Aiming to suppress the same frequency current vibration of the active magnetic bearing (AMB) system with rotor imbalance, this paper proposes a novel automatic balancing control strategy based on Recursive Least Squares (RLS) algorithm and uses fuzzy control algorithm to improve the robustness of the PID controller. This method can effectively suppress the same frequency current while enhancing the anti-interference ability of the control system. The simulation results demonstrate the availability of this strategy. Compared to the automatic balancing algorithm that combines traditional LMS filters and PID controllers, the control method combining the RLS filter and the fuzzy-PID controller has a faster current convergence speed and stronger anti-interference ability.
{"title":"Recursive Least Square Method Based Automatic Balance Control of Active Magnetic Bearings","authors":"Jiming Zou, Fayuan Xie, Wentao Zhang, Yongxiang Xu","doi":"10.1109/ICMA57826.2023.10215655","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215655","url":null,"abstract":"Aiming to suppress the same frequency current vibration of the active magnetic bearing (AMB) system with rotor imbalance, this paper proposes a novel automatic balancing control strategy based on Recursive Least Squares (RLS) algorithm and uses fuzzy control algorithm to improve the robustness of the PID controller. This method can effectively suppress the same frequency current while enhancing the anti-interference ability of the control system. The simulation results demonstrate the availability of this strategy. Compared to the automatic balancing algorithm that combines traditional LMS filters and PID controllers, the control method combining the RLS filter and the fuzzy-PID controller has a faster current convergence speed and stronger anti-interference ability.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131993182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-06DOI: 10.1109/ICMA57826.2023.10215887
Xiaozhen Huang, Min Yang, Xu Peng, Xiaoyao Zhao, Min Chen, Xiaomei Xie
Artificial acoustic metasurfaces with good low-frequency sound absorption properties have received extensive attention in the past few years, and different superstructure surfaces have been proposed. Reasonable structural size design is typically necessary for achieving better sound absorption performance in structures, but identifying the ideal size can be a challenging task. this paper suggests an approach to quickly find the appropriate size of the metasurface that meets the given sound absorption coefficient and structural thickness. We first studied the sensitivity of the absorption coefficient to the structural parameters. Based on the sensitivity ranking results, we further analyzed the influence of these structural parameters on the absorption coefficient. Finally, by introducing the Non-Dominated Sorted Genetic Algorithm-II(NSGA-II) in the structural design, the metasurface structure that meet the requirements of a given index can be constructed in the specified frequency range and absorption coefficient, and the structural optimization design of the broadband sound absorption metasurface can be carried out.
近年来，具有良好低频吸声性能的人造声学超表面受到了广泛的关注，并提出了不同的超结构表面。合理的结构尺寸设计通常是实现更好的吸声性能的必要条件，但确定理想的尺寸是一项具有挑战性的任务。本文提出了一种快速找到满足给定吸声系数和结构厚度的合适超表面尺寸的方法。我们首先研究了吸收系数对结构参数的敏感性。在灵敏度排序结果的基础上，进一步分析了结构参数对吸收系数的影响。最后，在结构设计中引入非支配排序遗传算法- ii (NSGA-II)，在规定的频率范围和吸收系数下构建满足给定指标要求的超表面结构，进行宽带吸声超表面的结构优化设计。
{"title":"Multi-objective optimization of Spatial Curved Acoustic Metasurface by Genetic Algorithm","authors":"Xiaozhen Huang, Min Yang, Xu Peng, Xiaoyao Zhao, Min Chen, Xiaomei Xie","doi":"10.1109/ICMA57826.2023.10215887","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215887","url":null,"abstract":"Artificial acoustic metasurfaces with good low-frequency sound absorption properties have received extensive attention in the past few years, and different superstructure surfaces have been proposed. Reasonable structural size design is typically necessary for achieving better sound absorption performance in structures, but identifying the ideal size can be a challenging task. this paper suggests an approach to quickly find the appropriate size of the metasurface that meets the given sound absorption coefficient and structural thickness. We first studied the sensitivity of the absorption coefficient to the structural parameters. Based on the sensitivity ranking results, we further analyzed the influence of these structural parameters on the absorption coefficient. Finally, by introducing the Non-Dominated Sorted Genetic Algorithm-II(NSGA-II) in the structural design, the metasurface structure that meet the requirements of a given index can be constructed in the specified frequency range and absorption coefficient, and the structural optimization design of the broadband sound absorption metasurface can be carried out.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132076780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-06DOI: 10.1109/ICMA57826.2023.10215663
Di Wu, Zhaolong Feng, Dongdong Hou, Rui Liu, Yufei Yin
Both path planning and obstacle avoidance are important for the navigation safety of autonomous underwater vehicles (AUVs) in unknown environments. In this paper, in order to adjust to the complexity and flexibility of underwater environments, path planning and obstacle avoidance algorithms based on value iterative network (VIN) and deep deterministic policy gradient (DDPG) respectively are proposed to navigate the AUV through an unknown complex area. With a simulation multi-beam sonar equipped to detect obstacles of subsea surroundings, a grid map is constructed online as inputs of VIN and DDPG. Taking advantage of generalization of deep reinforcement learning, methods studied in this paper have demonstrated validity in simulation experiments implemented in Unity3D where dynamic and static obstacles are randomly placed and experiments are conducted.
