Search Results (437)

Sensor fusion in intelligent suspension systems constitutes a fundamental technology for optimizing vehicle dynamic stability, ride comfort, and occupant safety. By integrating data from multiple sensor modalities, this study proposes a hierarchical multi-sensor fusion framework for active suspension control, aiming to enhance control precision. Initially, a binocular vision system is employed for target detection, enabling the identification of lane curvature initiation points and speed bumps, with real-time distance measurements. Subsequently, the integration of Global Positioning System (GPS) and inertial measurement unit (IMU) data facilitates the extraction of road elevation profiles ahead of the vehicle. A BP-PID control strategy is implemented to formulate mode-switching rules for the active suspension under three distinct road conditions: flat road, curved road, and obstacle road. Additionally, an ant colony optimization algorithm is utilized to fine-tune four suspension parameters. Utilizing the hardware-in-the-loop (HIL) simulation platform, the observed reductions in vertical, pitch, and roll accelerations were 5.37%, 9.63%, and 11.58%, respectively, thereby substantiating the efficacy and robustness of this approach. Full article

This paper presents a behavior tree-based control architecture for end-to-end mission planning of an autonomous underwater vehicle (AUV) collaborating with a moving mothership in dynamic marine environments. The framework is organized into three phases—prepare and launch, execute the mission, and retrieval and docking—each encapsulated in an independent sub-tree to enable modular error handling and seamless phase transitions. The AUV and mothership operate entirely underwater, with real-time docking to a moving platform. An extended Kalman filter (EKF) fuses data from inertial, pressure, and acoustic sensors for accurate navigation and state estimation. At the same time, obstacle avoidance leverages forward-looking sonar (FLS)-based potential field methods to react to unpredictable underwater hazards. The system is implemented on the robot operating system (ROS) and validated in the Stonefish physics engine simulator. Simulation results demonstrate reliable mission execution, successful dynamic docking under communication delays and sensor noise, and robust retrieval from injected faults, confirming the validity and stability of the proposed architecture. Full article

This study examined the integraftion of airborne Light Detection and Ranging (LiDAR), Simultaneous Localization and Mapping (SLAM)-based handheld LiDAR, and iPhone LiDAR to inspect forest road networks following forest operations. The goal is to overcome the challenges posed by dense canopy cover and ensure accurate and efficient data collection and mapping. Airborne data were collected using the DJI Matrice 300 RTK UAV equipped with a Zenmuse L2 LiDAR sensor, which achieved a high point density of 285 points/m² at an altitude of 80 m. Ground-level data were collected using the BLK2GO handheld laser scanner (HPLS) with SLAM methods (LiDAR SLAM, Visual SLAM, Inertial Measurement Unit) and the iPhone 13 Pro Max LiDAR. Data processing included generating DEMs, DSMs, and True Digital Orthophotos (TDOMs) via DJI Terra, LiDAR360 V8, and Cyclone REGISTER 360 PLUS, with additional processing and merging using CloudCompare V2 and ArcGIS Pro 3.4.0. The pairwise comparison analysis between ALS data and each alternative method revealed notable differences in elevation, highlighting discrepancies between methods. ALS + iPhone demonstrated the smallest deviation from ALS (MAE = 0.011, RMSE = 0.011, RE = 0.003%) and HPLS the larger deviation from ALS (MAE = 0.507, RMSE = 0.542, RE = 0.123%). The findings highlight the potential of fusing point clouds from diverse platforms to enhance forest road mapping accuracy. However, the selection of technology should consider trade-offs among accuracy, cost, and operational constraints. Mobile LiDAR solutions, particularly the iPhone, offer promising low-cost alternatives for certain applications. Future research should explore real-time fusion workflows and strategies to improve the cost-effectiveness and scalability of multisensor approaches for forest road monitoring. Full article

