Search Results (3,065)

Mobile robots represent one of the most relevant areas of study within robotics due to their potential for designing and developing new nonlinear control structures that can be implemented in simulations and applications in specific environments. In this work, a fuzzy steering controller with a symmetric distribution of fuzzy numbers is proposed and designed for implementation in the kinematic model of a non-holonomic mobile robot. The symmetry in the distribution of triangular fuzzy numbers contributes to a balanced response to disturbances and minimizes systematic errors in direction estimation. Additionally, it improves the system’s adaptability to various reference paths, ensuring accurate tracking and optimized performance in robot navigation. Furthermore, this fuzzy logic-based controller emulates the behavior of a classic PID controller by offering a robust and flexible alternative to traditional methods. A virtual environment was also developed using the UNITY platform to evaluate the performance of the fuzzy controller. The results were evaluated by considering the average tracking error, maximum error, steady-state error, settling time, and total distance traveled, emphasizing the trajectory error. The circular trajectory showed high accuracy with an average error of 0.0089 m, while the cross trajectory presented 0.01814 m, reflecting slight deviations in the turns. The point-to-point trajectory registered a more significant error of 0.9531 m due to abrupt transitions, although with effective corrections in a steady state. The simulation results validate the robustness of the proposed fuzzy controller, providing quantitative insights into its precision and efficiency in a virtual environment, and demonstrating the effectiveness of the proposal. Full article

With the ever-increasing volume of maritime traffic, the risks of ship navigation are becoming more significant, making the use of advanced multi-source perception strategies and AI technologies indispensable for obtaining information about ship navigation status. In this paper, first, the ship tracking system was optimized using the Bi-YOLO network based on the C2f_BiFormer module and the OC-SORT algorithms. Second, to extract the visual trajectory of the target ship without a reference object, an absolute position estimation method based on binocular stereo vision attitude information was proposed. Then, a perception data fusion framework based on ship spatio-temporal trajectory features (ST-TF) was proposed to match GPS-based ship information with corresponding visual target information. Finally, AR technology was integrated to fuse multi-source perceptual information into the real-world navigation view. Experimental results demonstrate that the proposed method achieves a mAP0.5:0.95 of 79.6% under challenging scenarios such as low resolution, noise interference, and low-light conditions. Moreover, in the presence of the nonlinear motion of the own ship, the average relative position error of target ship visual measurements is maintained below 8%, achieving accurate absolute position estimation without reference objects. Compared to existing navigation assistance, the AR-based navigation assistance system, which utilizes ship ST-TF-based perception data fusion mechanism, enhances ship traffic situational awareness and provides reliable decision-making support to further ensure the safety of ship navigation. Full article

In robotic surface UV printing, the irregular shape of the workpiece and frequent curvature changes require the printing robot to maintain the nozzle’s perpendicular orientation to the surface during path planning, which imposes high demands on trajectory accuracy and path smoothness. To address this challenge, this paper proposes a reinforcement-learning-based path planning method. First, an ideal main path is defined based on the nozzle characteristics, and then a robot motion accuracy model is established and transformed into a Markov Decision Process (MDP) to improve path accuracy and smoothness. Next, a framework combining Generative Adversarial Imitation Learning (GAIL) and Soft Actor–Critic (SAC) methods is proposed to solve the MDP problem and accelerate the convergence of SAC training. Experimental results show that the proposed method outperforms traditional path planning methods, as well as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Specifically, the maximum Cartesian space error in path accuracy is reduced from 1.89 mm with PSO and 2.29 mm with GA to 0.63 mm. In terms of joint space smoothness, the reinforcement learning method achieves the smallest standard deviation, especially with a standard deviation of 0.00795 for joint 2, significantly lower than 0.58 with PSO and 0.729 with GA. Moreover, the proposed method also demonstrates superior training speed compared to the baseline SAC algorithm. The experimental results validate the application potential of this method in intelligent manufacturing, particularly in industries such as automotive manufacturing, aerospace, and medical devices, with significant practical value. Full article

