Window grille is one of the expressions of traditional Chinese folk arts, which has unique stylistic characteristics and rich symbolic meanings. Studying how to extract the style characteristics of window grilles and generate new window grilles is beneficial to the inheritance and development of traditional Chinese arts. In recent years, the innovative development of generative adversarial networks (GANs) has made it possible to capture the intrinsic distribution of data and generate images that look like real ones. On the basis of researching existing three types of style-based generative adversarial networks (StyleGANs) and adaptive discriminator augmentation (ADA), we use StyleGAN2-ADA to train window grille datasets and generate new window grille images. Finally, multiple image quality evaluation metrics are used to analyze the generated images. The result shows that StyleGAN2-ADA has a good effect on the automatic generation of window grille images. In addition, by comparing the results of different size datasets, we found that the size of dataset has a significant impact on the quality of the generated window grilles.
{"title":"Image generation of traditional Chinese window grilles based on generative adversarial networks","authors":"Chengxi Miao, Jianqin Wu, Jialin Chen, Shiyi Xiong, Lingyue Wang, Qi Wang","doi":"10.1109/CoST57098.2022.00055","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00055","url":null,"abstract":"Window grille is one of the expressions of traditional Chinese folk arts, which has unique stylistic characteristics and rich symbolic meanings. Studying how to extract the style characteristics of window grilles and generate new window grilles is beneficial to the inheritance and development of traditional Chinese arts. In recent years, the innovative development of generative adversarial networks (GANs) has made it possible to capture the intrinsic distribution of data and generate images that look like real ones. On the basis of researching existing three types of style-based generative adversarial networks (StyleGANs) and adaptive discriminator augmentation (ADA), we use StyleGAN2-ADA to train window grille datasets and generate new window grille images. Finally, multiple image quality evaluation metrics are used to analyze the generated images. The result shows that StyleGAN2-ADA has a good effect on the automatic generation of window grille images. In addition, by comparing the results of different size datasets, we found that the size of dataset has a significant impact on the quality of the generated window grilles.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115556516","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 : 2022-08-01DOI: 10.1109/CoST57098.2022.00044
Hui Ren, Meng Li, Xiaochen Shen
In order to solve the problem of rapid switching of space equipment in the cultural complex, this paper combines Moth-Flame optimization Algorithm (MFO) and Dynamic Window Approach (DWA) to realize the hybrid path planning of handling robots in dynamic environments. Compared with the mainstream algorithms, the Moth-Flame optimization algorithm has the best performance. Different paths were classified and judged, and the global path planning based on MFO was proposed. The intersection of the dynamic obstacle and the global path were detected, and the dynamic window approach was used for local path planning in the road section where the collision occurs. Finally the combination of the global path planning and the local dynamic obstacle avoidance was realized. The effect of the hybrid path planning algorithm in the complex environment of the cultural complex had been verified.
{"title":"Obstacle Avoidance Algorithm of Handling Robot in Cultural Complex","authors":"Hui Ren, Meng Li, Xiaochen Shen","doi":"10.1109/CoST57098.2022.00044","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00044","url":null,"abstract":"In order to solve the problem of rapid switching of space equipment in the cultural complex, this paper combines Moth-Flame optimization Algorithm (MFO) and Dynamic Window Approach (DWA) to realize the hybrid path planning of handling robots in dynamic environments. Compared with the mainstream algorithms, the Moth-Flame optimization algorithm has the best performance. Different paths were classified and judged, and the global path planning based on MFO was proposed. The intersection of the dynamic obstacle and the global path were detected, and the dynamic window approach was used for local path planning in the road section where the collision occurs. Finally the combination of the global path planning and the local dynamic obstacle avoidance was realized. The effect of the hybrid path planning algorithm in the complex environment of the cultural complex had been verified.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"2010 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127346366","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 : 2022-08-01DOI: 10.1109/CoST57098.2022.00079
Maoyuan Xu, Tao Jia, Hongyang Zhou, Xiaobin Zhu
The conditional normalized flow model can alleviate the ill-posed nature of super-resolution problems by learning the conditional distribution of the output for a given low-resolution input, which allows multiple predictions for a given low-resolution image. However, the model may generate confusing artifacts in the high-frequency region of the image. While giving a smaller reduction in temperature would solve this problem, it would also smooth out the model's output, which would lead to a decrease in perceptual quality. In this paper, we propose a novel conditional normalizing flow-based distribution adaptation strategy for image Super-Resolution. More specifically, we demonstrate that the part of the latent variable that differs significantly between the latent variables of HR and the Bicubic of LR, contains mainly high-frequency information of the image. We adopt a Bicubic image of LR and a continuous threshold function to evaluate different temperatures in different latent variables. In this way, We can further alleviate generation of confusing artifacts without reducing perceptual quality. Extensive experiments show that our model can outperform state-of-the-art methods and generate more visually favorable results.
