In motion planning of biped robots, the place where the swing foot lands on the ground is crucial. Stability, energy consumption, smoothness of movement as well as naturalness of motion can be depending on the selecte...
详细信息
In motion planning of biped robots, the place where the swing foot lands on the ground is crucial. Stability, energy consumption, smoothness of movement as well as naturalness of motion can be depending on the selected foot placement. In this paper, a novel method based on the A* a*algorithm and kinematic manipulability for foot placement planning is presented. In this method, by calculating the magnitude and direction of the maximum manipulability for the candidate foot placements, one is selected that leads to the most dexterous and agile walking while maintaining stability. The advantage of this approach is avoiding singularities and being ready to create a higher potential for foot velocities. Therefore, the possibility of performing maneuvers to maintain walking stability would be enhanced. The mentioned a*algorithm has been successfully implemented on a simulated three-dimensional biped robot.
Aiming to address the timing skew mismatch in the time-interleaved analog-to-digital converter (TIADC) system, this paper presents a timing skew mismatch calibration method based on a back propagation (BP) neural netw...
详细信息
Aiming to address the timing skew mismatch in the time-interleaved analog-to-digital converter (TIADC) system, this paper presents a timing skew mismatch calibration method based on a back propagation (BP) neural network optimized by an adaptive genetic a*algorithm (AGA). In this paper, a trained BP neural network is used to detect the timing skew mismatch in the TIADC system, and the variable delay line is used to calibrate it. In this paper, AGA is used to optimize the BP neural network, accelerating its training speed and improving the detection accuracy of timing skew mismatch in the system. The proposed approach boasts superior detection speed and accuracy compared to other methods. In this paper, an 18-bit 1GS/S 4-channel TIADC system is simulated and the timing skew mismatch in the system is corrected. Simulation results show that the proposed calibration method has fast detection speed, high detection accuracy, and calibration accuracy. After completing the timing skew mismatch correction, the performance of the TIADC system is dramatically improved. The effective number of bits (ENOB) of the system increases by 9.5 bits, and the spurious-free dynamic range (SFDR) increases by 59.9 dB. This paper presents a timing skew mismatch calibration method based on a back propagation (BP) neural network optimized by an adaptive genetic a*algorithm (AGA). The optimized BP neural network is trained to detect the timing skew mismatch in the TIADC system. A variable delay line is used to correct timing skew mismatch within the TIADC system. The effective number of bits of the system increases by 9.5 bits, and the spurious-free dynamic range increases by 59.9 dB. image
Flying car is a new type of vehicle with high obstacle avoidance ability for urban air traffic and future smart travel. In order to plan feasible paths for flying cars in urban environments, a three dimensional path p...
详细信息
Flying car is a new type of vehicle with high obstacle avoidance ability for urban air traffic and future smart travel. In order to plan feasible paths for flying cars in urban environments, a three dimensional path planning strategy for flying cars based on the fusion of improved A* a*algorithm and Bezier curves is proposed. Firstly, the search neighborhood of the A* a*algorithm is improved, and the node expansion is carried out by using the ground mode 9 neighborhood and the low-altitude flight mode 10 neighborhood to quickly obtain feasible path options. Secondly, the energy consumption, time and mode switching loss cost of different motion processes are considered in the heuristic function to achieve unified planning of motion paths and motion modes. Finally, the path is smoothed using piecewise Bezier curves according to the planned path. The results show that in complex maps, compared with traditional vehicles that only consider energy consumption, this strategy effectively reduces the path length by 94.5 m and reduces the weighted cost by 33.1%. Compared with the strategy that comprehensively weighs energy consumption and time, the path length is reduced by 4.31 m and the weighted cost is reduced by 13.6%.
In this paper, an adaptive critic-based approximate optimal control scheme is constructed for the attitude coordinated tracking problem with prescribed performance requirements and input saturation constraint. Since t...