Flexible sensors are revolutionizing our lives as a key component of intelligent wearables. Their pliability, stretchability, and diverse designs enable foldable and portable devices while enhancing comfort and convenience. Advances in materials science have provided numerous options for creating flexible sensors. The core of their application in areas like electronic skin, health medical monitoring, motion monitoring, and human–computer interaction is selecting materials that optimize sensor performance in weight, elasticity, comfort, and flexibility. This article focuses on flexible sensors, analyzing their “sensing mechanisms–materials–applications” framework. It explores their development trajectory, material characteristics, and contributions in various domains such as electronic skin, health medical monitoring, and human–computer interaction. The article concludes by summarizing current research achievements and discussing future challenges and opportunities. Flexible sensors are expected to continue expanding into new fields, driving the evolution of smart wearables and contributing to the intelligent development of society. Full article

The rotary double inverted pendulum system is characterized by one stable equilibrium point and three unstable equilibrium points due to its kinematic properties. This paper defines the transition control problem between these equilibrium points to extend the conventional swing-up control problem and proposes an implementation method using a laboratory-developed rotary double inverted pendulum. To minimize energy consumption during the transition process while satisfying the boundary conditions of different equilibrium points, a two-point boundary value optimal control problem is formulated. The feedforward trajectory required for feedforward control is computed offline by solving this problem. The direct collocation method is employed to convert the constrained continuous optimal control problem into a nonlinear optimization problem. Furthermore, a time-varying linear–quadratic (LQ) controller is utilized as a feedback controller to accurately track the generated feedforward trajectory during real-time control, compensating for uncertainties in the feedforward control process. The proposed transition control strategy is experimentally implemented, and its effectiveness and practicality are validated through the successful tracking of 12 transition trajectories. Full article

According to statistics from the United Nations Environment Program (UNEP), the construction industry accounts for approximately 30% to 40% of global energy consumption and greenhouse gas emissions, making it a major source of carbon emissions. As a critical component of urban construction, residential buildings are characterized by their large scale and significant potential for carbon reduction. Building on this context, this study utilizes diversified geospatial data and applies the life-cycle stage framework for residential buildings alongside the emission factor method to calculate total carbon emissions during the material production, construction, and operation phases. It systematically analyzes the distribution characteristics and spatial evolution trends of life-cycle carbon emissions for urban residential buildings. The findings reveal that 63.06% of the cumulative carbon emissions from residential buildings in Xi’an originate from the operation phase, underscoring the importance of optimizing carbon emissions in this phase as a critical priority for future reductions. Additionally, the spatial distribution of residential building carbon emissions exhibits significant clustering, with an increasingly pronounced expansion pattern. Over time, the direction of expansion has shifted from a northeast–southwest orientation to a northwest–southeast trajectory and continues to extend toward peripheral areas. Economic growth, increased urbanization, and the intensive consumption of specific building materials are identified as significant drivers of residential carbon emissions, while population growth and improvements in material utilization efficiency help mitigate emissions to some extent. This study offers valuable insights to support the green development of China’s construction industry and to advance energy-saving and carbon-reduction strategies. Full article

Trajectory prediction is critical for ensuring the safety, reliability, and scalability of Unmanned Aerial Vehicle (UAV) in urban environments. Despite advances in deep learning, existing methods often struggle with dynamic UAV conditions, such as rapid directional changes and limited forecasting horizons, while lacking comprehensive real-time validation and generalization capabilities. This study addresses these challenges by proposing a gated recurrent unit (GRU)-based deep learning framework optimized through Look_Back and Forward_Length labeling to capture complex temporal patterns. The model demonstrated state-of-the-art performance, surpassing existing unmanned aerial vehicles (UAV) and aircraft trajectory prediction approaches, including FlightBERT++, in terms of both accuracy and robustness. It achieved reliable long-range predictions up to 4 s, and its real-time feasibility was validated due to its efficient resource utilization. The model’s generalization capability was confirmed through evaluations on two independent UAV datasets, where it consistently predicted unseen trajectories with high accuracy. These findings highlight the model’s ability to handle rapid maneuvers, extend prediction horizons, and generalize across platforms. This work establishes a robust trajectory prediction framework with practical applications in collision avoidance, mission planning, and anti-drone systems, paving the way for safer and more scalable UAV operations. Full article