{"title":"Rethinking the Adaptiveness of Conditional Flow A Novel Distribution Adaptation Strategy for Image Super-Resolution","authors":"Maoyuan Xu, Tao Jia, Hongyang Zhou, Xiaobin Zhu","doi":"10.1109/CoST57098.2022.00079","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00079","url":null,"abstract":"The conditional normalized flow model can alleviate the ill-posed nature of super-resolution problems by learning the conditional distribution of the output for a given low-resolution input, which allows multiple predictions for a given low-resolution image. However, the model may generate confusing artifacts in the high-frequency region of the image. While giving a smaller reduction in temperature would solve this problem, it would also smooth out the model's output, which would lead to a decrease in perceptual quality. In this paper, we propose a novel conditional normalizing flow-based distribution adaptation strategy for image Super-Resolution. More specifically, we demonstrate that the part of the latent variable that differs significantly between the latent variables of HR and the Bicubic of LR, contains mainly high-frequency information of the image. We adopt a Bicubic image of LR and a continuous threshold function to evaluate different temperatures in different latent variables. In this way, We can further alleviate generation of confusing artifacts without reducing perceptual quality. Extensive experiments show that our model can outperform state-of-the-art methods and generate more visually favorable results.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130131112","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 : 2022-08-01DOI: 10.1109/cost57098.2022.00027
Siyuan Pan, Sijin Song
Current retractable auditoriums, which are mostly used in stadiums and conference rooms, have insufficient mechanical stability and are unsuitable for long time use in the theater. In order to solve these downsides, a new retractable theater auditorium is designed according to the environment of the theater and the theater audience’s need. The retractable theater auditorium has a newly designed main frame module and a newly designed drive and transmission module. SolidWorks is used to conduct three-dimensional modeling and finite element analysis of these new designs. According to the results of finite element analysis, the stability of the design is tested. This new design can greatly minimize the risk of mechanical failure and enhance the structural stability of the retractable auditorium, so as to provide a good watching environment for audiences.
{"title":"Design of the Retractable Theater Auditorium Using SolidWorks","authors":"Siyuan Pan, Sijin Song","doi":"10.1109/cost57098.2022.00027","DOIUrl":"https://doi.org/10.1109/cost57098.2022.00027","url":null,"abstract":"Current retractable auditoriums, which are mostly used in stadiums and conference rooms, have insufficient mechanical stability and are unsuitable for long time use in the theater. In order to solve these downsides, a new retractable theater auditorium is designed according to the environment of the theater and the theater audience’s need. The retractable theater auditorium has a newly designed main frame module and a newly designed drive and transmission module. SolidWorks is used to conduct three-dimensional modeling and finite element analysis of these new designs. According to the results of finite element analysis, the stability of the design is tested. This new design can greatly minimize the risk of mechanical failure and enhance the structural stability of the retractable auditorium, so as to provide a good watching environment for audiences.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133648473","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}
Following the robots, whether virtual characters (VC) will cause the uncanny valley (UV) effect has become a new topic of UV studies, and also a topic that cannot be avoided by VC design and human-VC interaction. Based on the Web of Science core collection (WoSCC), this paper reviews literature on the topics of both the VC and UV (2007-2022) by summarizing the trends and methods research. It groups studies into three categories: verifying the UV and its influencing factors; suggestions for avoiding the UV; possibilities for crossing the UV. We suggest that, under current technological conditions, finding a proper balance between abstraction and high realism to avoid the risk of the UV is a sound choice for VC design, while also providing suggestions for future research.
