Screw theory serves as an influential mathematical tool, significantly contributing to mechanical engineering, with particular relevance to mechanism science and robotics. The instantaneous screw and the finite displacement screw have been used to analyse the degree of freedom and perform kinematic analysis of linkage mechanisms with only lower pairs. However, they are not suitable for higher pair mechanisms, which can achieve complex motions with a more concise structure by reasonably designing contact contours, and they possess advantages in some particular areas. Therefore, to improve the adaptability of screw theory, this paper aims to analyse higher kinematic pair (HKP) mechanisms and proposes a method to extend instantaneous screw and finite displacement screw theory. This method can not only analyse the instantaneous degree of freedom of HKP mechanisms but also determine the relationships between the motion variables of HKP mechanisms. Furthermore, this method is applied to calculate the degree of freedom and the relationships between the motion angles in both planar and spatial cam mechanisms, thereby demonstrating its efficiency and advantages.

In firefighting missions, human firefighters are often exposed to high-risk environments such as intense heat and limited visibility. To address this, firefighting robots can serve as valuable agents for autonomous navigation and flame perception. This paper proposes a novel visual Simultaneous Localization and Mapping (SLAM) framework, Fire SLAM, tailored for firefighting scenarios. The system integrates a flame detection and tracking thread-based on the YOLOv8n network and Kalman filtering-to achieve real-time flame detection, tracking, and 3D localization. By leveraging the detection results, dynamic flame regions are excluded from the SLAM front-end, allowing static features to be used for robust pose estimation and loop closure. To validate the proposed system, multiple datasets were collected from real-world and simulated fire environments. Experimental results demonstrate that Fire SLAM improves localization accuracy and robustness in fire scenes with flame disturbances, showing promise for autonomous firefighting robot deployment.

A modeling method of multi-objective optimization design for parallel mechanisms (PMs) is proposed, whose implementation is illustrated with 2RPU-RPS mechanism as an example. The orientation of biased output axis on moving platform is depicted by spherical attitude angles, and its kinematic model is deduced through vector method. With screw theory as mathematic tool, a comprehensive evaluation method of kinematic performance for PM is established. On this basis, the expensive constrained multi-objective optimization model of dimensional parameters for the discussed mechanism is constructed. The NSDE-II algorithm, formed by replacing the genetic algorithm operators in non-dominated sorting genetic algorithm II (NSGA-II) with DE operators, is utilized to solve this multi-objective optimization problem, thus obtaining multiple Pareto optimal solutions with engineering application significance, which proves the feasibility and effectiveness of the proposed modeling method and algorithm. Moreover, the normalization coverage space and the minimum adjacent vector angle are proposed to evaluate the computational performance of NSDE-II. Finally, the potential engineering application value for the optimized 2RPU-RPS PM is presented.

This paper deals with the optimization of a new redundant spherical parallel manipulator (New SPM). This manipulator consists of two spherical five-bar mechanisms connected by the end-effector, providing three degrees of freedom, and has an unlimited self-rotation capability. Three optimization procedures based on the genetic algorithm method were carried out to improve the dexterity of the New SPM. The first and the second optimizations were applied to a symmetric New SPM structure, while the third was applied to an asymmetric New SPM structure. In both cases, the optimization was performed using an objective function defined by the quadratic sum of link angles. In addition, certain criteria and constraints were implemented. The obtained results demonstrate significant improvements in the dexterity of the New SPM and its capability of an unlimited self-rotate in an extended workspace. A comparison of the self-rotation performances between the classical 3-RRR SPM (R for revolute joint) and the New SPM is also presented.

Upper extremity rehabilitation robots have become crucial in stroke rehabilitation due to their high durability, repeatability, and task-specific capabilities. A significant challenge in assessing the comfort performance of these robots is accurately calculating the human-robot interaction forces. In this study, a four-degree-of-freedom (4-DOF) upper extremity rehabilitation robot mechanism, kinematically compatible with the human upper limb, is proposed. Based on this mechanism, an algorithm for estimating human-robot interaction forces is developed using Newton-Euler dynamics. A prototype of the proposed robot is constructed, and a series of comparative experiments are carried out to validate the feasibility of the proposed force estimation approach. The results indicate that the proposed method reliably predicts interaction forces with minimal deviation from experimental data, demonstrating its potential for application in upper limb rehabilitation robots. This work provides a foundation for future studies focused on comfort evaluation and optimization of rehabilitation robots, with significant practical implications for improving patient rehabilitation outcomes.

