This study introduces an innovative deep learning method for intelligent healthcare emotion analysis, specifically targeting the recognition of pain based on facial expressions. The suggested approach combines cloud-based mobile applications, utilising separate front-end and back-end elements to optimise data processing. The main contributions consist of a Smart Automated System (SASys) that integrates statistical and deep learning methods to extract features, thereby guaranteeing both resilience and efficiency. Image preprocessing encompasses the tasks of detecting faces and normalising them, which is crucial for extracting features with high accuracy. The comparison of statistical feature representation using Histogram of Oriented Gradients and Local Binary Pattern, along with machine learning classifiers, against an enhanced deep learning-based approach with an integrated multi-tasking feature known as multi-task convolutional neural network, demonstrates encouraging outcomes that support the superiority of the convolutional neural network architecture. Statistical and deep learning-based classification scores, when combined, greatly enhance the system’s overall performance. The results of the experiments prove that the method is effective, outperforming traditional classifiers and exhibiting comparable accuracy to cutting-edge healthcare SASys.

With advancements in industrial robot technology and the ongoing enhancements in control system performance, the demand for precise robot motion is increasing. Generally, an increased number of interpolation points enhances the precision of robot movement, but excessive points can lead to jittering and out-of-step issues. This paper investigates the relationship between the number of motion interpolation points and the response times of the control system and the robot’s terminal velocity, based on the theoretical calculation and experimental analysis of the limit interpolation points for the control system of a self-developed 6-DOF (Six Degree of Freedom) robot. The method for calculating limit interpolation points is refined using the least squares method, and equations are derived for different control system response time and robot’s terminal velocity reaction times. The validity of the prediction curves is verified through experimental analysis.

This paper proposes a LiDAR-inertial odometry (LIO) based on the dynamic voxel merging and smoothing method, DV-LIO. In this approach, a local map management mechanism based on feature distribution is introduced to unify the features of similar adjacent voxels through dynamic merging and segmentation, thereby improving the perceptual consistency of environmental features. Moreover, a novel noise detector that performs noise detection and incremental filtering by evaluating the consistency of voxel features is designed to further reduce local map noise and improve mapping accuracy while ensuring real-time algorithm performance. Meanwhile, to ensure the computational efficiency of the LIO system, a point cache is set for each voxel, which allows the voxel to be updated incrementally and intermittently. The proposed method is extensively evaluated on datasets gathered over various environments, including campus, park, and unstructured gardens.

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.

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 addresses the issue of energy-efficient trajectory optimization for planetary surface manipulators under kinematic and dynamic constraints. To mitigate the inefficiency of existing algorithms, an adaptive boundary adjustment strategy for the multi-dimensional decision space is proposed, which modifies the time intervals between neighboring configuration nodes, enabling precise adaptation of the decision space boundaries. Additionally, a complementary dual-archive guided boundary exploration strategy is introduced to connect the feasible and infeasible regions, allowing for the effective utilization of information from infeasible solutions near the constraint boundaries. This heuristic approach guides the particle swarm in efficiently exploring areas close to the constraints, significantly enhancing the evolutionary optimization capability of the swarm. Furthermore, a swarm optimal position updating strategy based on sparsity sorting is developed. This guides the particle swarm to concentrate on exploring positions where non-dominated solutions on the Pareto front are more sparsely distributed, ensuring uniformity and completeness in the final Pareto front. Finally, the aforementioned strategies are integrated into a heuristic multi-objective particle swarm optimization (HMOPSO) algorithm for the trajectory optimization of manipulators. Comparative experiments are conducted with HMOPSO and existing advanced algorithms in the field of multi-objective optimization. Experimental results demonstrate that HMOPSO exhibits superior evolutionary optimization capabilities and faster convergence rates. Moreover, performance metrics such as inverse generation distance and dominant area during the iterative process of HMOPSO significantly outperform those of existing optimization algorithms.

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.

Collaborative robotics in manufacturing introduces a new era of seamless human–robot collaboration (HRC), enhancing production line efficiency and adaptability. However, guaranteeing safe interaction while maintaining performance objectives presents significant challenges. Integrating safety with optimal robot performance is paramount to minimize task time and ensure its completion. Our work introduces an architecture for safety in confined human–robot workspaces by integrating existing safety and productivity methods into a unified framework specifically designed for constrained environments. By employing an improved artificial potential field, we optimize paths based on length and bending energy and compare baseline algorithms like gradient descent algorithm and rapidly exploring random tree (RRT*). We propose an evaluation metric for system performance that objectively maps to the system’s safety and efficiency in diverse collaborative scenarios. Additionally, the architecture supports multimodal interaction, including gesture-based inputs, for intuitive control and improved operator experience. Safety measures address static and dynamic obstacles using potential fields and safety zones, with a real-time safety evaluation module adjusting trajectories under specified constraints. A performance recovery algorithm facilitates swift resumption of high-speed operations post safety interventions. Validation includes comparing the algorithmic performance through simulations and experiments using the 6-degrees of freedom UR5 robot by universal robots to identify the most suitable algorithm. Results demonstrate an 83.87% improvement in system performance compared to ideal case scenarios, validating the effectiveness of the proposed architecture, evaluation metric, and multimodal interaction in enhancing safety and productivity.