继机器人之后，虚拟人物(VC)是否会产生恐怖谷效应成为了UV研究的新课题，也是VC设计和人机交互无法回避的课题。本文以Web of Science核心馆藏(WoSCC)为基础，综述了2007-2022年关于VC和UV主题的文献，总结了研究趋势和方法。它将研究分为三类:验证紫外线及其影响因素;避免紫外线的建议;穿越紫外线的可能性。我们认为，在目前的技术条件下，在抽象和高真实感之间找到适当的平衡，以避免紫外线的风险，是VC设计的一个合理选择，同时也为未来的研究提供了建议。
{"title":"Virtual Characters Meet the Uncanny Valley: A Literature Review Based on the Web of Science Core Collection (2007-2022)","authors":"Hui Jiang, Lin Cheng, Dalin Pan, Shuangbin Shi, Zhimeng Wang, Yuevi Xiao","doi":"10.1109/cost57098.2022.00088","DOIUrl":"https://doi.org/10.1109/cost57098.2022.00088","url":null,"abstract":"Following the robots, whether virtual characters (VC) will cause the uncanny valley (UV) effect has become a new topic of UV studies, and also a topic that cannot be avoided by VC design and human-VC interaction. Based on the Web of Science core collection (WoSCC), this paper reviews literature on the topics of both the VC and UV (2007-2022) by summarizing the trends and methods research. It groups studies into three categories: verifying the UV and its influencing factors; suggestions for avoiding the UV; possibilities for crossing the UV. We suggest that, under current technological conditions, finding a proper balance between abstraction and high realism to avoid the risk of the UV is a sound choice for VC design, while also providing suggestions for future research.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116355069","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}
For millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems, several existing beamspace channel estimation schemes for wideband systems tend to assume that the beamspace channels have common support in the frequency domain. In this case, the validity of the results obtained is limited due to the beam squint effect caused by wideband in practice. In this paper, a multiple-sparse Bayesian learning (M-SBL) algorithm is proposed for channel estimation of wideband mmWave MIMO orthogonal frequency division multiplexing (OFDM) systems. In the absence of a common supporting hypothesis, an empirical Bayesian prior is used to estimate a convenient posterior distribution candidate basis vector to estimate the channel. Simulation analysis shows that the proposed method based on M-SBL can accurately estimate the low-complexity beamspace channel and has smaller normalized mean square error (NMSE) performance than the traditional algorithms. The method based on M-SBL still has better estimation performance when the number of users is large and the number of pilots is small.
{"title":"A Sparse Bayesian Learning Algorithm for Channel Estimation in Wideband mmWave MIMO-OFDM Systems","authors":"Sitong Wang, Jing He, Jiali Cao, Y. Guan, Meng Han, Weijia Yu","doi":"10.1109/CoST57098.2022.00068","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00068","url":null,"abstract":"For millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems, several existing beamspace channel estimation schemes for wideband systems tend to assume that the beamspace channels have common support in the frequency domain. In this case, the validity of the results obtained is limited due to the beam squint effect caused by wideband in practice. In this paper, a multiple-sparse Bayesian learning (M-SBL) algorithm is proposed for channel estimation of wideband mmWave MIMO orthogonal frequency division multiplexing (OFDM) systems. In the absence of a common supporting hypothesis, an empirical Bayesian prior is used to estimate a convenient posterior distribution candidate basis vector to estimate the channel. Simulation analysis shows that the proposed method based on M-SBL can accurately estimate the low-complexity beamspace channel and has smaller normalized mean square error (NMSE) performance than the traditional algorithms. The method based on M-SBL still has better estimation performance when the number of users is large and the number of pilots is small.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"595 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116455883","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 : 2022-08-01DOI: 10.1109/cost57098.2022.00080
Bin Wu, Bo Feng, Jun Du, Xiaojia Huang, Liangliang Gao
In today’s life, Online Travel Agency (OTA) platform gets more and more users. Tourists on OTA platform makes much more comments on hotels. Similarly, the authenticity also increases significantly. Real user feedback plays a guiding role in improving the quality of the hotel, but it needs to obtain useful information from the complex comment data and a series of data analysis processes. In this paper, the ‘Bazhuayu’ collector is used to gain data, making pre-processing of the dataset. Using jieba to finish segmentation. The Term Frequency-Inverse Document Frequency algorithm is used to extract keywords, and then the Bag-of-Words model is used to construct the word vector. Finally, subsampled is used to balance the dataset. The support vector machine, Naive Bayes and Long Short-Term Memory neural network model are established to classify and adjust the parameters, compare the classification performance of the models, put forward some suggestions for hotel self optimization and upgrading according to the classification result.
{"title":"Analysis and Application of Tourists’ Sentiment Based on Hotel Comment Data","authors":"Bin Wu, Bo Feng, Jun Du, Xiaojia Huang, Liangliang Gao","doi":"10.1109/cost57098.2022.00080","DOIUrl":"https://doi.org/10.1109/cost57098.2022.00080","url":null,"abstract":"In today’s life, Online Travel Agency (OTA) platform gets more and more users. Tourists on OTA platform makes much more comments on hotels. Similarly, the authenticity also increases significantly. Real user feedback plays a guiding role in improving the quality of the hotel, but it needs to obtain useful information from the complex comment data and a series of data analysis processes. In this paper, the ‘Bazhuayu’ collector is used to gain data, making pre-processing of the dataset. Using jieba to finish segmentation. The Term Frequency-Inverse Document Frequency algorithm is used to extract keywords, and then the Bag-of-Words model is used to construct the word vector. Finally, subsampled is used to balance the dataset. The support vector machine, Naive Bayes and Long Short-Term Memory neural network model are established to classify and adjust the parameters, compare the classification performance of the models, put forward some suggestions for hotel self optimization and upgrading according to the classification result.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114077651","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 : 2022-08-01DOI: 10.1109/CoST57098.2022.00082
Junyi He, Hongyang Zhou, Yan Ma
Deep-learning based Super-Resolution (SR) methods have achieved remarkable performance in many aspects. However, most existing methods are constructed for a single specific scale, and few are multi-scale, lightweight, and have a short running time. To this end, we propose a wavelet-based progressive super-resolution method (WPSR). WPSR could process low and high-frequency information separately by reconstructing different wavelet coefficients in order and could generate multiple SR images at multiple scales sequentially. Experiments demonstrate that our WPSR could outperform existing state-of-the-art methods at multiple scales, especially for ×8 and ×16 scale factors.