This study explores virtual sensing techniques for the Eolink floating offshore wind turbine (FOWT), which features a pyramidal platform and a single-point mooring system that enables weathervaning to maximize power production and reduce structural loads. To address the challenges and costs associated with monitoring submerged components, virtual sensors are investigated as an alternative to physical instrumentation. The main objective is to design a virtual sensor of mooring hawser loads using a reduced set of input features from GPS, anemometer, and inertial measurement unit (IMU) data. A virtual sensor is also proposed to estimate the bending moment at the joint of the pyramid masts. The FOWT is modeled in OrcaFlex, and a range of load cases is simulated for training and testing. Under defined sensor sampling conditions, both supervised and physics-informed machine learning algorithms are evaluated. The models are tested under aligned and misaligned environmental conditions, as well as across operating regimes below- and above-rated conditions. Results show that mooring tensions can be estimated with high accuracy, while bending moment predictions also perform well, though with lower precision. These findings support the use of virtual sensing to reduce instrumentation requirements in critical areas of the floating wind platform. Full article

This work systematically addresses the dual challenges of non-inertial dynamic coupling and kinematic constraint redundancy encountered in dynamic modeling of serial–parallel–serial hybrid robotic mechanisms, and proposes an improved Newton–Euler modeling method with constraint compensation. Taking the Skiing Simulation Platform with 6-DOF as the research mechanism, the inverse kinematic model of the closed-chain mechanism is established through $G_F$ set theory, with explicit analytical expressions derived for the motion parameters of limb mass centers. Introducing a principal inertial coordinate system into the dynamics equations, a recursive algorithm incorporating force/moment coupling terms is developed. Numerical simulations reveal a 9.25% periodic deviation in joint moments using conventional methods. Through analysis of the mechanism’s intrinsic properties, it is identified that the lack of angular momentum conservation constraints on the end-effector in non-inertial frames leads to system controllability degradation. Accordingly, a constraint compensation strategy is proposed: establishing linearly independent differential algebraic equations supplemented with momentum/angular momentum balance equations for the end platform. Co-Simulation results demonstrate that the optimized model reduces the maximum relative error of actuator joint moments to 0.98%, and maintains numerical stability across the entire configuration space. The constraint compensation framework provides a universal solution for dynamics modeling of complex closed-chain mechanisms, validated through applications in flight simulators and automotive driving simulators. Full article

This study presents the development of a software solution for processing, analyzing, and visualizing sensor data collected by an educational mobile robot. The focus is on statistical analysis and identifying correlations between diverse datasets. The research utilized the PlatypOUs mobile robot platform, equipped with odometry and inertial measurement units (IMUs), to gather comprehensive motion data. To enhance the reliability and interpretability of the data, advanced data processing techniques—such as moving averages, correlation analysis, and exponential smoothing—were employed. Python-based tools, including Matplotlib and Visual Studio Code, were used for data visualization and analysis. The analysis provided key insights into the robot’s motion dynamics; specifically, its stability during linear movements and variability during turns. By applying moving average filtering and exponential smoothing, noise in the sensor data was significantly reduced, enabling clearer identification of motion patterns. Correlation analysis revealed meaningful relationships between velocity and acceleration during various motion states. These findings underscore the value of advanced data processing techniques in improving the performance and reliability of educational mobile robots. The insights gained in this pilot project contribute to the optimization of navigation algorithms and motion control systems, enhancing the robot’s future potential in STEM education applications. Full article

This paper presents FWStab, a specialized video stabilization dataset tailored for flapping-wing platforms. The dataset encompasses five typical flight scenarios, featuring 48 video clips with intense dynamic jitter. The corresponding Inertial Measurement Unit (IMU) sensor data are synchronously collected, which jointly provide reliable support for multimodal modeling. Based on this, to address the issue of poor image acquisition quality due to severe vibrations in aerial vehicles, this paper proposes a multi-modal signal fusion video stabilization framework. This framework effectively integrates image features and inertial sensor features to predict smooth and stable camera poses. During the video stabilization process, the true camera motion originally estimated based on sensors is warped to the smooth trajectory predicted by the network, thereby optimizing the inter-frame stability. This approach maintains the global rigidity of scene motion, avoids visual artifacts caused by traditional dense optical flow-based spatiotemporal warping, and rectifies rolling shutter-induced distortions. Furthermore, the network is trained in an unsupervised manner by leveraging a joint loss function that integrates camera pose smoothness and optical flow residuals. When coupled with a multi-stage training strategy, this framework demonstrates remarkable stabilization adaptability across a wide range of scenarios. The entire framework employs Long Short-Term Memory (LSTM) to model the temporal characteristics of camera trajectories, enabling high-precision prediction of smooth trajectories. Full article