This paper presents a novel control framework for achieving collision-free trajectory tracking in tractor-trailer mobile robots (TTMRs) within both static and dynamic environments. This study addresses the challenges posed by nonholonomic constraints and kinematic coupling inherent in TTMR systems. An inverse kinematic control strategy, augmented with pure integral controllers, is proposed to ensure precise trajectory tracking. The control framework is further enhanced using three obstacle avoidance approaches: two customized artificial potential field (APF) approaches and a novel path planning mode (PPM) for continuous-time trajectory adjustment. APF methods, applied for the first time to TTMR trajectory tracking, incorporate gravitational and repulsive forces to guide the robot away from obstacles, whereas PPM dynamically generates a semi-circular trajectory when the robot approaches an obstacle. Case studies validate the effectiveness of the proposed strategy in accurate trajectory tracking and safe obstacle avoidance. Comparative analyses highlight the superior performance of PPM in managing complex environments.

In response to the prevailing trend of an aging society and the increasing requirements of rehabilitation, this paper presents an approach involving brain-machine interaction (BMI) for a single-degree-of-freedom (1-DOF) sit-to-stand transfer robot. Based on a 1-DOF rehabilitation robot, three experiment paradigms involving motor imagery (MI), action observation of motor imagery (AO-MI) and motor execution are designed using both electroencephalography (EEG) and electromyography (EMG). To enhance motion intention recognition accuracy, a Gumbel-ResNet-KANs decoding model is established. The Gumbel-ResNet-KANs model integrates the Gumbel-Softmax method with the ResNet-KANs network module and demonstrates strong decoding capability, as demonstrated by comparative tests in this paper. To validate the effect of robotic assistance, EEG and EMG coherence are analyzed to assess the impact of robotic assistance on rehabilitation from a neuromuscular perspective in both assisted and unassisted conditions. We assessed the effect of robotics on rehabilitation from an emotional perspective by analyzing the difference between the differential entropy of the right and left brain. The proposed study also reveals that the movement-related cortical potentials in AO-MI are beneficial for promoting the performance of BMI in sit-to-stand training, which provides a possible approach for the development of new types of robots for lower limb rehabilitation.

The path navigation of robot in an entirely known space is presented by various researchers in the recent times. The navigational complexity arises when a robot moves in a completely unknown and complex environment from one defined start to a designated desired location. As the success of the nature-inspired algorithms in the unclear navigational problem is better, therefore, an improved butterfly optimization algorithm (IBOA) to determine the optimal feasible path for a humanoid robot navigating through a platform cluttered with both known and unfamiliar barriers is presented in this study. The BOA is inspired by the food-gathering habits of butterflies, where the sense of smell is the vital parameter in the global optimal search. However, the performance of this technique in the complex environment is poor, as a result, the chances of being trapped in local minima are more. Hence, the BOA is improved by using a nonlinear weight reduction strategy in updating the position of the butterflies in every iteration. The simulation is carried out in the Webots platform by considering variable-legged robot, NAO, in an unfamiliar environment. The outcomes derived from the simulation and real assessments demonstrate the potential of the proposed technique and compare with other existing algorithms, which highlights the potential and efficacy of the proposed IBOA algorithm.