In this article, the performance analysis and multiobjective structure optimization of 4RRR parallel mechanism are carried out. Firstly, the 4RRR pure rotation parallel mechanism and its design route are introduced. Secondly, the Jacobian matrices in 2DoF pure rotation and 3DoF pure rotation modes are derived using the motion equations of the mechanism. Next, the singularity analysis, kinematic dexterity analysis, dynamic dexterity analysis, and stiffness analysis of the mechanism are carried out, respectively, and it is proved that there is no singularity in the mechanism in its workspace. Since the dexterity performance expression is a nonlinear piecewise function, the kinematic local comprehensive dexterity index and the dynamic local comprehensive dexterity index are proposed as the objects of analysis. Furthermore, the kinematic global comprehensive dexterity index, the dynamic global comprehensive dexterity index, and the global comprehensive stiffness index are proposed to carry out the multiobjective structural optimization. Finally, NSGA3 was used to complete the optimization, and the comprehensive optimal solution of the structure size was obtained.

Humanoid robots are highly redundant, and finding whole-body optimal trajectories for various tasks is very complex. This paper proposes a method to find an energy-optimal, dynamically balanced, and collision-free trajectory of the 20 degrees of freedom humanoid robot in pick and place application. The task of pick and place is divided into three subtasks using the Pseudoinverse Jacobian method of redundancy resolution. The three subtasks are end effector trajectory represented by $\mathcal {T}_1$, hip trajectory represented by $\mathcal {T}_2$, and maximizing the manipulability represented by $\mathcal {T}_3$. The Pseudoinverse Jacobian method is coupled with particle swarm optimization (PSO) to find the optimal trajectories. The main contribution of this paper is the decomposition of the whole-body task of the humanoid robot into three distinct subtasks to find energy-optimal, dynamically balanced, and obstacle-free trajectories. The concept of virtual surface is used to avoid dragging objects on the table surface. The problem is optimized with Particle Swarm Optimization. Simulations were conducted to pick up and place objects from a table and constrained spaces like a drawer. The results show that the robot can pick and place objects from defined locations on the table.

Target tracking technology is a key research area in the field of mobile robots, with wide applications in logistics, security, autonomous driving, and more. It generally involves two main components: target recognition and target following. However, the limited computational power of the mobile robot’s controller makes achieving high precision and fast target recognition and tracking a challenge. To address the challenges posed by limited computing power, this paper proposes a target-tracking control algorithm based on lightweight neural networks. First, a depthwise separable convolution-based backbone is introduced for feature extraction. Then, an efficient channel attention module is incorporated into the target recognition algorithm to minimize the impact of redundant features and emphasize important channels, thereby reducing model complexity and enhancing network efficiency. Finally, based on the data collected from visual and ultrasonic sensors, a model predictive control strategy is used to achieve target tracking. Validation of the proposed algorithm is conducted using a mobile robot equipped with Raspberry Pi 4B. Experimental results demonstrate that the proposed algorithm achieves rapid target tracking.

Robotic lower limb exoskeletons are wearable devices designed to augment human motor functions and enhance physical capabilities mostly adopted in healthcare and rehabilitation. The field is strongly dominated by rigid exoskeletons driven by electromagnetic actuators constituted by electrical motors, gearboxes, and cylinders. This review focuses on the design and specifications of the actuation systems of lower limb exoskeletons, with the ultimate goal of providing reporting guidelines to allow for full reproducibility. For each paper, we assessed the quality and completeness of technical characteristics with two ad hoc rating scales for motors and reducers; we extracted the main parameters of the actuation unit and a quantitative analysis of the mechanical characteristics of the individual components was carried out considering the exoskeleton application. Overall, we observed a lack of details in reporting on actuation systems equipped on exoskeletons. To overcome this limitation, herein we conclude by proposing a data form and a checklist to provide researchers with a common approach in reporting the mechanical characteristics of the actuation unit of their lower limb exoskeletons. We believe that the convergence of exoskeletons’ literature toward a clearer standardization of design and reporting will boost the development of this technology and its diffusion outside the laboratory.

Global path planning using roadmap (RM) path-planning methods including Voronoi diagram (VD), rapidly exploring random trees (RRT), and probabilistic roadmap (PRM) has gained popularity over the years in robotics. These global path-planning methods are usually combined with other path-planning techniques to achieve collision-free robot control to a specified destination. However, it is unclear which of these methods is the best choice to compute the efficient path in terms of path length, computation time, path safety, and consistency of path computation. This article reviewed and adopted a comparative research methodology to perform a comparative analysis to determine the efficiency of these methods in terms of path optimality, safety, consistency, and computation time. A hundred maps of different complexities with obstacle occupancy rates ranging from 50.95% to 78.42% were used to evaluate the performance of the RM path-planning methods. Each method demonstrated unique strengths and limitations. The study provides critical insights into their relative performance, highlighting application-specific recommendations for selecting the most suitable RM method. These findings contribute to advancing robot path-planning techniques by offering a detailed evaluation of widely adopted methods.