Background/Objectives: This study evaluated the reliability and validity of three methods to measure jump height during countermovement jumps performed with (CMJ_AS) and without (CMJ_NAS) arm swing: (1) an impulse–momentum method with force platforms (FP_imp), (2) a flight time method with force platforms (FP_time), and (3) an inertial measurement unit (PUSH Band 2.0; PUSH2). Methods: Eighteen physically active men performed CMJ_AS and CMJ_NAS on force platforms while wearing PUSH2 over two days. Besides jump height, we computed intraclass correlation coefficients (ICC) and the absolute and relative increases in jump height due to arm swing, compared to CMJ_NAS. Results: The reliability of intra-session, inter-session, and concurrent measures were good to excellent (intra-session ICC_2,1 = 0.957–0.979, inter-session ICC_2,1 = 0.806–0.990, concurrent ICC_3,1 = 0.940–0.973) for CMJ_AS and CMJ_NAS heights, in all three methods. The three methods showed high to very high reliability for both the absolute and relative indices of arm swing contribution (ICC_2,1 = 0.649–0.812). FP_time significantly overestimated CMJ_NAS height relative to FP_imp (p < 0.01). The absolute index of arm swing contribution was similar in FP_imp and FP_time (p = 0.38) but higher in PUSH2 (p < 0.01), indicating that arm swing amplified overestimation. Conclusions: All three methods demonstrated high reliability for jump height measurements, but FP_time and PUSH2 misestimated jump height depending on jump modalities. Caution is advised when assessing the absolute and relative contribution of arm swing, because errors in CMJ_NAS and CMJ_AS height measurements can affect these values and their interpretation. Full article

Aiming at the problem that the whole row of reciprocating seedling picking mechanism is prone to inertial impacts during operation due to its excessive mass, causing seedling damage and positioning errors, this study builds a motion control system with a PLC controller as the core and proposes a composite motion control strategy based on planned S-curve acceleration and deceleration and fuzzy PID to achieve rapid response, precise positioning, and smooth operation of the seedling picking mechanism. By establishing the objective function and constraint conditions and taking into account the dynamic change of the seedling picking displacement, the S-curve acceleration and deceleration control algorithm is planned in six and seven stages to meet the requirements of a smooth transition of the speed and continuous change of the acceleration curve of the seedling picking mechanism during movement. A fuzzy PID positioning control system is designed, the control system transfer function is constructed, and fuzzy rules are formulated to dynamically compensate for the error and its rate of change to meet the requirements of fast response and no overshoot oscillation of the positioning control system. The speed and acceleration of the seedling picking mechanism under the six-segment and seven-segment S-curve acceleration and deceleration motion control conditions were simulated using MATLAB2024a simulation software and compared with the trapezoidal acceleration and deceleration motion control. The planned S-curve acceleration and deceleration control algorithm has a more stable control effect on the seedling picking mechanism when it operates under the conditions of the dynamic change of the displacement, and it meets the design requirements of seedling picking efficiency. The positioning control system was modeled and simulated using the Simulink simulation platform. When KP = 15, KI = 3, and KD = 1, the whole-row seedling picking control system ran stably, responded quickly, and had no overshoot. Compared with the PID control system with fixed parameters, the fuzzy PID control system reduced the time consumption in the rising stage by 24.5% and shortened the overall stabilization process by 17.6%. The zero overshoot characteristic was ensured, and the response speed was faster. When a disturbance signal is added, the overshoot of the fuzzy PID control system is reduced by 2.4%, and the response speed is increased by 6.8% compared with the fixed-parameter PID control system. The dynamic response rate and anti-disturbance performance are better than those of the fixed-parameter PID control system. A bench comparison test was carried out. The results showed that the S-curve acceleration and deceleration motion control algorithm reduced the average mass loss rate of seedlings by 46.19% compared with the trapezoidal acceleration and deceleration motion control algorithm, and the seedling picking efficiency met the design requirements. Fuzzy PID positioning control was used, and the maximum displacement error of the end effector during seedling picking was −1.4 mm, and the average relative error rate was 0.22%, which met the positioning accuracy requirements of the end effector in the X-axis direction and verified the stability and accuracy of the designed control system. The designed control system was tested in the field, and the average comprehensive success rate of seedling picking and throwing reached 96.2%, which verified the feasibility and practicality of the control system. Full article

