Aiming at the dimension disaster problem, poor model generalization ability and deadlock problem in special obstacles environment caused by the increase of state information in the local path planning process of mobil...Aiming at the dimension disaster problem, poor model generalization ability and deadlock problem in special obstacles environment caused by the increase of state information in the local path planning process of mobile robot, this paper proposed a Double BP Q-learning algorithm based on the fusion of Double Q-learning algorithm and BP neural network. In order to solve the dimensional disaster problem, two BP neural network fitting value functions with the same network structure were used to replace the two <i>Q</i> value tables in Double Q-Learning algorithm to solve the problem that the <i>Q</i> value table cannot store excessive state information. By adding the mechanism of priority experience replay and using the parameter transfer to initialize the model parameters in different environments, it could accelerate the convergence rate of the algorithm, improve the learning efficiency and the generalization ability of the model. By designing specific action selection strategy in special environment, the deadlock state could be avoided and the mobile robot could reach the target point. Finally, the designed Double BP Q-learning algorithm was simulated and verified, and the probability of mobile robot reaching the target point in the parameter update process was compared with the Double Q-learning algorithm under the same condition of the planned path length. The results showed that the model trained by the improved Double BP Q-learning algorithm had a higher success rate in finding the optimal or sub-optimal path in the dense discrete environment, besides, it had stronger model generalization ability, fewer redundant sections, and could reach the target point without entering the deadlock zone in the special obstacles environment.展开更多
The forward-looking image sonar is a necessary vision device for Autonomous Underwater Vehicles （AUV）. Based on the acoustic image received from forward-looking image sonar, AUV local path is planned. When the envir...The forward-looking image sonar is a necessary vision device for Autonomous Underwater Vehicles （AUV）. Based on the acoustic image received from forward-looking image sonar, AUV local path is planned. When the environment model is made to adapt to local path planning, an iterative algorithm of binary conversion is used for image segmentation. Raw data of the acoustic image, which were received from serial port, are processed. By the use of ＂Mathematic Morphology＂ to filter noise, a mathematic model of environment for local path planning is established after coordinate transformation. The optimal path is searched by the distant transmission （Dt） algorithm. Simulation is conducted for the analysis of the algorithm. Experiment on the sea proves it reliable.展开更多
Conducting hydrodynamic and physical motion simulation tests using a large-scale self-propelled model under actual wave conditions is an important means for researching environmental adaptability of ships. During the ...Conducting hydrodynamic and physical motion simulation tests using a large-scale self-propelled model under actual wave conditions is an important means for researching environmental adaptability of ships. During the navigation test of the self-propelled model, the complex environment including various port facilities, navigation facilities, and the ships nearby must be considered carefully, because in this dense environment the impact of sea waves and winds on the model is particularly significant. In order to improve the security of the self-propelled model, this paper introduces the Q learning based on reinforcement learning combined with chaotic ideas for the model＇s collision avoidance, in order to improve the reliability of the local path planning. Simulation and sea test results show that this algorithm is a better solution for collision avoidance of the self navigation model under the interference of sea winds and waves with good adaptability.展开更多
An efficient algorithm for path planning is crucial for guiding autonomous surface vehicles(ASVs)through designated waypoints.However,current evaluations of ASV path planning mainly focus on comparing total path lengt...An efficient algorithm for path planning is crucial for guiding autonomous surface vehicles(ASVs)through designated waypoints.However,current evaluations of ASV path planning mainly focus on comparing total path lengths,using temporal models to estimate travel time,idealized integration of global and local motion planners,and omission of external environmental disturbances.These rudimentary criteria cannot adequately capture real-world operations.To address these shortcomings,this study introduces a simulation framework for evaluating navigation modules designed for ASVs.The proposed framework is implemented on a prototype ASV using the Robot Operating System(ROS)and the Gazebo simulation platform.The implementation processes replicated satellite images with the extended Kalman filter technique to acquire localized location data.Cost minimization for global trajectories is achieved through the application of Dijkstra and A*algorithms,while local obstacle avoidance is managed by the dynamic window approach algorithm.The results demonstrate the distinctions and intricacies of the metrics provided by the proposed simulation framework compared with the rudimentary criteria commonly utilized in conventional path planning works.展开更多
