The precise and timely extraction of railway signals is crucial for the creation of railway electronic maps.This paper introduces a novel real-time detection approach for dynamically adjusting railway signals,leveragi...The precise and timely extraction of railway signals is crucial for the creation of railway electronic maps.This paper introduces a novel real-time detection approach for dynamically adjusting railway signals,leveraging an enhanced Real-Time DEtection TRansformer(RT-DETR)model.The enhancement involves the integration of a vision Transformer with Dynamically Quantifiable Sampling Attention Mechanism(DQSAM)into the ResNet50 backbone of the RT-DETR framework,thereby enhancing the model’s efficiency and accuracy in handling intricate visual tasks.Secondly,an ultra-lightweight and effective Dynamic Grouping upSampler(DyGSample)is inserted into the efficient hybrid encode module as the up-sampling part.This operator can effectively upsample the feature graph without increasing the computational burden,and improve the model resolution and detail capture ability.In addition,in order to solve the problem of deep layer of model network and high operating cost,a new bounding box similarity loss function of rotation intersection over union based on minimum point distance is adopted in this paper,which takes into account all relevant factors of existing loss functions,namely overlapping or non-overlapping regions,center point distance,width and height deviation,and simplifies the calculation process.As a lightweight signal detection model with ultra-fast,high real-time,and high precision,the detection accuracy of this method is improved from 90.21%to 97.45%,which proves the superior performance and effectiveness of the improved real-time dynamic adjustment RT-DETR model in railway signal extraction.展开更多
Compared with the traditional manipulator,the hyper‐redundant manipulator has the advantage of high flexibility,which is particularly suitable for all kinds of complex working environments.However,the complex space e...Compared with the traditional manipulator,the hyper‐redundant manipulator has the advantage of high flexibility,which is particularly suitable for all kinds of complex working environments.However,the complex space environment requires the hyper‐redundant manipulator to have stronger obstacle avoidance ability and adaptability.In order to solve the problems of a large amount of calculation and poor obstacle avoidance effects in the path planning of the hyper‐redundant manipulator,this paper introduces the‘backbone curve’approach,which transforms the problem of solving joint path points into the behaviour of determining the backbone curve.After the backbone curve approach is used to design the curve that meets the requirements of obstacle avoidance and the end pose,the least squares fitting and the improved space joint fitting are used to match the plane curve and the space curve respectively,and the angle value of each joint of the manipulator is limited by the algorithm.Furthermore,a fusion obstacle avoidance algorithm is proposed to obtain the joint path points of the hyper‐redundant manipulator.Compared with the classic Jacobian iteration method,this method can avoid obstacles better,has the advantages of simple calculation,high efficiency,and can fully reflect the geometric characteristics of the manipulator.Simulation experiments have proven the feasibility of the algorithm.展开更多
A deep reinforcement learning(DRL)method based on the deep deterministic policy gradient(DDPG)algorithm is proposed to address the problems of a mismatch between the needed training samples and the actual training sam...A deep reinforcement learning(DRL)method based on the deep deterministic policy gradient(DDPG)algorithm is proposed to address the problems of a mismatch between the needed training samples and the actual training samples during the training of in-telligence,the overestimation and underestimation of the existence of Q-values,and the insufficient dynamism of the intelligence policy exploration.This method introduces the Actor-Critic Off-Policy Correction(AC-Off-POC)reinforcement learning framework and an improved double Q-value learning method,which enables the value function network in the target task to provide a more accurate evaluation of the policy network and converge to the optimal policy more quickly and stably to obtain higher value returns.The method is applied to multiple MuJoCo tasks on the Open AI Gym simulation platform.The experimental results show that it is better than the DDPG algorithm based solely on the different policy correction framework(AC-Off-POC)and the conventional DRL algorithm.The value of returns and stability of the double-Q-network off-policy correction algorithm for the deep deterministic policy gradient(DCAOP-DDPG)pro-posed by the authors are significantly higher than those of other DRL algorithms.展开更多
基金supported by the Hunan Provincial Natural Science Foundation of China(Nos.2025JJ70018 and 2025JJ70057)the Hunan Provincial Key Research and Development Program(No.2024JK2065).
文摘The precise and timely extraction of railway signals is crucial for the creation of railway electronic maps.This paper introduces a novel real-time detection approach for dynamically adjusting railway signals,leveraging an enhanced Real-Time DEtection TRansformer(RT-DETR)model.The enhancement involves the integration of a vision Transformer with Dynamically Quantifiable Sampling Attention Mechanism(DQSAM)into the ResNet50 backbone of the RT-DETR framework,thereby enhancing the model’s efficiency and accuracy in handling intricate visual tasks.Secondly,an ultra-lightweight and effective Dynamic Grouping upSampler(DyGSample)is inserted into the efficient hybrid encode module as the up-sampling part.This operator can effectively upsample the feature graph without increasing the computational burden,and improve the model resolution and detail capture ability.In addition,in order to solve the problem of deep layer of model network and high operating cost,a new bounding box similarity loss function of rotation intersection over union based on minimum point distance is adopted in this paper,which takes into account all relevant factors of existing loss functions,namely overlapping or non-overlapping regions,center point distance,width and height deviation,and simplifies the calculation process.As a lightweight signal detection model with ultra-fast,high real-time,and high precision,the detection accuracy of this method is improved from 90.21%to 97.45%,which proves the superior performance and effectiveness of the improved real-time dynamic adjustment RT-DETR model in railway signal extraction.
基金State Administration of Science.Technology and Industry for National Defense,Grant/Award Number:JCKY2020404C001。
文摘Compared with the traditional manipulator,the hyper‐redundant manipulator has the advantage of high flexibility,which is particularly suitable for all kinds of complex working environments.However,the complex space environment requires the hyper‐redundant manipulator to have stronger obstacle avoidance ability and adaptability.In order to solve the problems of a large amount of calculation and poor obstacle avoidance effects in the path planning of the hyper‐redundant manipulator,this paper introduces the‘backbone curve’approach,which transforms the problem of solving joint path points into the behaviour of determining the backbone curve.After the backbone curve approach is used to design the curve that meets the requirements of obstacle avoidance and the end pose,the least squares fitting and the improved space joint fitting are used to match the plane curve and the space curve respectively,and the angle value of each joint of the manipulator is limited by the algorithm.Furthermore,a fusion obstacle avoidance algorithm is proposed to obtain the joint path points of the hyper‐redundant manipulator.Compared with the classic Jacobian iteration method,this method can avoid obstacles better,has the advantages of simple calculation,high efficiency,and can fully reflect the geometric characteristics of the manipulator.Simulation experiments have proven the feasibility of the algorithm.
文摘A deep reinforcement learning(DRL)method based on the deep deterministic policy gradient(DDPG)algorithm is proposed to address the problems of a mismatch between the needed training samples and the actual training samples during the training of in-telligence,the overestimation and underestimation of the existence of Q-values,and the insufficient dynamism of the intelligence policy exploration.This method introduces the Actor-Critic Off-Policy Correction(AC-Off-POC)reinforcement learning framework and an improved double Q-value learning method,which enables the value function network in the target task to provide a more accurate evaluation of the policy network and converge to the optimal policy more quickly and stably to obtain higher value returns.The method is applied to multiple MuJoCo tasks on the Open AI Gym simulation platform.The experimental results show that it is better than the DDPG algorithm based solely on the different policy correction framework(AC-Off-POC)and the conventional DRL algorithm.The value of returns and stability of the double-Q-network off-policy correction algorithm for the deep deterministic policy gradient(DCAOP-DDPG)pro-posed by the authors are significantly higher than those of other DRL algorithms.