Background: The ankle joint plays a key role in stabilizing the lower limb during interaction with ground reaction forces. Instability can result in pain, weakness, and impaired movement. Although assessing ankle stability is important, few studies examine existing in vivo methodologies for dynamic load assessment, limiting effective injury management. Objective: To identify in vivo techniques using objective measurement tools for assessing ankle stability during dynamic exercise. Methods: A scoping review was performed based on PRISMA-ScR criteria. Five databases—PubMed, PEDro, Embase, SPORTDiscus, and CDSR—were searched from inception to September 2024. Results: Out of 1678 records, 32 studies met the inclusion criteria. A total of 1142 subjects were included: 293 females (25.6%), 819 males (71.7%), and 30 unspecified (2.62%). Six categories of dynamic exercise were identified: analytical, functional, balance, stair climbing, running, and walking. The techniques used included 3D motion capture, force and pressure platforms, dynamometry, electromyography, accelerometers, pressure and speed sensors, instrumented treadmills, and inertial measurement units. Conclusions: The 3D motion capture systems (240 Hz) and the force platforms (1000 Hz) were most frequently used in functional tasks and walking. Combining these with multisegmented foot models appears optimal, though tool selection depends on study goals. This review enhances our understanding of ankle stability assessment. Full article

Small object detection in traffic scenes presents unique challenges for mobile robots operating under constrained computational resources and highly dynamic environments. Unlike general object detection, small targets often suffer from low resolution, weak semantic cues, and frequent occlusion, especially in complex outdoor scenarios. This study systematically analyses the challenges, technical advances, and deployment strategies for small object detection tailored to mobile robotic platforms. We categorise existing approaches into three main strategies: feature enhancement (e.g., multi-scale fusion, attention mechanisms), network architecture optimisation (e.g., lightweight backbones, anchor-free heads), and data-driven techniques (e.g., augmentation, simulation, transfer learning). Furthermore, we examine deployment techniques on embedded devices such as Jetson Nano and Raspberry Pi, and we highlight multi-modal sensor fusion using Light Detection and Ranging (LiDAR), cameras, and Inertial Measurement Units (IMUs) for enhanced environmental perception. A comparative study of public datasets and evaluation metrics is provided to identify current limitations in real-world benchmarking. Finally, we discuss future directions, including robust detection under extreme conditions and human-in-the-loop incremental learning frameworks. This research aims to offer a comprehensive technical reference for researchers and practitioners developing small object detection systems for real-world robotic applications. Full article

Accurate and robust pose estimation is critical for simultaneous localization and mapping (SLAM), and multi-sensor fusion has demonstrated efficacy with significant potential for robotic applications. This study presents VOX-LIO, an effective LiDAR-inertial odometry system. To improve both robustness and accuracy, we propose an adaptive hash voxel-based point cloud map management method that incorporates surfel features and planarity. This method enhances the efficiency of point-to-surfel association by leveraging long-term observed surfel. It facilitates the incremental refinement of surfel features within classified surfel voxels, thereby enabling precise and efficient map updates. Furthermore, we develop a weighted fusion approach that integrates LiDAR and IMU data measurements on the manifold, effectively compensating for motion distortion, particularly under high-speed LiDAR motion. We validate our system through experiments conducted on both public datasets and our mobile robot platforms. The results demonstrate that VOX-LIO outperforms the existing methods, effectively handling challenging environments while minimizing computational cost. Full article