In order to solve the problem of path planning of tower cranes,an improved ant colony algorithm was proposed.Firstly,the tower crane was simplified into a three-degree-of-freedom mechanical arm,and the D-H motion mode...In order to solve the problem of path planning of tower cranes,an improved ant colony algorithm was proposed.Firstly,the tower crane was simplified into a three-degree-of-freedom mechanical arm,and the D-H motion model was established to solve the forward and inverse kinematic equations.Secondly,the traditional ant colony algorithm was improved.The heuristic function was improved by introducing the distance between the optional nodes and the target point into the function.Then the transition probability was improved by introducing the security factor of surrounding points into the transition probability.In addition,the local path chunking strategy was used to optimize the local multi-inflection path and reduce the local redundant inflection points.Finally,according to the position of the hook,the kinematic inversion of the tower crane was carried out,and the variables of each joint were obtained.More specifically,compared with the traditional ant colony algorithm,the simulation results showed that improved ant colony algorithm converged faster,shortened the optimal path length,and optimized the path quality in the simple and complex environment.展开更多
In the wireless localization application, multipath propagation seriously affects the localization accuracy. This paper presents two algorithms to solve the multipath problem. Firstly, we improve the Line of Possible ...In the wireless localization application, multipath propagation seriously affects the localization accuracy. This paper presents two algorithms to solve the multipath problem. Firstly, we improve the Line of Possible Mobile Device(LPMD) algorithm by optimizing the utilization of the direct paths for single-bound scattering scenario. Secondly, the signal path reckoning method with the assistance of geographic information system is proposed to solve the problem of localization with multi-bound scattering paths. With the building model's idealization, the proposed method refers to the idea of ray tracing and dead reckoning. According to the rule of wireless signal reflection, the signal propagation path is reckoned using the measurements of emission angle and propagation distance, and then the estimated location can be obtained. Simulation shows that the proposed method obtains better results than the existing geometric localization methods in multipath environment when the angle error is controlled.展开更多
The physical properties of a reliable acoustic path （RAP） are analysed and subsequently a weighted-subspace~ fitting matched field （WSF-MF） method for passive localization is presented by exploiting the properties...The physical properties of a reliable acoustic path （RAP） are analysed and subsequently a weighted-subspace~ fitting matched field （WSF-MF） method for passive localization is presented by exploiting the properties of the RAP environment. The RAP is an important acoustic duct in the deep ocean, which occurs when the receiver is placed near the bottom where the sound velocity exceeds the maximum sound velocity in the vicinity of the surface. It is found that in the RAP environment the transmission loss is rather low and no blind zone of surveillance exists in a medium range. The ray theory is used to explain these phenomena. Furthermore, the analysis of the arrival structures shows that the source localization method based on arrival angle is feasible in this environment. However, the conventional methods suffer from the complicated and inaccurate estimation of the arrival angle. In this paper, a straightforward WSF-MF method is derived to exploit the information about the arrival angles indirectly. The method is to minimize the distance between the signal subspace and the spanned space by the array manifold in a finite range-depth space rather than the arrival-angle space. Simulations are performed to demonstrate the features of the method, and the results are explained by the arrival structures in the RAP environment.展开更多
For mobile anchor node static path planning cannot accord the actual distribution of node for dynamic adjustment. We take advantage of the high localization accuracy and low computational complexity of ad-hoc localiza...For mobile anchor node static path planning cannot accord the actual distribution of node for dynamic adjustment. We take advantage of the high localization accuracy and low computational complexity of ad-hoc localization system( AHLos)algorithm. This article introduces mobile anchor nodes instead of the traditional fixed anchor nodes to improve the algorithm. The result shows that, through introduce the mobile anchor node, the information of initial anchor nodes can be configured more flexible.Meanwhile,with the use of the approximate location and the transition path,the distance and energy consumption of the mobile anchor node is greatly reduced.展开更多
In automatic visual inspection, the object image subspace should be segmented and matched quickly so that the affine relationship can be built between the template image and the sample image. When the interference is ...In automatic visual inspection, the object image subspace should be segmented and matched quickly so that the affine relationship can be built between the template image and the sample image. When the interference is strong and the illumination is uneven, for example in an industrial application, this can make it difficult to obtain an objects subspace quickly and accurately in real-time. In this paper, a novel strategy is proposed to adopt discrete radial search paths instead of searching all points in an image. Therefore, the searching time can be substantially reduced. In order to reduce the influence coming from the industrial environment, the paper proposes another method that is local energy level set segmentation, which can locate the object subspace more efficiently and accurately. The detection of ＂crown caps＂ is presented as an example in this paper. Detection effects and computing time are compared between several detection methods, and the mechanisms of inspection have also been analyzed.展开更多