详细信息
In this paper, an adaptive critic-based approximate optimal control scheme is constructed for the attitude coordinated tracking problem with prescribed performance requirements and input saturation constraint. Since the virtual leader's information is not available for some followers, a predetermined-time distributed observer is deployed for each follower to reconstruct the leader's information. Subsequently, an error transformation procedure is imported to reformulate the prescribed-time attitude coordination issue with prescribed performance constraint as the stabilization one of an unconstraint error system. To confront the input saturation constraint, a nonquadratic function is included in the cost function and in this case the described issue is formulated as a series of nonlinear optimal control problems. The critic architecture is built to approximately solve the corresponding Hamilton-Jacobi-Bellman (HJB) equation, i.e., only critic neural network (NN) is utilized to reconstruct the value function and control policy for each follower. The effectiveness and advantage is validated through numerical examples.
Load balancing is essential in cloud computing (CC) to manage the increasing load on servers efficiently. This article proposes a load balancing strategy utilizing constraint measures to distribute the load evenly amo...
详细信息
Load balancing is essential in cloud computing (CC) to manage the increasing load on servers efficiently. This article proposes a load balancing strategy utilizing constraint measures to distribute the load evenly amongst the servers while minimizing power consumption. Firstly, the capacity and load of every Virtual Machine (VM) is evaluated, and tasks are assigned using the African Vultures a*algorithm (AVA) when the load exceeds a predefined threshold. This approach aim is to minimize energy consumption, makespan, and data center usage. Additionally, a load balancing method computes critical features for each VM and assesses their load, followed by calculating selection factors for tasks. Tasks with superior selection factors are assigned to VMs. The proposed Efficient Load Balancing in Cloud Computing under African Vultures a*algorithm (ELB-CC-AVA) demonstrates better performance in cloud environments, achieving lower makespan by 32.82%, 30.47%, and 25.32%, along with higher resource utilization rates of 38.22%, 40.21%, and 25.46% compared to the existing methods.
Timely prediction of Ship Traffic Flow (STF) is essential for managing maritime traffic and preventing congestion. However, existing deep neural network-based STF models often face challenges with hyperparameter selec...
详细信息
Timely prediction of Ship Traffic Flow (STF) is essential for managing maritime traffic and preventing congestion. However, existing deep neural network-based STF models often face challenges with hyperparameter selection and limited accuracy improvements. This study introduces a Temporal Convolutional Network (TCN) model optimized by an Adaptive Genetic a*algorithm (AGA) to address these issues. The methodology begins with comprehensive data preprocessing, using gate-line-based rules to analyze ship traffic entering and leaving ports, leveraging Automatic Identification System (AIS) data. The AGA-TCN model then employs causally dilated convolutions to capture long-term dependencies and extract frequency domain features, with the AGA dynamically optimizing TCN hyperparameters for specific prediction tasks, resulting in an end-to-end STF prediction framework. AIS data from San Francisco waters, covering the period from June 1, 2022, to December 14, 2022, was used to evaluate the model. The performance of the AGA-TCN model was compared against Particle Swarm Optimization (PSO)-TCN, standard TCN, Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models. These models were chosen for comparison due to their widespread use in time-series prediction tasks, representing a variety of approaches in deep learning and optimization. The experiments demonstrate that the AGA-TCN model outperformed all these models, with improvements in RMSE, MSE, and MAPE of 54.37%, 79.18%, and 27.43%, respectively, over the standard TCN. These results underscore the robustness and high accuracy of the AGA-TCN model in STF prediction, establishing it as a superior approach for this application.
The peak strength is a significant parameter in rock engineering, the traditional empirical strength criteria for rocks show good agreement with test results under specific conditions. However, it is not completely ac...
详细信息
The peak strength is a significant parameter in rock engineering, the traditional empirical strength criteria for rocks show good agreement with test results under specific conditions. However, it is not completely accurate for a wide range of loading stress domains and uncorrelated rock types. In this research, porosity, uniaxial compressive strength (UCS) and confining pressure are selected as input variables, and the artificial bee colony (ABC) a*algorithm is used to optimize the support vector machine (SVM) model. Finally, we validate and comparatively analyze the applicability of the models based on the testing set and the comprehensive evaluation indexes (namely correlation coefficient (R2), root mean square error (RMSE) and mean absolute percentage error (MAPE)). Meanwhile, the cosine amplitude method is applied to analyze the correlation between the peak strength and the input variables. The results indicate that both SVM model and ABC-SVM model are suitable for the prediction of peak strength under triaxial compression. Additionally, the ABC-SVM model obviously has better prediction performance by comparison.