{"title":"DRL-based path planning and obstacle avoidance of autonomous underwater vehicle","authors":"Di Wu, Zhaolong Feng, Dongdong Hou, Rui Liu, Yufei Yin","doi":"10.1109/ICMA57826.2023.10215663","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215663","url":null,"abstract":"Both path planning and obstacle avoidance are important for the navigation safety of autonomous underwater vehicles (AUVs) in unknown environments. In this paper, in order to adjust to the complexity and flexibility of underwater environments, path planning and obstacle avoidance algorithms based on value iterative network (VIN) and deep deterministic policy gradient (DDPG) respectively are proposed to navigate the AUV through an unknown complex area. With a simulation multi-beam sonar equipped to detect obstacles of subsea surroundings, a grid map is constructed online as inputs of VIN and DDPG. Taking advantage of generalization of deep reinforcement learning, methods studied in this paper have demonstrated validity in simulation experiments implemented in Unity3D where dynamic and static obstacles are randomly placed and experiments are conducted.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132135980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-06DOI: 10.1109/ICMA57826.2023.10215543
Lei Wang, Yi Wang, Jin Wu
In order to assess the independent walking ability of elderly people, a system for assessing the independent walking ability of elderly people using yolov5 target detection was developed, and the accuracy of the detection was improved with a modified R2-yo1ov based on yolov5 by replacing the residual structure bottleneck in its unique C3 structure with the Res2net residual module, and by channel-wise and activation function optimization in terms of channels and activation functions. In order to enhance the information transfer between network layers, the upper and lower feature layers are fused to improve the detection effect. The experimental results show that the map of R2-yo1ov5 tested on the elderly helper dataset can reach 96.7%, which is 1.8% higher than the original yolov5 network, and the detection effect of support class is improved by 5.5%, which is a significant improvement in the detection effect and can meet the requirements of the detection scenario.
{"title":"Elderly Helper Detection based on R2-yolov5","authors":"Lei Wang, Yi Wang, Jin Wu","doi":"10.1109/ICMA57826.2023.10215543","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215543","url":null,"abstract":"In order to assess the independent walking ability of elderly people, a system for assessing the independent walking ability of elderly people using yolov5 target detection was developed, and the accuracy of the detection was improved with a modified R2-yo1ov based on yolov5 by replacing the residual structure bottleneck in its unique C3 structure with the Res2net residual module, and by channel-wise and activation function optimization in terms of channels and activation functions. In order to enhance the information transfer between network layers, the upper and lower feature layers are fused to improve the detection effect. The experimental results show that the map of R2-yo1ov5 tested on the elderly helper dataset can reach 96.7%, which is 1.8% higher than the original yolov5 network, and the detection effect of support class is improved by 5.5%, which is a significant improvement in the detection effect and can meet the requirements of the detection scenario.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132211059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-06DOI: 10.1109/ICMA57826.2023.10215810
C. Ye, Yuhui Zhang, Suyang Yu, Dongqi Li
A novel omni-directional mobile robot for lower limb rehabilitation is proposed for the needs of stroke patients. The robot consists of an omni-directional mobile platform equipped with MY3 wheels, a lower limb joint module and a hip support module for rehabilitation training and assisted mobility. Parameters of the normal walking gait pattern are evaluated and obtained. The omni-directional mobile platform was designed based on the MY3 wheel modules. The lower limb joint module is designed in combination with cam and synchronous belt mechanism to achieve multi-degree of freedom movement with a single drive, which can assist patients in executing normal gait during general training. The overall kinematic model of the robot is developed for motion control by applying the velocity equation and the D-H method. The prototype of robot is developed and experiments are conducted on unloaded operation and manned linear trajectory walking. Experimental results show that the robot can achieve a simple mechanism to guide the movement of the lower limb in the desired gait pattern. The study demonstrates the concept and feasibility of this new lower extremity gait rehabilitation robot.