文摘Aiming at the dimension disaster problem, poor model generalization ability and deadlock problem in special obstacles environment caused by the increase of state information in the local path planning process of mobile robot, this paper proposed a Double BP Q-learning algorithm based on the fusion of Double Q-learning algorithm and BP neural network. In order to solve the dimensional disaster problem, two BP neural network fitting value functions with the same network structure were used to replace the two <i>Q</i> value tables in Double Q-Learning algorithm to solve the problem that the <i>Q</i> value table cannot store excessive state information. By adding the mechanism of priority experience replay and using the parameter transfer to initialize the model parameters in different environments, it could accelerate the convergence rate of the algorithm, improve the learning efficiency and the generalization ability of the model. By designing specific action selection strategy in special environment, the deadlock state could be avoided and the mobile robot could reach the target point. Finally, the designed Double BP Q-learning algorithm was simulated and verified, and the probability of mobile robot reaching the target point in the parameter update process was compared with the Double Q-learning algorithm under the same condition of the planned path length. The results showed that the model trained by the improved Double BP Q-learning algorithm had a higher success rate in finding the optimal or sub-optimal path in the dense discrete environment, besides, it had stronger model generalization ability, fewer redundant sections, and could reach the target point without entering the deadlock zone in the special obstacles environment.
文摘The forward-looking image sonar is a necessary vision device for Autonomous Underwater Vehicles （AUV）. Based on the acoustic image received from forward-looking image sonar, AUV local path is planned. When the environment model is made to adapt to local path planning, an iterative algorithm of binary conversion is used for image segmentation. Raw data of the acoustic image, which were received from serial port, are processed. By the use of ＂Mathematic Morphology＂ to filter noise, a mathematic model of environment for local path planning is established after coordinate transformation. The optimal path is searched by the distant transmission （Dt） algorithm. Simulation is conducted for the analysis of the algorithm. Experiment on the sea proves it reliable.
基金Foundation item： Supported by the National Natural Science Foundation of China under Grant No.61100005.
文摘Conducting hydrodynamic and physical motion simulation tests using a large-scale self-propelled model under actual wave conditions is an important means for researching environmental adaptability of ships. During the navigation test of the self-propelled model, the complex environment including various port facilities, navigation facilities, and the ships nearby must be considered carefully, because in this dense environment the impact of sea waves and winds on the model is particularly significant. In order to improve the security of the self-propelled model, this paper introduces the Q learning based on reinforcement learning combined with chaotic ideas for the model＇s collision avoidance, in order to improve the reliability of the local path planning. Simulation and sea test results show that this algorithm is a better solution for collision avoidance of the self navigation model under the interference of sea winds and waves with good adaptability.
基金Supported by the funding from RMIT Internal Research Grant R1.
文摘An efficient algorithm for path planning is crucial for guiding autonomous surface vehicles(ASVs)through designated waypoints.However,current evaluations of ASV path planning mainly focus on comparing total path lengths,using temporal models to estimate travel time,idealized integration of global and local motion planners,and omission of external environmental disturbances.These rudimentary criteria cannot adequately capture real-world operations.To address these shortcomings,this study introduces a simulation framework for evaluating navigation modules designed for ASVs.The proposed framework is implemented on a prototype ASV using the Robot Operating System(ROS)and the Gazebo simulation platform.The implementation processes replicated satellite images with the extended Kalman filter technique to acquire localized location data.Cost minimization for global trajectories is achieved through the application of Dijkstra and A*algorithms,while local obstacle avoidance is managed by the dynamic window approach algorithm.The results demonstrate the distinctions and intricacies of the metrics provided by the proposed simulation framework compared with the rudimentary criteria commonly utilized in conventional path planning works.
基金supported by Shaanxi Provincial Key Research and Development Program of China(Nos.2024GX-YBXM-305,2024GX-YBXM-178)Shaanxi Province Qinchuangyuan“Scientists+Engineers”Team Construction(No.2022KXJ032)。
文摘In order to solve the problem of path planning of tower cranes,an improved ant colony algorithm was proposed.Firstly,the tower crane was simplified into a three-degree-of-freedom mechanical arm,and the D-H motion model was established to solve the forward and inverse kinematic equations.Secondly,the traditional ant colony algorithm was improved.The heuristic function was improved by introducing the distance between the optional nodes and the target point into the function.Then the transition probability was improved by introducing the security factor of surrounding points into the transition probability.In addition,the local path chunking strategy was used to optimize the local multi-inflection path and reduce the local redundant inflection points.Finally,according to the position of the hook,the kinematic inversion of the tower crane was carried out,and the variables of each joint were obtained.More specifically,compared with the traditional ant colony algorithm,the simulation results showed that improved ant colony algorithm converged faster,shortened the optimal path length,and optimized the path quality in the simple and complex environment.