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.

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.

Onboard localization for multi-robot systems stands as a critical area of research with wide-ranging applications. This paper introduces an innovative framework for multi-robot localization, uniquely characterized by its onboard capability, thereby negating the dependency on external infrastructure. Our approach harnesses the inherent capabilities of each robot, enabling them to localize and synchronize their movements independently. The integration of cooperative localization algorithms with formation control mechanisms empowers a group of robots to sustain a predefined formation while following a linear trajectory. The efficacy of our framework is substantiated through comprehensive simulations and real-world experimental validations. We rigorously assess the system’s resilience to localization inaccuracies and external disturbances, demonstrating its adaptability and consistency in maintaining formation under diverse conditions. Furthermore, we explore the scalability of our approach, highlighting its potential to manage varying numbers of robots and its applicability in tasks such as collaborative transportation.

In this paper, a cellular robot for space trusses is structured so that it can perform tasks such as moving the truss and assembling the truss. There may be some spatial operating mechanisms on the space truss that cause obstacles to the robot’s movement, especially other mobile mechanical devices that are working, which are dynamic obstacles, so a suitable path planning for the robot is needed. In path planning, A-star algorithm has the advantages of efficient searching speed and good optimization effect, but it can’t deal with the path planning problem with dynamic obstacles, so this paper improves Lifelong Planning A-star (LPA-star) algorithm so that the improved algorithm satisfies the dynamic path planning task. Then a three-dimensional truss mathematical model is established, a dynamic obstacle environment is set up, the improved LPA-star algorithm is used for path planning, and the unimproved LPA-star algorithm and the improved A-star algorithm are used to compare with it. The simulation results show that in the environment set up in this paper, the optimal path length of the improved LPA-star algorithm is shortened by about 25% and the algorithm search time is shortened by about 55% compared with the improved A-star algorithm; while the unimproved LPA-star algorithm is unable to accomplish the dynamic path planning task. Therefore, the improved LPA-star algorithm can reduce the robot’s moving distance and time consumption.

Walking mechanisms offer advantages over wheels or tracks for locomotion but often require complex designs. This paper presents the kinematic design and analysis of a novel overconstrained spatial a single degree-of-freedom leg mechanism for walking robots. The mechanism is generated by combining spherical four-bar linkages into two interconnecting loops, resulting in an overconstrained design with compact scalability. Kinematic analysis is applied using recurrent unit vector methods. Dimensional synthesis is performed using the Firefly optimization algorithm to achieve a near-straight trajectory during the stance phase for efficient walking. Constraints for mobility, singularity avoidance, and transmission angle are also implemented. The optimized design solution is manufactured using 3D printing and experimentally tested. Results verify the kinematic properties including near-straight-line motion during stance. The velocity profile shows low perpendicular vibrations. Advantages of the mechanism include compact scalability allowing variable stride lengths, smooth motion from overconstraint, and simplicity of a single actuator. The proposed overconstrained topology provides an effective option for the leg design of walking robots and mechanisms.

A more intuitive appreciation of spatial compliant behavior can be obtained through analysis and description of the behavior in terms of its centers, specifically the center of stiffness, the center of compliance, and the center of elasticity. This paper investigates the properties of each of these centers. Necessary and sufficient conditions for the coincidence of these centers are identified. A physical appreciation of those compliant behaviors that have coincident centers is obtained in terms of restrictions on the geometry of topologically simple mechanisms that realize those behaviors. The results can be used in the design of compliant mechanisms for robotic manipulation, especially when the compliance is characterized by the location of its center.

The problem of how to effectively track and intercept small aircraft that break into the no-fly zones is now attracting increasing interest in robotics society. Vision-based control has been proved an effective solution to the target tracking problem for unmanned aerial vehicles (UAVs). Due to the limited field of view (FOV) of onboard vision sensors, existing works assume that the target is always detectable during tracking or limit the flight speed of the UAV in practice. In this paper, inspired by the broad FOV of camera network, we are the first to propose an eye-to-hand (i.e., fixed cameras) visual servoing scheme to track and intercept aerial targets by using UAVs and ground visual sensors. Specifically, utilizing rotation matrices, we first present a visual servoing equation to convert the UAV motion in image planes to the inertial frame. Then, an image-based visual servoing controller is designed directly based on image errors of camera nodes in the sensor network, and system stability is proved by means of Lyapunov analysis. Additionally, to achieve the desired translational velocity command, a low-level attitude controller is developed based on the UAV dynamics. Finally, a series of experiments in both simulated and real flight scenarios show the outstanding efficacy of our method.