Accurately localizing individual trees and identifying species distribution are critical tasks in forestry remote sensing. Visual Simultaneous Localization and Mapping (visual SLAM) algorithms serve as important tools for outdoor spatial positioning and mapping, mitigating signal loss caused by tree canopy obstructions. To address these challenges, a semantic SLAM algorithm called LPD-SLAM (Line-Point-Distance Semantic SLAM) is proposed, which integrates stereo cameras with an inertial measurement unit (IMU), with contributions including dynamic feature removal, an individual tree data structure, and semantic point distance constraints. LPD-SLAM is capable of performing individual tree localization and tree species discrimination tasks in forest environments. In mapping, LPD-SLAM reduces false species detection and filters dynamic objects by leveraging a deep learning model and a novel individual tree data structure. In optimization, LPD-SLAM incorporates point and line feature reprojection error constraints along with semantic point distance constraints, which improve robustness and accuracy by introducing additional geometric constraints. Due to the lack of publicly available forest datasets, we choose to validate the proposed algorithm on eight experimental plots, which are selected to cover different seasons, various tree species, and different data collection paths, ensuring the dataset’s diversity and representativeness. The experimental results indicate that the average root mean square error (RMSE) of the trajectories of LPD-SLAM is reduced by up to 81.2% compared with leading algorithms. Meanwhile, the mean absolute error (MAE) of LPD-SLAM in tree localization is 0.24 m, which verifies its excellent performance in forest environments. Full article

This paper proposes a novel convex optimization framework for two-stage launch vehicle (TSLV) ascent trajectory planning from liftoff to orbit insertion, featuring two groundbreaking advancements over existing convex optimization methodologies: (1) an innovative second-order Birkhoff pseudospectral (BPS) method is developed that reduces the number of dynamic equality constraints by 50% compared to traditional PS methods, meanwhile, an augmented variable transcription technique is used to formulate inequality constraints; therefore, the sparsity ratio of the inequality matrix is reduced to less than 1%; (2) a new iterative solution strategy initialized by a few guesses is proposed to efficiently obtain the optimal solution. The framework is rigorously supported by theoretical convergence guarantees and validated through comprehensive numerical experiments. The numerical results demonstrate around a 50% reduction in computational time compared to the differential PS baseline method. With the significantly reduced computational cost, the proposed method exhibits strong potential for real-time onboard implementation in the future. Full article

The accurate reconstruction of vehicle paths is essential for effective highway toll management. To address the challenge of multiple possible paths due to missing trajectory data, this study proposes a novel two-stage model for vehicle path reconstruction. In the first stage, a Gaussian Mixture Model (GMM) is integrated into a path choice model to estimate the mean and standard deviation of travel times for each road segment, utilizing an improved Expectation Maximization (EM) algorithm. In the second stage, based on the estimated time parameters, path choice prior probabilities and observed data are combined using maximum likelihood estimation to infer the most probable paths among candidate routes. The results indicate that the improved EM algorithm achieved convergence in 17 iterations compared to 41 iterations for the traditional EM algorithm. The two-stage model outperforms the Shortest Path and Bidirectional Long Short-Term Memory models in path reconstruction, particularly with a high number of missing trajectory points. Additionally, when the number of candidate paths $K=4$, the path reconstruction performance is optimal. These results demonstrate the effectiveness of the proposed method in handling sparse and incomplete trajectory data, offering robust and accurate vehicle path estimations that enhance traffic management and toll calculation precision. Full article

Permanent magnet synchronous motors (PMSMs) are widely used in industrial automation and electric vehicles due to their high efficiency and excellent dynamic performance. However, controlling PMSMs presents challenges such as parameter variations and system nonlinearities. This paper proposes a twin delayed deep deterministic policy gradient (TD3)-based energy-saving optimization control method for PMSM drive systems. The TD3 algorithm uses double networks, target policy smoothing regularization, and delayed actor network updates to improve training stability and accuracy. Simulation experiments under two operating conditions show that the TD3 algorithm outperforms traditional proportional–integral (PI) controllers and linear active disturbance rejection control (LADRC) controllers in terms of reference trajectory tracking, q-axis current regulation, and speed tracking error minimization. The results demonstrate the TD3 algorithm’s effectiveness in enhancing motor efficiency and system robustness, offering a novel approach to PMSM drive system control through deep reinforcement learning. Full article