{"title":"Development of an Omni-directional Lower Limb Rehabilitation Mobile Robot","authors":"C. Ye, Yuhui Zhang, Suyang Yu, Dongqi Li","doi":"10.1109/ICMA57826.2023.10215810","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215810","url":null,"abstract":"A novel omni-directional mobile robot for lower limb rehabilitation is proposed for the needs of stroke patients. The robot consists of an omni-directional mobile platform equipped with MY3 wheels, a lower limb joint module and a hip support module for rehabilitation training and assisted mobility. Parameters of the normal walking gait pattern are evaluated and obtained. The omni-directional mobile platform was designed based on the MY3 wheel modules. The lower limb joint module is designed in combination with cam and synchronous belt mechanism to achieve multi-degree of freedom movement with a single drive, which can assist patients in executing normal gait during general training. The overall kinematic model of the robot is developed for motion control by applying the velocity equation and the D-H method. The prototype of robot is developed and experiments are conducted on unloaded operation and manned linear trajectory walking. Experimental results show that the robot can achieve a simple mechanism to guide the movement of the lower limb in the desired gait pattern. The study demonstrates the concept and feasibility of this new lower extremity gait rehabilitation robot.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130279942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-06DOI: 10.1109/ICMA57826.2023.10216247
Ying Zhang, Zhigang Kan, Dongyu Qu
This study takes into account the emphasis on cultural industries in China’s national policy and the government’s plans for related industries in industrial cities after the “New Crown Epidemic”, and proposes strategies for developing cultural and creative product designs that suit the characteristics of industrial tourism in the region. This study takes Jilin Province, China, as a case study, and proposes a series of targeted design strategies, such as the differentiation of pre-design thinking, adhering to the principle of giving full play to the local industrial cultural characteristics, digging deeper into the value of cultural tourism resources, and incorporating the unique industrial cultural genes of the region, forming specific measures to solve the problem of cultural and creative product design, and enriching the theoretical research and practical application of “industrial tourism Theoretical research and practical application of “industrial tourism culture”, the development and design of cultural and creative products as an entry point to promote the effective adjustment of modern industrial structure and the development of regional economy.
{"title":"Study on the Creative Design of Tourism Products in Industrial Culture","authors":"Ying Zhang, Zhigang Kan, Dongyu Qu","doi":"10.1109/ICMA57826.2023.10216247","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10216247","url":null,"abstract":"This study takes into account the emphasis on cultural industries in China’s national policy and the government’s plans for related industries in industrial cities after the “New Crown Epidemic”, and proposes strategies for developing cultural and creative product designs that suit the characteristics of industrial tourism in the region. This study takes Jilin Province, China, as a case study, and proposes a series of targeted design strategies, such as the differentiation of pre-design thinking, adhering to the principle of giving full play to the local industrial cultural characteristics, digging deeper into the value of cultural tourism resources, and incorporating the unique industrial cultural genes of the region, forming specific measures to solve the problem of cultural and creative product design, and enriching the theoretical research and practical application of “industrial tourism Theoretical research and practical application of “industrial tourism culture”, the development and design of cultural and creative products as an entry point to promote the effective adjustment of modern industrial structure and the development of regional economy.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130292685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-06DOI: 10.1109/ICMA57826.2023.10216034
Mingyang Guo, J. Sha, Yanheng Wang, Jixin Gao
Aiming at the problems of complex background, low resolution, and target scale variation in infrared images observed from UAV, we propose an efficient infrared scene target detection algorithm (FSC-YOLOv5s), which can effectively improve the accuracy of infrared target detection in the perspective of UAV. Firstly, we propose the FC3 module to improve the backbone network of YOLOv5s, which has information fusion between the backbone networks. Then, the Swin Transformer module is added to the end of the feature extraction Spatial Pyramid Pooling Structure (SPPF) and the neck network feature fusion to fully extract the image feature information. Finally, on the basis of the original feature fusion, the shallow features were fused by downsampling to extract rich semantic information. Experimental results show that although the number of model parameters is increased slightly, the detection accuracy mAP reaches 92.3%, which is 2% higher than that of YOLOv5s, and the speed reaches 37.88FPS. It can be seen that FSC-YOLOv5s has faster convergence speed, higher detection accuracy, and good real-time performance, which is more conducive to practical applications.
