The Tool Center Point (TCP) coordinate parameter of the robot end tool is the benchmark of the robot operation. In this paper, a robot TCP automatic calibration algorithm based on binocular vision measurement is proposed. A target which can be recognized by the binocular vision sensor is attached to the robot TCP. The pose transformation between the vision sensor and the robot base is calculated by taking the binocular vision three-dimensional space measurement as the constraint and combining with the multiple translational motions of the robot end tool. After several free rotations of the end tool of the robot, TCP takes the measurement vector of the corresponding binocular vision sensor as the stroke to carry out the hypothetical parallel movement. So that the translated TCP is located at the same point in the space. To calculate the data of the corresponding flange coordinate system after the translation of TCP, and finally infers the position parameters of the TCP of the robot.
{"title":"Automatic Calibration Algorithm of Robot TCP Based on Binocular Vision","authors":"Sujie Liu, Yujun Wu, Chengrong Qiu, Xuefeng Zou","doi":"10.1145/3483845.3483888","DOIUrl":"https://doi.org/10.1145/3483845.3483888","url":null,"abstract":"The Tool Center Point (TCP) coordinate parameter of the robot end tool is the benchmark of the robot operation. In this paper, a robot TCP automatic calibration algorithm based on binocular vision measurement is proposed. A target which can be recognized by the binocular vision sensor is attached to the robot TCP. The pose transformation between the vision sensor and the robot base is calculated by taking the binocular vision three-dimensional space measurement as the constraint and combining with the multiple translational motions of the robot end tool. After several free rotations of the end tool of the robot, TCP takes the measurement vector of the corresponding binocular vision sensor as the stroke to carry out the hypothetical parallel movement. So that the translated TCP is located at the same point in the space. To calculate the data of the corresponding flange coordinate system after the translation of TCP, and finally infers the position parameters of the TCP of the robot.","PeriodicalId":134636,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122700406","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}
In the report of the 19th National Congress of the Communist Party of China, President Xi proposed to "strengthen the use of military forces, accelerate the development of military intelligence, and improve the joint combat capability and global combat capability based on the network information system". Therefore, we should make intelligent traction mechanization stride forward to informatiza-tion, and lay a good foundation for intelligence while realizing mechanization; In the process of in-formatization, we should accelerate the process of intelligence, strive to improve scientific and techno-logical literacy, and consolidate the intellectual foundation of future commanders and fighters. There-fore, military academies should take the initiative to explore a series of reforms in teaching content, cur-riculum system and teaching means, and pay close attention to let artificial intelligence into teaching and classroom. By introducing the concept and theoretical basis of intelligent education in military acade-mies, this paper puts forward the main ideas for the transformation and development of intelligent edu-cation in military academies, and points out the main measures for the transformation and development.
{"title":"Research on The Intelligent Transformation and Development of Military Academy Education","authors":"Chenggong Zhai, Heng Zhang, Yang Huang, Xingguang Yuan, Fei Zhong, Qing-Zheng Xu, Hongsi Xu, Hongri Zhu","doi":"10.1145/3483845.3483862","DOIUrl":"https://doi.org/10.1145/3483845.3483862","url":null,"abstract":"In the report of the 19th National Congress of the Communist Party of China, President Xi proposed to \"strengthen the use of military forces, accelerate the development of military intelligence, and improve the joint combat capability and global combat capability based on the network information system\". Therefore, we should make intelligent traction mechanization stride forward to informatiza-tion, and lay a good foundation for intelligence while realizing mechanization; In the process of in-formatization, we should accelerate the process of intelligence, strive to improve scientific and techno-logical literacy, and consolidate the intellectual foundation of future commanders and fighters. There-fore, military academies should take the initiative to explore a series of reforms in teaching content, cur-riculum system and teaching means, and pay close attention to let artificial intelligence into teaching and classroom. By introducing the concept and theoretical basis of intelligent education in military acade-mies, this paper puts forward the main ideas for the transformation and development of intelligent edu-cation in military academies, and points out the main measures for the transformation and development.","PeriodicalId":134636,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121174906","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}
Baizhen Li, Yibin Zhan, Zhihua Wei, Shikun Huang, Lijun Sun
Dialogue systems, a powerful tool of human-machine interaction, are widely applied in e-commerce, online education, and cellphone assistant, etc. Dialogue state tracking (DST), updating the state of user goals during dialogue, is a core part of task-oriented dialogue systems. Recent research has made progress in low-latency and good-performance DST neural network models, i.e., non-autoregressive dialogue state tracking model (NADST). However, there are still some rooms for improvement in dialogue state tracking. In this paper, we propose following ways to improve the efficiency of NADST: (1) adding shrinkage residual network into fertility prediction; (2) constructing residual connection between different hierarchical attentions; (3) inserting a relative position encoding into state decoder for improving the performance of state prediction. The results of analysis and experiments indicate that the proposed model is the SOTA non-autoregressive method of dialog state tracking.