Path-planning is the key for marine rescue using unmanned surface vessel. Planning an efficient and safe path can significantly improve the efficiency of marine rescue, and existing path-planning a*algorithms are prone ...
详细信息
Path-planning is the key for marine rescue using unmanned surface vessel. Planning an efficient and safe path can significantly improve the efficiency of marine rescue, and existing path-planning a*algorithms are prone to collision and grounding with islands and shallows. To address this issue, this paper proposes a method for improving A* a*algorithm. First, global key nodes were extracted based on maritime map information using image processing techniques. Then, the global key nodes that can be directly reached in a straight line and meet safety threshold were screened as child nodes of current node to participate in the search. Finally, the path was planned by introducing the path danger value into the cost function of A* a*algorithm to consider the path cost and safety. Simulation results showed that the path planned by improved A* a*algorithm is safer and smoother than other paths, and the search time and path cost are optimized.
The direct position determination (DPD) a*algorithm, which combines the parameter estimation and position calculation procedures together, has attracted significant attention due to its good performance in low signal-to...
详细信息
The direct position determination (DPD) a*algorithm, which combines the parameter estimation and position calculation procedures together, has attracted significant attention due to its good performance in low signal-to-noise ratio (SNR) situations. However, the high computing consumption and being only suitable for noncoherent signals make its application limited in real situations. To address these problems, we first propose to use the Kronecker theory to decompose the original signal into signal and noise subspaces, based on which a cost function is constructed, and thus, the localization is transformed into a nonconvex optimization problem. Compared with traditional decomposition a*algorithms, this processing can improve the freedom degree of linear arrays and address the challenge to identify the direct transmitting path in the case of coherent signals. Then, to solve the nonconvex optimization problem, an adaptive reverse particle swarm optimization (ARPSO) a*algorithm is proposed, in which the adaptive elite mutation (AEM) strategy is introduced into the traditional particle swarm optimization (PSO) a*algorithms to avoid obtaining the local optimal solution caused by local convergence. Moreover, we adopt a noninertial velocity (NIV) update scheme to guide the particle flight trajectories. This scheme accelerates the process of convergence, saving the computing overhead a lot. The experimental results show that our proposed decomposition a*algorithm performs well for coherent and incoherent signals, and the improved optimization a*algorithm outperforms existing a*algorithms in both precision and computing consumption.
Aiming at the noise interference problem in wing fatigue tests, this paper improves the traditional LMS a*algorithm using the variational Versoria function and the variational Gaussian function. Additionally, this paper...
详细信息
Aiming at the noise interference problem in wing fatigue tests, this paper improves the traditional LMS a*algorithm using the variational Versoria function and the variational Gaussian function. Additionally, this paper proposes a variable step-size LMS (VSS-LMS) filtering a*algorithm based on the composite function (CVSS-LMS). The composite function combines the variational Versoria function and the variational Gaussian function to describe the nonlinear relationship between the iteration step size and the error. To adapt to environments with different signal-to-noise ratios, the a*algorithm replaces the fixed parameters with a combination of current and previous errors, thus enabling adaptive adjustment of the parameters. Moreover, a step-size dynamic constraint rule is proposed to further improve the stability of the a*algorithm. The a*algorithm is normalized using a combination of the cumulative sum of error squares, the mean square error (MSE), and the power of the input signal, which reduces the sensitivity to the input signal amplitude. The above parts finally constitute the adaptive CVSS-LMS (ACVSS-LMS) filtering a*algorithm. The convergence of the ACVSS-LMS a*algorithm is verified through theoretical derivation. The ACVSS-LMS a*algorithm is experimentally analyzed by using the simulation data generated by MATLAB and the actual data collected from the wing fatigue test, and the results show that the ACVSS-LMS a*algorithm proposed in this paper has a faster convergence speed and lower steady-state error compared to other a*algorithms.
暂无评论