{"title":"FSC-YOLOv5s: A target detection algorithm for aerial infrared scenes","authors":"Mingyang Guo, J. Sha, Yanheng Wang, Jixin Gao","doi":"10.1109/ICMA57826.2023.10216034","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10216034","url":null,"abstract":"Aiming at the problems of complex background, low resolution, and target scale variation in infrared images observed from UAV, we propose an efficient infrared scene target detection algorithm (FSC-YOLOv5s), which can effectively improve the accuracy of infrared target detection in the perspective of UAV. Firstly, we propose the FC3 module to improve the backbone network of YOLOv5s, which has information fusion between the backbone networks. Then, the Swin Transformer module is added to the end of the feature extraction Spatial Pyramid Pooling Structure (SPPF) and the neck network feature fusion to fully extract the image feature information. Finally, on the basis of the original feature fusion, the shallow features were fused by downsampling to extract rich semantic information. Experimental results show that although the number of model parameters is increased slightly, the detection accuracy mAP reaches 92.3%, which is 2% higher than that of YOLOv5s, and the speed reaches 37.88FPS. It can be seen that FSC-YOLOv5s has faster convergence speed, higher detection accuracy, and good real-time performance, which is more conducive to practical applications.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134192426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-06DOI: 10.1109/ICMA57826.2023.10216115
Ming Wang, P. Xu, Yiming Liu, Dong Xu, Qishuang Ma
This article introduces a new prototype of a magnetic-driven capsule robot. The design utilizes the idea of nonlinear magnetic field motion coupling to achieve four degrees of freedom motion of the capsule robot. Transmission of force and torque between an external driving device and an internal camera device through magnetic field coupling and the internal camera's anchoring and rotation functions are achieved by an external rotating magnetic field. As the motion and posture control of the capsule robot are entirely controlled by six permanent magnets, we use a 3D printer to print a resin shell to hold two square permanent magnets, and an external stepper motor is used to control the rotational motion of the annular permanent magnet in the external device to drive the posture control of the capsule robot's head movement device. The overall width and length of the capsule robot are 25mm and 108mm, respectively, meeting the minimum incision size for laparoscopic minimally invasive surgery. To validate the feasibility of the capsule robots, we used a nylon board as the human abdominal cavity (their magnetic permeability is approximately 1). We completed a four-degree-of-freedom control experiment of capsule robots in an open environment and verified the stable tilt angle error of the capsule robot to be within 0.1°. This demonstrated the feasibility of the new magnetic-controlled robot in obtaining stable images during actual single-port laparoscopic surgery.
{"title":"Research on anchoring and actuation of a novel magnetically driven laparoscopic robot","authors":"Ming Wang, P. Xu, Yiming Liu, Dong Xu, Qishuang Ma","doi":"10.1109/ICMA57826.2023.10216115","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10216115","url":null,"abstract":"This article introduces a new prototype of a magnetic-driven capsule robot. The design utilizes the idea of nonlinear magnetic field motion coupling to achieve four degrees of freedom motion of the capsule robot. Transmission of force and torque between an external driving device and an internal camera device through magnetic field coupling and the internal camera's anchoring and rotation functions are achieved by an external rotating magnetic field. As the motion and posture control of the capsule robot are entirely controlled by six permanent magnets, we use a 3D printer to print a resin shell to hold two square permanent magnets, and an external stepper motor is used to control the rotational motion of the annular permanent magnet in the external device to drive the posture control of the capsule robot's head movement device. The overall width and length of the capsule robot are 25mm and 108mm, respectively, meeting the minimum incision size for laparoscopic minimally invasive surgery. To validate the feasibility of the capsule robots, we used a nylon board as the human abdominal cavity (their magnetic permeability is approximately 1). We completed a four-degree-of-freedom control experiment of capsule robots in an open environment and verified the stable tilt angle error of the capsule robot to be within 0.1°. This demonstrated the feasibility of the new magnetic-controlled robot in obtaining stable images during actual single-port laparoscopic surgery.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134236684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-06DOI: 10.1109/ICMA57826.2023.10215844
Qi Shao
Navigation software can be extensively used in vehicle navigation, robot navigation, etc. commonly used such as RTKLIB, the quality of which directly affects the navigation effect. Variation testing is a software testing method that effectively identifies the quality of test data sets, and occupies a significant position in the field of software testing. Based on the source program, it generates variants by subtle changes in the fallible place, producing automatically the testing data of killing the variants to improve the efficiency of variation testing. As the core of RTKLIB navigation software, this paper adopts the weak variant testing method based on paths comparison, i.e., the variant is killed if the paths generated by the testing data running the source program and variations respectively are the same. Compared with randomization, the genetic algorithm adopted in this paper is qualified with shorter testing time and higher efficiency in generating variation testing data.
