted from the improved A* algorithm as the local target point of the DWA algorithm. On this basis, a grid map is established to simulate and analyze the proposed path planning algorithm. Finally, the autonomous path planning and walking experiment of inspection robot in simulated roadway environment are carried out. The results show that the hybrid path planning method based on improved A* algorithm and DWA algorithm proposed in this paper is more efficient and safer, which can meet the motion requirements of inspection robot in coal mine roadway.

This study presents an innovative framework to improve the accessibility and usability of collaborative robot programming. Building on previous research that evaluated the feasibility of using a domain-specific language based on behaviour-driven development, this paper addresses the limitations of earlier work by integrating additional features like a drag-and-drop Blockly web interface. The system enables end users to define and execute robot actions with minimal technical knowledge, making it more adaptable and intuitive. Additionally, a gesture-recognition module facilitates multimodal interaction, allowing users to control robots through natural gestures. The system was evaluated through a user study involving participants with varying levels of professional experience and little to no programming background. Results indicate significant improvements in user satisfaction, with the system usability scale overall score increasing from 7.50 to 8.67 out of a maximum of 10 and integration ratings rising from 4.42 to 4.58 out of 5. Participants completed tasks using a manageable number of blocks (5 to 8) and reported low frustration levels (mean: 8.75 out of 100) alongside moderate mental demand (mean: 38.33 out of 100). These findings demonstrate the tool’s effectiveness in reducing cognitive load, enhancing user engagement and supporting intuitive, efficient programming of collaborative robots for industrial applications.

In this work, we propose a novel approach for tomato pollination that utilizes visual servo control. The objective is to meet the growing demand for automated robotic pollinators to overcome the decline in bee populations. Our approach focuses on addressing this challenge by leveraging visual servo control to guide the pollination process. The proposed method leverages deep learning to estimate the orientations and depth of detected flower, incorporating CAD-based synthetic images to ensure dataset diversity. By utilizing a 3D camera, the system accurately estimates flower depth information for visual servoing. The robustness of the approach is validated through experiments conducted in a laboratory environment with a 3D printed tomato flower plant. The results demonstrate a high detection rate, with a mean average precision of 91.2 %. Furthermore, the average depth error for accurately localizing the pollination target is impressively minimal, measuring only 1.1 cm. This research presents a promising solution for tomato pollination, showcasing the effectiveness of visual-guided servo control and its potential to address the challenges posed by diminishing bee populations in greenhouses.

Compliant and safe human–robot interaction is an important requirement in lower limb exoskeleton design. Motivated by this need, this paper presents the design of a compatible lower limb exoskeleton with variable stiffness actuation and anthropomorphic joint mechanisms, for walking assistance and gait rehabilitation. A novel variable stiffness actuator (VSA) based on a guide-bar mechanism was designed, to provide force and impedance controllability. By changing the crank length of the mechanism, the stiffness of the actuator is adjusted in a wide range (from 0 to 1301 Nm/rad), at fast speed (about 2582 Nm/rad/s), and with low-energy cost. These features make it possible for online stiffness adjustment during one gait cycle, to change the human–robot coupling behavior and improve the performance of the exoskeleton. An anthropomorphic hip joint mechanism was designed based on a parallelogram linkage and a passive joint compensation approach, which absorbs misalignment and improves kinematic compatibility between the human and the exoskeleton joint. Furthermore, a torque control-based multimode control strategy, which consists of passive mode, active mode, and hybrid mode, was developed for different disease stages. Finally, the torque control performance of the actuator was verified by benchtop test, and experimental validations of the exoskeleton with a human subject were carried out, which demonstrate that compliant human–robot interaction was achieved, and stiffness variation benefits for control performance improvement when the control mode changes.

Unmanned surface vehicles (USVs) frequently encounter inadequate energy levels while navigating to their destinations, which complicates their successful berthing in intricate harbor environments. A bacterial foraging optimization algorithm (BFO) is proposed that takes energy consumption into account and incorporates multiple constraints (MC-BFO). The energy consumption model is redefined for wind environments, enhancing the sensitivity of USVs to wind conditions. Additionally, a reward function is integrated into the algorithm, and the fitness function is reconstructed to improve the goal orientation of the USV. This approach enables the USV to maintain a reasonable path length while pursuing low energy consumption, resulting in more practical navigation. Constraining the USV’s sailing posture for smoother paths and restricting the USV’s heading and speed near the berthage facilitate safe berthing. Finally, three distinct experimental environments are established to compare the paths generated by MC-BFO, BFO, and genetic algorithm under both downwind and upwind conditions, ensuring consistency in relevant parameters. Data on sailing posture, energy consumption, and path length are collected, generalized, and analyzed. The results indicate that MC-BFO effectively reduces energy consumption while maintaining an acceptable path length, resulting in smoother and more coherent paths compared to traditional segmented planning. In conclusion, this method significantly enhances the quality of the berthing path.

Precise pose estimation is crucial to various robots. In this paper, we present a localization method using correlative scan matching (CSM) technique for indoor mobile robots equipped with 2D-LiDAR to provide precise and fast pose estimation based on the common occupancy map. A pose tracking module and a global localization module are included in our method. On the one hand, the pose tracking module corrects accumulated odometry errors by CSM in the classical Bayesian filtering framework. A low-pass filter associating the predictive pose from odometer with the corrected pose by CSM is applied to improve precision and smoothness of the pose tracking module. On the other hand, our localization method can autonomously detect localization failures with several designed trigger criteria. Once a localization failure occurs, the global localization module can recover correct robot pose quickly by leveraging branch-and-bound method that can minimize the volume of CSM-evaluated candidates. Our localization method has been validated extensively in simulated, public dataset-based, and real environments. The experimental results reveal that the proposed method achieves high-precision, real-time pose estimation, and quick pose retrieve and outperforms other compared methods.