基金supported by the National Natural Science Foundation of China (61471031)the Fundamental Research Funds for the Central Universities,Beijing Jiaotong University (2013JBZ001)+2 种基金National Science and Technology Major Project (2016ZX03001014006)the Open Research Fund of National Mobile Communications Research Laboratory,Southeast University (No.2017D14)Shenzhen Peacock Program under Grant No.KQJSCX20160226193545
文摘In the wireless localization application, multipath propagation seriously affects the localization accuracy. This paper presents two algorithms to solve the multipath problem. Firstly, we improve the Line of Possible Mobile Device(LPMD) algorithm by optimizing the utilization of the direct paths for single-bound scattering scenario. Secondly, the signal path reckoning method with the assistance of geographic information system is proposed to solve the problem of localization with multi-bound scattering paths. With the building model's idealization, the proposed method refers to the idea of ray tracing and dead reckoning. According to the rule of wireless signal reflection, the signal propagation path is reckoned using the measurements of emission angle and propagation distance, and then the estimated location can be obtained. Simulation shows that the proposed method obtains better results than the existing geometric localization methods in multipath environment when the angle error is controlled.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11174235 and 61101192)the Science and Technology Development Project of Shaanxi Province,China(Grant No.2010KJXX-02)+2 种基金the Program for New Century Excellent Talents in University,China(Grant No.NCET-08-0455)the Foundation of State Key Lab of Acoustics,China(Grant No.SKLOA201101)the Doctorate Foundation of Northwestern Polytechnical University,China(Grant No.CX201226)
文摘The physical properties of a reliable acoustic path （RAP） are analysed and subsequently a weighted-subspace~ fitting matched field （WSF-MF） method for passive localization is presented by exploiting the properties of the RAP environment. The RAP is an important acoustic duct in the deep ocean, which occurs when the receiver is placed near the bottom where the sound velocity exceeds the maximum sound velocity in the vicinity of the surface. It is found that in the RAP environment the transmission loss is rather low and no blind zone of surveillance exists in a medium range. The ray theory is used to explain these phenomena. Furthermore, the analysis of the arrival structures shows that the source localization method based on arrival angle is feasible in this environment. However, the conventional methods suffer from the complicated and inaccurate estimation of the arrival angle. In this paper, a straightforward WSF-MF method is derived to exploit the information about the arrival angles indirectly. The method is to minimize the distance between the signal subspace and the spanned space by the array manifold in a finite range-depth space rather than the arrival-angle space. Simulations are performed to demonstrate the features of the method, and the results are explained by the arrival structures in the RAP environment.
基金National Natural Science Foundations of China(Nos.U1162202,61203157)the Fundamental Research Funds for the Central Universities and Shanghai Leading Academic Discipline Project,China(No.B504)
文摘For mobile anchor node static path planning cannot accord the actual distribution of node for dynamic adjustment. We take advantage of the high localization accuracy and low computational complexity of ad-hoc localization system( AHLos)algorithm. This article introduces mobile anchor nodes instead of the traditional fixed anchor nodes to improve the algorithm. The result shows that, through introduce the mobile anchor node, the information of initial anchor nodes can be configured more flexible.Meanwhile,with the use of the approximate location and the transition path,the distance and energy consumption of the mobile anchor node is greatly reduced.
文摘In automatic visual inspection, the object image subspace should be segmented and matched quickly so that the affine relationship can be built between the template image and the sample image. When the interference is strong and the illumination is uneven, for example in an industrial application, this can make it difficult to obtain an objects subspace quickly and accurately in real-time. In this paper, a novel strategy is proposed to adopt discrete radial search paths instead of searching all points in an image. Therefore, the searching time can be substantially reduced. In order to reduce the influence coming from the industrial environment, the paper proposes another method that is local energy level set segmentation, which can locate the object subspace more efficiently and accurately. The detection of ＂crown caps＂ is presented as an example in this paper. Detection effects and computing time are compared between several detection methods, and the mechanisms of inspection have also been analyzed.