A flexible power assistive exoskeleton is proposed in this study to overcome limitations in range of motion, assistance, and comfort existing in current exoskeletons. The flexible power assistive exoskeleton is made of three springs that store energy from shoulder movements to provide assistance. It uses biomechanical models to simulate muscle forces. It is highly portable and comfortable, with only 83.29 g weight. A theoretical model was established to address the relationship between body work and output force. An evaluation system is proposed to assess the comfort effect of the assistive exoskeleton. Results show that the assistive exoskeleton can support all ranges of motion for the human upper limbs. It can offer up to 14.2% assistance. It also has a mass-to-assistance value of 120. For a comforting evaluation, its satisfaction rate reaches 93.4%. In summary, we present a highly flexible power-assisted exoskeleton with a large motion range, noticeable assistance effect, and high comfortability. This work contributes to the development of flexible assistive exoskeletons and comforting evaluation strategies for wearable devices.

This paper proposes a mobile robot recovery mechanism for low-cost robotic systems due to vision sensor failure in vSLAM systems. The approach takes advantage of ROS architecture and adopts the Shannon Nyquist sampling theory to selectively sample path parameters that will be used for back travel in case of vision sensor failure. As opposed to point clouds normally used to store vSLAM data, this paper proposes to store and use lightweight variables namely distance between sampled points, velocity combinations, i.e., linear and angular velocity, sampled period, and yaw angle values to describe the robot path and reduce the memory space required to store these variables. In this study, low-cost robotic systems typically using cameras aided by proprioceptive sensors such as IMU during vSLAM activities are investigated. A demonstration is made on how the ROS architecture can be used in a scenario where vision sensing is adversely affected, resulting in mapping failure. Additionally, a recommendation is made for adoption of the approach for vSLAM platforms implemented on both ROS1 and ROS2. Furthermore, a proposal is made to add an additional layer to vSLAM systems that will be exclusively used for back travel in case of vision loss during vSLAM activities resulting in mapping failure.

A multi-modal embodied robot framework was developed and evaluated to support English as a Second Language (ESL) learning in preschoolers through physical interaction and adaptive engagement. The system integrates a 4-DOF OpenManipulator-X robot with a tablet-based educational application, forming a unified instructional platform that delivers synchronized auditory, visual, and kinesthetic stimuli. Designed to improve lexical retention and motivation in early learners, the framework enables task-based interaction through pick-and-place vocabulary reinforcement, collaborative drawing, and tablet-mediated language tasks, coupled with a real-time emotion recognition module to adjust instructional cues.

An experimental design within the subject was used with 21 Korean preschool children (ages 4–8), comparing robot-assisted language learning (RALL) with traditional teacher-led language learning (TLLL) in matched tasks involving vocabulary learning, math reasoning, color categorization, and spelling recall. Each session was conducted under controlled classroom conditions and analyzed using both quantitative and qualitative metrics, including engagement frequency, task precision, and structured post-session surveys.

The results demonstrate significantly higher participation and task completion rates in the RALL condition, with vocabulary acquisition outcomes comparable to TLLL (p > 0.05). Children exhibited increased motivation and sustained interaction when guided by the robot and the application, suggesting that embodied adaptive systems can effectively support early second language learning. The study contributes validated design principles for integrating physical embodiment, affective responsiveness, and multi-modal instructional delivery in educational robotics. Implications are discussed for the scalable deployment of robot-assisted systems in preschool contexts, emphasizing child-centered interaction and developmental appropriateness within RALL environments.

Industrial robots are widely utilized in the machining of complex parts because of their flexibility. However, their low positioning accuracy and spatial geometric error characteristics significantly limit the contour precision of robot machined parts. Therefore, in the robot machining procedure, an in situ measurement system is typically required. This study aims to enhance the trajectory accuracy of robotic machining through robotic in situ measurement and meta-heuristic optimization. In this study, a measurement-machining dual-robot system for measurement and machining is established, consisting of a measurement robot with a laser sensor mounted at the robot end and a machining robot equipped with a machining tool. In the measuring process, high-precision standard spheres are set on the edge of the machining area, and the high-precision standard geometry is measured by the measurement robot. According to measured geometry information in the local area, the trajectory accuracy for the machining robot is improved. By utilizing the standard radius of the standard spheres and adopting a meta-heuristic optimization algorithm, this study addresses the complexity of the robot kinematics model, while also overcoming local optima commonly introduced by gradient-based iterative methods. The results of the experiments in this study confirm that the proposed method markedly refines the precision of the robot machining trajectory.