A machine learning framework is developed to interpret vehicle subsystem status from sensor data, providing actionable insights for adaptive control systems. Using the vehicle’s suspension as a case study, inertial data are collected from driving maneuvers, including braking and cornering, to seed a prototype XGBoost classifier. The classifier then pseudo-labels a larger exemplar dataset acquired from street and racetrack sessions, which is used to train an inference model capable of robust generalization across both regular and performance driving. An overlapping sliding-window grading approach with reverse exponential weighting smooths transient fluctuations while preserving responsiveness. The resulting real-time semantic mode predictions accurately describe the vehicle’s current dynamics and can inform a model predictive control system that can adjust suspension parameters and update internal constraints for improved performance, ride comfort, and component longevity. The methodology extends to other components, such as braking systems, offering a scalable path toward fully self-optimizing vehicle control in both conventional and autonomous platforms. Full article

Background/Objectives: This study explores the integration of wearable sensors and artificial intelligence (AI) for Human Activity Recognition (HAR) in the diagnosis and rehabilitation of Parkinson’s disease (PD). The objective was to develop a proof-of-concept model based on internal reproducibility, without external generalization, that is capable of distinguishing pathological movements from healthy ones while ensuring clinical relevance and patient safety. Methods: Nine subjects, including eight patients with Parkinson’s disease and one healthy control, were included. Motion data were collected using the Motigravity platform, which integrates inertial sensors in a controlled environment. The signals were automatically segmented into fixed-length windows, with poor-quality segments excluded through preprocessing. A hybrid CNN-LSTM (Convolutional Neural Networks—Long Short-Term Memory) model was trained to classify motion patterns, leveraging convolutional layers for spatial feature extraction and LSTM layers for temporal dependencies. The Motigravity system provided a controlled hypogravity environment for data collection and rehabilitation exercises. Results: The proposed CNN-LSTM model achieved a validation accuracy of 100%, demonstrating classification potential. The Motigravity system contributed to improved data reliability and ensured patient safety. Despite increasing class imbalance in extended experiments, the model consistently maintained perfect accuracy, suggesting strong generalizability after external validation to overcome the limitations. Conclusions: Integrating AI and wearable sensors has significant potential to improve the HAR-based classification of movement impairments and guide rehabilitation strategies in PD. While challenges such as dataset size remain, expanding real-world validation and enhancing automated segmentation could further improve clinical impact. Future research should explore larger cohorts, extend the model to other neurodegenerative diseases, and evaluate its integration into clinical rehabilitation workflows. Full article

In addition to axial motor complications such as abnormal posture, instability, falls, and gait variability, neurodegenerative diseases like Parkinsonian syndromes include executive dysfunction, Parkinson’s disease dementia, and neuropsychiatric symptoms. These motor disorders significantly affect mobility, quality of life, and well-being. Recently, physical activity of various intensities monitored both remotely and face-to-face via digital health technologies, mobile platforms, or sensory cues has gained relevance in managing idiopathic and atypical Parkinson’s disease (PD and APD). Remote monitoring solutions, including home-based digital health assessments using semi-structured activities, offer unique advantages. Real-world gait parameters like walking speed can now be continuously assessed with body-worn sensors. Developing effective strategies to slow pathological aging and mitigate neurodegenerative progression is essential. This study presents outcomes of using digital health technologies (DHTs) for remote assessment of motor function, physical activity, and daily living tasks, aiming to reduce disease progression in PD and APD. In addition to wearable inertial sensors, clinical rating scales and digital biomarkers enhance the ability to characterize and monitor motor symptoms. By reviewing recent literature, we identified emerging trends in quantifying and intervening in neurodegeneration using tools that evaluate both remote and face-to-face physical activity. Our findings confirm that DHTs offer accurate detection of motor fluctuations and support clinical evaluations. In conclusion, DHTs represent a scalable, effective strategy for improving the clinical management of PD and APD. Their integration into healthcare systems may enhance patient outcomes, support early intervention, and help delay the progression of both motor and cognitive symptoms in aging individuals. Full article