A unified control system that possesses the abilities to arrange collision-free trajectories, precise trajectory tracking, and control allocation for unmanned surface vessels is investigated in this paper by integrating methods, including an image-based trajectory generator, a nonlinear robust controller, and a control allocation maker. For the purpose of rapidly generating an optimal collision-free trajectory, a rapid image-searching method, named double-sided Finite Angle A* (FAA*), is developed to cooperate with a continuous trajectory generator. This proposed control system provides an effective means for letting controlled unmanned surface vessels be able to execute given tasks by following collision-free trajectories under the influences of modeling uncertainties and ocean environmental disturbances. To eliminate the effects of modeling uncertainties and ocean environmental disturbances, a robust compensator is developed to co-work with a nonlinear control law. Furthermore, the required robust control commands are perfectly performed by a pair of rotatable actuators with an analytical control allocation design. Finally, two demonstrations are examined to validate the control performance of this proposed unified control system. Full article

With the rapid advancement of edge-computing technology, more computing tasks are moving from traditional cloud platforms to edge nodes. This shift imposes challenges on efficiently handling the substantial data generated at the edge, especially in extreme scenarios, where conventional data collection methods face limitations. UAVs have emerged as a promising solution for overcoming these challenges by facilitating data collection and transmission in various environments. However, existing UAV trajectory optimization algorithms often overlook the critical factor of the battery capacity, leading to potential mission failures or safety risks. In this paper, we propose a trajectory planning approach Hyperion that incorporates charging considerations and employs a greedy strategy for decision-making to optimize the trajectory length and energy consumption. By ensuring the UAV’s ability to return to the charging station after data collection, our method enhances task reliability and UAV adaptability in complex environments. Full article

Recently, significant research efforts have been directed toward leveraging Artificial Intelligence for sensor data processing and system control. In particular, it is essential to determine the optimal path and trajectory by calculating sensor data for effective control systems. For instance, model-predictive control based on Proportional-Integral-Derivative models is intuitive, efficient, and provides outstanding control performance. However, challenges in tracking persist, which requires active research and development to integrate and optimize the control system in terms of Machine Learning. Specifically, Reinforcement Learning, a branch of Machine Learning, has been used in several research fields to solve optimal control problems. In this paper, we propose an Extended Maximum Actor–Critic using a Reinforcement Learning-based method to combine the advantages of both value and policy to enhance the learning stability of actor–critic for optimization of system control. The proposed method integrates the actor and the maximized actor in the learning process to evaluate and identify actions with the highest value, facilitating effective learning exploration. Additionally, to enhance the efficiency and robustness of the agent learning process, we propose Prioritized Hindsight Experience Replay, combining the advantages of Prioritized Experience Replay and Hindsight Experience Replay. To verify this, we performed evaluations and experiments to examine the improved training stability in the MuJoCo environment, which is a simulator based on Reinforcement Learning. The proposed Prioritized Hindsight Experience Replay method significantly enhances the experience to be compared with the standard replay buffer and PER in experimental simulators, such as the simple HalfCheetah-v4 and the complex Ant-v4. Thus, Prioritized Hindsight Experience Replay achieves a higher success rate than PER in FetchReach-v2, demonstrating the significant effectiveness of our proposed method in more complex reward environments. Full article

With advancements in mobile robot technology, wheel-legged robots have emerged as promising next-generation mobile solutions, reducing design costs and enhancing adaptability in unstructured environments. As underactuated systems, their balance control has become a prominent research focus. Despite there being numerous control approaches, challenges remain. Balance control methods for wheel-legged robots are influenced by hardware characteristics, such as motor friction, which can induce oscillations and hinder dynamic convergence. This paper presents a friction feedforward Linear Quadratic Regulator (LQR) balance control method. Specifically, a basic LQR controller is developed based on the dynamics model of the wheel-legged robot, and a Stribeck friction model is established to characterize motor friction. A constant-speed excitation trajectory is designed to gather data for friction identification, and the Particle Swarm Optimization (PSO) algorithm is applied to determine the optimal friction parameters. The identified friction model is subsequently incorporated as feedforward compensation for the LQR controller’s torque output, resulting in the proposed friction feedforward LQR balance control algorithm. The minimum standard deviation for friction identification is approximately 0.30, and the computed friction model values closely match the actual values, indicating effective and accurate identification results. Balance experiments demonstrate that under diverse conditions—such as flat ground, single-sided bridges, and disturbance scenarios—the convergence performance of the friction feedforward LQR algorithm markedly surpasses that of the baseline LQR, effectively reducing oscillations, accelerating convergence, and improving the robot’s stability and robustness. Full article