Learning has recently played a vital role in control engineering, producing numerous applications and facilitating easier control over systems; however, it has presented serious challenges in flight learning for unmanned platforms. Iterative learning control (ILC) is a practical method for cases needing repetition in control loops. This work focuses on the ILC of a quadrotor flight. An unstable flight might lead to a crash in the system and stop the iterations; hence, a base controller, the state-dependent Riccati equation (SDRE), is selected to stabilize the drone in the first loop. The ILC acts on top of the SDRE to increase the precision and force the system to learn to track trajectories better. The combination of ILC and SDRE was tested for stationary (fixed-base) systems without the risk of crashes; nonetheless, its implementation on a flying (mobile) system is reported for the first time. The gradient descent method shapes the training criteria for error reduction in the ILC. The proposed design is implemented on simulation and a real flight of a quadrotor in a series of tests, showing the effectiveness of the proposed input law. The nonlinear and optimal structure of the base controller and the complex iterative learning programming were challenges of this work, which were successfully addressed and demonstrated experimentally.

This paper focuses on the feature-based visual-inertial odometry (VIO) in dynamic illumination environments. While the performance of most existing feature-based VIO methods is degraded by the dynamic illumination, which leads to unstable feature association, we propose a tightly-coupled VIO algorithm termed RAFT-VINS, integrating a Lite-RAFT tracker into the visual inertial navigation system (VINS). The key module of this odometry algorithm is a lightweight optical flow network designed for accurate feature tracking with real-time operation. It guarantees robust feature association in dynamic illumination environments and thereby ensures the performance of the odometry. Besides, to further improve the accuracy of the pose estimation, a moving consistency check strategy is developed in RAFT-VINS to identify and remove the outlier feature points. Meanwhile, a tightly-coupled optimization-based framework is employed to fuse IMU and visual measurements in the sliding window for efficient and accurate pose estimation. Through comprehensive experiments in the public datasets and real-world scenarios, the proposed RAFT-VINS is validated for its capacity to provide trustable pose estimates in challenging dynamic illumination environments. Our codes are open-sourced on https://github.com/USTC-AIS-Lab/RAFT-VINS.

Capturing the non-cooperative tumbling target by the free-floating space robot stands as a crucial task within on-orbit servicing. However, the strong dynamic coupling of the base-spacecraft and the manipulator seriously disturbs the base-spacecraft, which reduces the power generation efficiency of solar panels and the communication quality with the earth station. In this paper, the trajectory planning method of the free-floating space robot for non-cooperative tumbling target capture based on deep reinforcement learning is proposed, which can reduce the disturbance of the base-spacecraft during target capture. First, the generalized Jacobian matrix of the space robot is derived, from which the dynamics model is obtained. The kinematics model of the space non-cooperative tumbling target is established. And the contact collision dynamics between the space robot and the tumbling target are analysed. Second, the twin delayed deep deterministic policy gradient algorithm is introduced to plan the trajectory for capturing the non-cooperative tumbling target, where apart from the motion parameters of the manipulator and the generalized manipulability of the space robot, the pose disturbance of the base-spacecraft is initially added to the reward function. Finally, the simulation for target capture is carried out. The results show that compared with the existing method, the proposed method converges faster with a larger reward, and the pose disturbance of the base-spacecraft is reduced. Moreover, the method performs well for capturing the non-cooperative tumbling target with different initial rotational angular velocities.

In this paper, a novel fast nonsingular integral terminal sliding mode controller based on an adaptive neural network (ANN-FNITSMC) is proposed for the trajectory tracking control of cable-driven continuum robots (CDCRs) in complex underwater environments with uncertainties. First, a novel fast nonsingular integral terminal sliding mode control (FNITSMC) is designed to solve the chattering and singularity problems of the conventional terminal sliding mode control (TSMC). Second, an adaptive neural network (ANN) based on a radial basis function (RBF) is established to derive the uncertainties and compensate for the control input of CDCRs, enabling high-stable accuracy and strong robustness trajectory tracking in complex underwater environments. Simulation results are presented to demonstrate the high accuracy and strong robustness of the ANN-FNITSMC. Finally, the high accuracy, high stability, and strong robustness of the proposed trajectory tracking strategy are verified through an underwater experiment platform.