{"title":"A Wavelet-based Progressive Super-Resolution Model","authors":"Junyi He, Hongyang Zhou, Yan Ma","doi":"10.1109/CoST57098.2022.00082","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00082","url":null,"abstract":"Deep-learning based Super-Resolution (SR) methods have achieved remarkable performance in many aspects. However, most existing methods are constructed for a single specific scale, and few are multi-scale, lightweight, and have a short running time. To this end, we propose a wavelet-based progressive super-resolution method (WPSR). WPSR could process low and high-frequency information separately by reconstructing different wavelet coefficients in order and could generate multiple SR images at multiple scales sequentially. Experiments demonstrate that our WPSR could outperform existing state-of-the-art methods at multiple scales, especially for ×8 and ×16 scale factors.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132425785","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 : 2022-08-01DOI: 10.1109/CoST57098.2022.00033
Dongpo Guo, Jintao Suo, Qihui Hu, Chao Duan
The advancement of technology promotes the advancement of society. The introduction of technology into educational resources has produced amazing results in learning. Given which core technologies promote the leapfrog development of educational resources, this research sorts out the relationship between educational resources and technologies. The integrated development of educational resources and technology is divided into four stages: verbal instruction, handwritten text, printed text, electrical communication, and digital communication. These four stages make educational resources spread slowly from a small range to a large range of high-speed. The latter utilizes the latest technologies including big data, artificial intelligence, 5G edge cloud computing, metaverse, etc. The role of technology in educational resources has revolutionized traditional education, and student-centered instruction has changed the educational paradigm. With the continuous advancement of technology, future educational resources will become more contextualized and intelligent, which is the basis for teaching students to their aptitude.
{"title":"The Impact of Technology in Educational Resources: a Survey and New Perspectives","authors":"Dongpo Guo, Jintao Suo, Qihui Hu, Chao Duan","doi":"10.1109/CoST57098.2022.00033","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00033","url":null,"abstract":"The advancement of technology promotes the advancement of society. The introduction of technology into educational resources has produced amazing results in learning. Given which core technologies promote the leapfrog development of educational resources, this research sorts out the relationship between educational resources and technologies. The integrated development of educational resources and technology is divided into four stages: verbal instruction, handwritten text, printed text, electrical communication, and digital communication. These four stages make educational resources spread slowly from a small range to a large range of high-speed. The latter utilizes the latest technologies including big data, artificial intelligence, 5G edge cloud computing, metaverse, etc. The role of technology in educational resources has revolutionized traditional education, and student-centered instruction has changed the educational paradigm. With the continuous advancement of technology, future educational resources will become more contextualized and intelligent, which is the basis for teaching students to their aptitude.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130799811","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 : 2022-08-01DOI: 10.1109/cost57098.2022.00084
Siyi Tian, Shuo Lei, Qiming Huang, Anyi Huang
To meet the need for autonomous route planning for tour guide robots in tourist venues, this paper proposes a path planning algorithm based on deep reinforcement learning. The traditional Deep Q-learning Network (DQN) algorithm two defects - overfitting and overestimation. This paper adopts a method that discards the experience pool and treats behavioural values equally, which not only solves the shortcomings of the traditional method, but also satisfies the need for mobile robots to lead tourists on tours through autonomous learning. The paper analyses the principle and process of the method and compares it with the traditional method through experiments to verify that the method outperforms the traditional method in terms of accuracy and speed.
{"title":"The application of path planning algorithm based on deep reinforcement learning for mobile robots","authors":"Siyi Tian, Shuo Lei, Qiming Huang, Anyi Huang","doi":"10.1109/cost57098.2022.00084","DOIUrl":"https://doi.org/10.1109/cost57098.2022.00084","url":null,"abstract":"To meet the need for autonomous route planning for tour guide robots in tourist venues, this paper proposes a path planning algorithm based on deep reinforcement learning. The traditional Deep Q-learning Network (DQN) algorithm two defects - overfitting and overestimation. This paper adopts a method that discards the experience pool and treats behavioural values equally, which not only solves the shortcomings of the traditional method, but also satisfies the need for mobile robots to lead tourists on tours through autonomous learning. The paper analyses the principle and process of the method and compares it with the traditional method through experiments to verify that the method outperforms the traditional method in terms of accuracy and speed.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124309740","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：