A path-planning algorithm for autonomous vehicles based on traffic stability criteria: the AS-IAPF algorithm DOI Creative Commons

Minqing Zhao,

Xuan Li, Yuming Lu

и другие.

Mechanical sciences, Год журнала: 2024, Номер 15(2), С. 613 - 631

Опубликована: Ноя. 8, 2024

Abstract. Urban traffic congestion, obstacle avoidance, and driving efficiency are the challenges faced by autonomous-vehicle path-planning technology in cities. The traditional artificial potential field (APF) algorithm is insufficient to meet requirements of safety path planning, as it easily gets trapped local optima when dealing with complex environments. Therefore, this paper proposes a novel AS-IAPF more efficiently enhance target reachability autonomous vehicles Firstly, analyzes elucidates macroscopic model, achieving effective modeling dynamic flow stability based on Lyapunov theorem classical 1D model. Thus, threshold discriminant formula for element obtained. Secondly, aforementioned formula, new proposed. mainly includes two aspects: firstly, pre-generating initial paths introducing Gaussian oscillation coefficient force fields, avoids falling into optima; secondly, using dimensional adjustment adaptively improving adjusting strength AS-APF repulsive field, further improves planning. Finally, subjected joint simulations 2D 3D scenarios different types. research results show that outperforms other algorithms same type respect comprehensive performance multiple scenario simulation experiments. In experiments three typical scenarios, proposed can drive effectively perform corresponding avoidance actions actual ahead, ultimately safe avoidance. method while considering vehicles, providing promising approach reference planning vehicles.

Язык: Английский

Research on autonomous navigation of mobile robots based on IA-DWA algorithm DOI Creative Commons

Quanling He,

Zongyan Wang, Kun Li

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 15, 2025

To improve the efficiency of mobile robot movement, this paper investigates fusion A* algorithm with Dynamic Window Approach (DWA) (IA-DWA) to quickly search for globally optimal collision-free paths and avoid unknown obstacles in time. First, data from odometer inertial measurement unit (IMU) are fused using extended Kalman filter (EKF) reduce error caused by wheel slippage on robot's positioning accuracy. Second, prediction function, weight coefficients, neighborhood, path smoothing processing optimally designed incorporate critical point information global into DWA calculation framework. Then, length time convergence speed planning compared simulated raster maps different complexity. In terms time, reduces 23.3% A*-DWA; length, 1.8% A*-DWA, optimization iterations converge faster. Finally, reliability improved is verified conducting autonomous navigation experiments a ROS (Robot Operating System) as an experimental platform.

Язык: Английский

Процитировано

0
Nonlinear Compensation of the Linear Variable Differential Transducer Using an Advanced Snake Optimization Integrated with Tangential Functional Link Artificial Neural Network DOI Creative Commons
Qiuxia Fan,

X. Zhang,

Zhuang Wen

и другие.

Sensors, Год журнала: 2025, Номер 25(4), С. 1074 - 1074

Опубликована: Фев. 11, 2025

The linear variable differential transformer is a key component for measuring vibration noise and active isolation. nonlinear output associated with increased displacement in LVDT constrains the measurement range. To extend range, this paper proposes an advanced Snake Optimization–Tangential Functional Link Artificial Neural Network (ASO-TFLANN) model to range of LVDT. First, Latin hypercube sampling method Levy flight are introduced into snake optimization (SO) algorithm, which enhances global search ability diversity preservation SO algorithm effectively solves common overfitting local optimal problems training process gradient descent method. Second, voltage–displacement test bench constructed, collecting input data under four different main excitation conditions. Then, collected fed ASO-TFLANN determine weight vectors tangential functional link (TFLANN). Finally, by comparing simulation experiments several algorithms, it proven that ASO proposed On basis, through offline comparison online tests, reduces ϵfs while expanding significantly improves provides reliable basis improving accuracy.

Язык: Английский

Процитировано

0
3D path planning for AUVs under ocean currents by prioritized experience replay mechanism DOI

Hélène Huang,

Kai Song, Yun Chen

и другие.