In this paper, fractional-order (FO), intelligent, and robust sliding mode control (SMC) and stabilization of inherently nonlinear, multi-input, multi-output 6-DOF robot manipulators are investigated. To ensure robust control and better performance of the robot system, significant studies on various control transactions have been explored. First, a sliding proportional-integral-derivative (PID) surface is conceived and then its FO constitute is developed. It is an important fact that in SMC, the reaching phase is fast and the chattering is abated in the sliding phase. In particular, the discontinuity in the SMC is prevented in view of the boundary layer obtained by recommending the sigmoid function together with fuzzy logic to eliminate the chattering phenomenon. A hybrid tuning method consisting of gray wolf optimization and particle swarm optimization (GWO-PSO) algorithms is applied to tune the parameters of PID sliding mode control (PIDSMC), FO PIDSMC (FOPIDSMC), fuzzy PIDSMC (FPIDSMC), and FO fuzzy PIDSMC (FOFPIDSMC) controllers. In simulation results, the tuned FOFPIDSMC controller consistently outperforms PIDSMC, FOPIDSMC, and FPIDSMC controllers tuned by the GWO-PSO in dynamic performance, trajectory tracking, disturbance rejection, and mass uncertainty scenarios. It has been seen through a thorough performance analysis that 91.93% and 44.13% improvement are, respectively, obtained for mean absolute error (MAE) and torques root mean square (RMS) values of the joints when using from the PIDSMC to the FOFPIDSMC. Finally, the simulation outcomes reveal the superior aspects of the designed FOFPIDSMC and also demonstrate that the FOFPIDSMC controller enhances the dynamic performances of the 6-revolute universal robots 5 (6R UR5) robot manipulator under a variety of operating conditions.

The underwater target detection is affected by image blurring caused by suspended particles in water bodies and light scattering effects. To tackle this issue, this paper proposes a reparameterized feature enhancement and fusion network for underwater blur object recognition (REFNet). First, this paper proposes the reparameterized feature enhancement and gathering (REG) module, which is designed to enhance the performance of the backbone network. This module integrates the concepts of reparameterization and global response normalization to enhance the network’s feature extraction capabilities, addressing the challenge of feature extraction posed by image blurriness. Next, this paper proposes the cross-channel information fusion (CIF) module to enhance the neck network. This module combines detailed information from shallow features with semantic information from deeper layers, mitigating the loss of image detail caused by blurring. Additionally, this paper replace the CIoU loss function with the Shape-IoU loss function improves target localization accuracy, addressing the difficulty in accurately locating bounding boxes in blurry images. Experimental results indicate that REFNet achieves superior performance compared to state-of-the-art methods, as evidenced by higher mAP scores on the underwater robot professional competitionand detection underwater objects datasets. REFNet surpasses YOLOv8 by approximately 1.5% in $mAP_{50:95}$ on the URPC dataset and by about 1.3% on the DUO dataset. This enhancement is achieved without significantly increasing the model’s parameters or computational load. This approach enhances the precision of target detection in challenging underwater environments.

In this study, we introduce a real-time pose estimation for a class of mobile robots with rectangular body (e.g., the common automatic guided vehicles), by integrating odometry and RGB-D images. First, a lightweight object detection model is designed based on the visual information. Then, a pose estimation algorithm is proposed based on the depth value variations within the target region that exhibit specific patterns due to the robot’s three-dimensional geometry and the observation perspective (termed as “differentiated depth information”). To improve the robustness of object detection and pose estimation, a Kalman filter is further constructed by incorporating odometry data. Finally, a series of simulations and experiments are conducted to demonstrate the method’s effectiveness. Experiments show that the proposed algorithm can achieve a speed over 20 Frames Per Second (FPS) together with a good estimation accuracy on a mobile robot equipped with an Nvidia Jetson Nano Developer KIT.