Efficient local trajectory optimization of the coordinated manipulator is a bottleneck task in the narrow feeding scenario. To optimize the trajectory locally and generate collision-free trajectories with local support performance, the analytical reinforcement method is proposed. Firstly, multiple coordinated machines operating in the narrow space are transformed into decentralized dynamic constraints for the target manipulator. Combined with the circle envelope method in the dynamic constraint, the collision-free gradient optimization function determines the support region of the local optimal trajectory. Based on the forward kinematics and inverse kinematics method, the collision-prone pose of the target manipulator outside the support region is analytically optimized. And chi-square distribution further ensures the smooth interpolation of the variable-period trajectory outside the fixed-period support region. For the emergency collision avoidance of the coordinated manipulator in the flexible stamping line, the analytical reinforcement method is successfully verified by generating the collision-free and smooth trajectory. It provides an optimization direction for rapidly improving the work efficiency of multi-machine coordination in the narrow feeding scenario.

Parallel manipulators (PMs) are adopted in different fields due to their superior characteristics compared to serial manipulators. PMs with flexible links are likely more energy efficient and have high dynamic performance since they are lighter than those with rigid links. On the other hand, due to their lightweight design, the flexibility can lead to undesired deformation and vibration, decreasing the tracking trajectory and transient errors. This work proposes a two-loop active vibration control strategy, using strain gauges and piezoelectric lead zirconate (PZT) actuators, to compensate for the undesired effect of the flexibility. A pose control loop exploits the sliding mode control using data collected from images acquired by an oCam-5CRO-U camera, while the active vibration control loop uses strain gauge sensors and PZT actuators. Strain gauges are responsible for measuring the deformation of each link, and after being treated by digital filters, these signals are applied to the PZT actuator. Combining both loops allows the manipulator to be guided over the desired trajectory with positive vibration attenuation. The results reveal that the presence of the PZT on both sides of the flexible links increases the links’ rigidity, yielding overshoot and vibration reduction during the manipulator’s motion. In addition, the maximum peak is significantly attenuated, and the overall oscillations are also positively reduced when using the two-loop active control strategy. The root mean square error quantifies this attenuation, showing an average reduction of 30% in the corresponding step input directions. Therefore, the proposal improves the system performance by enhancing the tracking trajectory with lower vibrations.

Designing autonomous robotic systems for monitoring tasks in critical security scenarios requires more rigorous verification criteria. The losses associated with unsuccessful practical experiments are immeasurable, ranging from the simple loss of high-value-added equipment to those related to loss of life. This reality justifies the need to adopt an extensive framework of tools for realistic, efficient, and responsive computer simulation. This article proposes a novel integration architecture and combines open-source tools to promote the successful implementation of autonomous robotic systems in monitoring tasks. The proposed solution relies on consolidated tools like Robot Operating System (ROS), Gazebo Simulator, and ArduPilot FCU (Flight Control Unit). It includes full support for implementing XITL techniques (such as Model, Software, and Hardware) – in the Loop. Experimental results demonstrate the proposal’s effectiveness for a new model of autonomous surface vehicles (ASVs) in a realistic environment, dedicated to environmental monitoring in challenging natural conditions, commonly found in a stretch of the Madeira River – Brazil, specifically at Santo Antônio hydroelectric plant.

Navigation is an important skill required for an autonomous robot, as information about the location of the robot is necessary for making decisions about upcoming events. The objective of the localization technique is “to know about the location of the collected data.” In previous works, several deep learning methods were used to detect localization, but none of them gives sufficient accuracy. To address this issue, an Enhanced Capsule Generation Adversarial Network and optimized Dual Interactive Wasserstein Generative Adversarial Network for landmark detection and localization of autonomous robots in outdoor environments (ECGAN-DIWGAN-RSO-LAR) is proposed in this manuscript. Here, the outdoor robot localization dataset is taken from the Virtual KITTI dataset. It contains two phases, which are landmark detection and localization. The landmark detection phase is determined using Enhanced Capsule Generation Adversarial Network for detecting the landmark of the captured image. Then the robot localization phase is determined using Dual Interactive Wasserstein Generative Adversarial Network (DIWGAN) for determining the robot location coordinates as well as compass orientation from identified landmarks. After that, the weight parameters of the DIWGAN are optimized by Rat Swarm Optimization (RSO) algorithm. The proposed ECGAN-DIWGAN-RSO-LAR is implemented in Python. The efficiency of the proposed ECGAN-DIWGAN-RSO-LAR technique shows higher accuracy of 22.67%, 12.45 %, and 8.89% compared to the existing methods.

Pouch-type actuators have recently garnered significant interest and are increasingly utilized in diverse fields, including soft wearable robotics and prosthetics. This is largely due to their lightweight, high output force, and low cost. However, the inherent hysteresis behavior markedly affects the stability and force control of pouch-type driven systems. This study proposes a modified generalized Prandtl–Ishlinskii (MGPI) model, which includes generalized play operators, the tangent envelope function, and one-sided dead-zone operators, to describe the asymmetric and non-convex hysteresis characteristics of pouch-type actuators. Compared to a classical Prandtl–Ishlinskii (PI) model incorporating one-sided dead-zone functions, the MGPI model exhibits smaller relative errors at six different air pressures, demonstrating its capability to accurately describe asymmetric and non-convex hysteresis curves. Subsequently, the MGPI hysteresis model is integrated with displacement sensing technology to establish a load compensation control system for maintaining human posture. Four healthy subjects are recruited to conduct a 1 kg load compensation test, achieving efficiencies of 85.84%, 84.92%, 83.63%, and 68.86%, respectively.