Neurocomputing, Год журнала: 2025, Номер unknown, С. 129719 - 129719

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
Time-Impact Optimal Trajectory Planning for Wafer-Handling Robotic Arms Based on the Improved Snake Optimization Algorithm DOI Creative Commons
Yujie Ji,

J. Yu

Sensors, Год журнала: 2025, Номер 25(6), С. 1872 - 1872

Опубликована: Март 18, 2025

To enhance the working efficiency of a wafer-handling robotic arm and simultaneously alleviate impact vibration during motion process, trajectory planning approach based on an improved snake optimization (ISO) algorithm is proposed. The following improvements have been made to (SO) algorithm: introduction Chaotic Tent Map for initializing swarm, use randomly perturbed dynamic learning factors replace fixed values, application cosine annealing rate self-adaptively updating individual positions, incorporation Bayesian parameterization fine-tuning system’s selection process. Furthermore, ISO applied in Cartesian space effectively address challenge single-segment start–stop S-shaped speed curve with arc transitions. simulation results indicate that has increased by 24.1% compared original plan, mean variance rankings have, respectively, 60.8% 63.4%, SO algorithm. Meanwhile, this study successfully achieved Pareto optimal solution time as targets established MATLAB experimental platform.

Язык: Английский

Процитировано

0
Improved Quintic Polynomial Autonomous Vehicle Lane-Change Trajectory Planning Based on Hybrid Algorithm Optimization DOI Creative Commons

Y. Zhang,

Lingshan Chen, Ning Li

и другие.

World Electric Vehicle Journal, Год журнала: 2025, Номер 16(5), С. 244 - 244

Опубликована: Апрель 23, 2025

A trajectory planning method is proposed to address the lane-changing problem in intelligent vehicles. The based on quintic polynomial improvement. transit position determined according and state of motion vehicle obstacle vehicle; process divided into two segments. polynomials are commonly applied planning, respectively, According different characteristics paths front rear segments, a multi-objective optimization function with weight coefficients established. safe comfortable achieved through improved particle swarm algorithm. Real-time simulation tests conducted hardware-in-the-loop platform. can be used scenarios plan trajectories.

Язык: Английский

Процитировано

0
Mechanical properties and adhesive parameter optimization of CFRP-Al bonded structures in hygrothermal environments DOI
Shuhui Zhang, Weiwen Cai, Qihua Ma

и другие.

Journal of Adhesion Science and Technology, Год журнала: 2025, Номер unknown, С. 1 - 37

Опубликована: Апрель 27, 2025

Язык: Английский

Процитировано

0
Path Planning Based on Artificial Potential Field with an Enhanced Virtual Hill Algorithm DOI Creative Commons

Hyun Jeong Lee,

Moon-Sik Kim, Min Cheol Lee

и другие.

Applied Sciences, Год журнала: 2024, Номер 14(18), С. 8292 - 8292

Опубликована: Сен. 14, 2024

The artificial potential field algorithm has been widely applied to mobile robots and robotic arms due its advantage of enabling simple efficient path planning in unknown environments. However, solving the local minimum problem is an essential task still being studied. Among current methods, technique using virtual hill concept reliable suitable for real-time because it does not create a new provides lower complexity. previous study, shape obstacles was considered determining robot’s direction at moment trapped minimum. For this reason, longer or blocked paths are sometimes selected. In we propose enhanced reduce errors selecting driving improve efficiency robot movemenIt. area, dead-end also proposed that allows return without entering deeply when encounters dead end.

Язык: Английский

Процитировано

3
A path-planning algorithm for autonomous vehicles based on traffic stability criteria: the AS-IAPF algorithm DOI Creative Commons

Minqing Zhao,

Xuan Li, Yuming Lu

и другие.

Mechanical sciences, Год журнала: 2024, Номер 15(2), С. 613 - 631

Опубликована: Ноя. 8, 2024

Abstract. Urban traffic congestion, obstacle avoidance, and driving efficiency are the challenges faced by autonomous-vehicle path-planning technology in cities. The traditional artificial potential field (APF) algorithm is insufficient to meet requirements of safety path planning, as it easily gets trapped local optima when dealing with complex environments. Therefore, this paper proposes a novel AS-IAPF more efficiently enhance target reachability autonomous vehicles Firstly, analyzes elucidates macroscopic model, achieving effective modeling dynamic flow stability based on Lyapunov theorem classical 1D model. Thus, threshold discriminant formula for element obtained. Secondly, aforementioned formula, new proposed. mainly includes two aspects: firstly, pre-generating initial paths introducing Gaussian oscillation coefficient force fields, avoids falling into optima; secondly, using dimensional adjustment adaptively improving adjusting strength AS-APF repulsive field, further improves planning. Finally, subjected joint simulations 2D 3D scenarios different types. research results show that outperforms other algorithms same type respect comprehensive performance multiple scenario simulation experiments. In experiments three typical scenarios, proposed can drive effectively perform corresponding avoidance actions actual ahead, ultimately safe avoidance. method while considering vehicles, providing promising approach reference planning vehicles.

Язык: Английский

Процитировано

0