{"title":"Automatic Case Generation of Variation Testing in Navigation Software Based on the Genetic Algorithm","authors":"Qi Shao","doi":"10.1109/ICMA57826.2023.10215844","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215844","url":null,"abstract":"Navigation software can be extensively used in vehicle navigation, robot navigation, etc. commonly used such as RTKLIB, the quality of which directly affects the navigation effect. Variation testing is a software testing method that effectively identifies the quality of test data sets, and occupies a significant position in the field of software testing. Based on the source program, it generates variants by subtle changes in the fallible place, producing automatically the testing data of killing the variants to improve the efficiency of variation testing. As the core of RTKLIB navigation software, this paper adopts the weak variant testing method based on paths comparison, i.e., the variant is killed if the paths generated by the testing data running the source program and variations respectively are the same. Compared with randomization, the genetic algorithm adopted in this paper is qualified with shorter testing time and higher efficiency in generating variation testing data.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131724236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-06DOI: 10.1109/ICMA57826.2023.10215569
Yan Gao, Ze Ji, Jing Wu, Changyun Wei, R. Grech
Hierarchical reinforcement learning (HRL) is a promising approach for complex mapless navigation tasks by decomposing the task into a hierarchy of subtasks. However, selecting appropriate subgoals is challenging. Existing methods predominantly rely on sensory inputs, which may contain inadequate information or excessive redundancy. Inspired by the cognitive processes underpinning human navigation, our aim is to enable the robot to leverage both ‘intrinsic and extrinsic factors’ to make informed decisions regarding subgoal selection. In this work, we propose a novel HRL-based mapless navigation framework. Specifically, we introduce a predictive module, named Predictive Exploration Worthiness (PEW), into the high-level (HL) decision-making policy. The hypothesis is that the worthiness of an area for further exploration is related to obstacle spatial distribution, such as the area of free space and the distribution of obstacles. The PEW is introduced as a compact representation for obstacle spatial distribution. Additionally, to incorporate ‘intrinsic factors’ in the subgoal selection process, a penalty element is introduced in the HL reward function, allowing the robot to take into account the capabilities of the low-level policy when selecting subgoals. Our method exhibits significant improvements in success rate when tested in unseen environments.
{"title":"Hierarchical Reinforcement Learning-based Mapless Navigation with Predictive Exploration Worthiness","authors":"Yan Gao, Ze Ji, Jing Wu, Changyun Wei, R. Grech","doi":"10.1109/ICMA57826.2023.10215569","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215569","url":null,"abstract":"Hierarchical reinforcement learning (HRL) is a promising approach for complex mapless navigation tasks by decomposing the task into a hierarchy of subtasks. However, selecting appropriate subgoals is challenging. Existing methods predominantly rely on sensory inputs, which may contain inadequate information or excessive redundancy. Inspired by the cognitive processes underpinning human navigation, our aim is to enable the robot to leverage both ‘intrinsic and extrinsic factors’ to make informed decisions regarding subgoal selection. In this work, we propose a novel HRL-based mapless navigation framework. Specifically, we introduce a predictive module, named Predictive Exploration Worthiness (PEW), into the high-level (HL) decision-making policy. The hypothesis is that the worthiness of an area for further exploration is related to obstacle spatial distribution, such as the area of free space and the distribution of obstacles. The PEW is introduced as a compact representation for obstacle spatial distribution. Additionally, to incorporate ‘intrinsic factors’ in the subgoal selection process, a penalty element is introduced in the HL reward function, allowing the robot to take into account the capabilities of the low-level policy when selecting subgoals. Our method exhibits significant improvements in success rate when tested in unseen environments.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132604137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：