{"title":"Improved non-autoregressive dialog state tracking model","authors":"Baizhen Li, Yibin Zhan, Zhihua Wei, Shikun Huang, Lijun Sun","doi":"10.1145/3483845.3483880","DOIUrl":"https://doi.org/10.1145/3483845.3483880","url":null,"abstract":"Dialogue systems, a powerful tool of human-machine interaction, are widely applied in e-commerce, online education, and cellphone assistant, etc. Dialogue state tracking (DST), updating the state of user goals during dialogue, is a core part of task-oriented dialogue systems. Recent research has made progress in low-latency and good-performance DST neural network models, i.e., non-autoregressive dialogue state tracking model (NADST). However, there are still some rooms for improvement in dialogue state tracking. In this paper, we propose following ways to improve the efficiency of NADST: (1) adding shrinkage residual network into fertility prediction; (2) constructing residual connection between different hierarchical attentions; (3) inserting a relative position encoding into state decoder for improving the performance of state prediction. The results of analysis and experiments indicate that the proposed model is the SOTA non-autoregressive method of dialog state tracking.","PeriodicalId":134636,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System","volume":"20 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113978817","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}
J. Zhang, Jin Lei, Xinyan Qin, B. Jia, Zhaojun Li, Huidong Li, Bo Li
Power line Inspection is the key to maintain the safety and reliability of the power system. To ensure the safety of power line inspection work, automatic detection technology is widely used in power line inspection. A novel flying-walking power line inspection robot (FPLIR) is proposed in this paper, which has two working modes, flying modes and walking modes. The basic structure of the FPLIR is described, and the dynamic equations of the FPLIR are derived. The stability of FPLIR under wind load is simulated, and simulation data are analyzed by the response surface. The results showed that average centroid displacement is approximately linear with the wind speed, and the relationship between the wind angle and average centroid displacement is nonlinear. When the wind angle is 31° and the wind speed is 14m/s, the FPLIR is most affected by wind. The stability of the FPLIR is analyzed by rigid-flexible coupling simulation and response surface, providing a theoretical basis and technical references to control FPLIR walking in a stable scope.
{"title":"Modeling and Analysis of a Flying-Walking Power Line Inspection Robot","authors":"J. Zhang, Jin Lei, Xinyan Qin, B. Jia, Zhaojun Li, Huidong Li, Bo Li","doi":"10.1145/3483845.3483850","DOIUrl":"https://doi.org/10.1145/3483845.3483850","url":null,"abstract":"Power line Inspection is the key to maintain the safety and reliability of the power system. To ensure the safety of power line inspection work, automatic detection technology is widely used in power line inspection. A novel flying-walking power line inspection robot (FPLIR) is proposed in this paper, which has two working modes, flying modes and walking modes. The basic structure of the FPLIR is described, and the dynamic equations of the FPLIR are derived. The stability of FPLIR under wind load is simulated, and simulation data are analyzed by the response surface. The results showed that average centroid displacement is approximately linear with the wind speed, and the relationship between the wind angle and average centroid displacement is nonlinear. When the wind angle is 31° and the wind speed is 14m/s, the FPLIR is most affected by wind. The stability of the FPLIR is analyzed by rigid-flexible coupling simulation and response surface, providing a theoretical basis and technical references to control FPLIR walking in a stable scope.","PeriodicalId":134636,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124049949","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}
Shruthi Srinarasi, Reshma Ram, S. Raghavendra, A. Patil, S. Rajarajeswari, Manjunath Belgod Lokanath, Rituraj Kabra, Abhishek Singh
The task of measuring sentence similarity deals with computing the likeness between a pair of sentences by adopting Natural Language Processing techniques (Euclidean distance, Jaccard distance, Manhattan distance, etc.) as well as embedding techniques (word2vec, GloVe, Flair, etc.). For the purpose of determining sentence similarity, this paper proposes a novel, ensemble learning approach which uses the WordNet corpus and the Bidirectional Encoder Representations from Transformers (BERT) in order to consider the context of words in sentences while computing the similarity scores. The accuracy of the proposed model is computed by calculating the Pearson and Spearman scores for the sentence pairs from the Sentences Involving Compositional Knowledge (SICK) dataset. On analyzing the results, the proposed approach is observed to outperform existing state-of-the-art semantic textual similarity models since it returns the highest correlation scores. Further, this paper also introduces a possible machine learning approach for the same and evaluates its scope and drawbacks.
{"title":"A Combination of Enhanced WordNet and BERT for Semantic Textual Similarity","authors":"Shruthi Srinarasi, Reshma Ram, S. Raghavendra, A. Patil, S. Rajarajeswari, Manjunath Belgod Lokanath, Rituraj Kabra, Abhishek Singh","doi":"10.1145/3483845.3483898","DOIUrl":"https://doi.org/10.1145/3483845.3483898","url":null,"abstract":"The task of measuring sentence similarity deals with computing the likeness between a pair of sentences by adopting Natural Language Processing techniques (Euclidean distance, Jaccard distance, Manhattan distance, etc.) as well as embedding techniques (word2vec, GloVe, Flair, etc.). For the purpose of determining sentence similarity, this paper proposes a novel, ensemble learning approach which uses the WordNet corpus and the Bidirectional Encoder Representations from Transformers (BERT) in order to consider the context of words in sentences while computing the similarity scores. The accuracy of the proposed model is computed by calculating the Pearson and Spearman scores for the sentence pairs from the Sentences Involving Compositional Knowledge (SICK) dataset. On analyzing the results, the proposed approach is observed to outperform existing state-of-the-art semantic textual similarity models since it returns the highest correlation scores. Further, this paper also introduces a possible machine learning approach for the same and evaluates its scope and drawbacks.","PeriodicalId":134636,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126345598","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}
In recent years, the multi-element phase-controlled transducer used in high intensity focused ultrasound (HIFU) treatment have attracted the attention of many researchers due to their advantages such as adjustable focal length. The phase control and drive system of the multi-element phase-controlled transducer is one of the key factors that determine whether it can be used in clinical treatment. In this paper, a field programmable logic gate array (FPGA), a high-speed digital-to-analog converter and an integrated power amplifier are used to design a phase control and drive system for multi-element phase-controlled transducer for high intensity focused ultrasound treatment. The system has functions of multi-channel output and real-time transmission of delay data of each channel by the personal computer. The actual measurement results show that the peak-to-peak value of the output sine wave signal of each channel of the system can reach 35.3V, the phase resolution can reach 1ns, the delay error is less than 1ns, and the output signal has no high-order harmonic interference, which meets the phase resolution and driving requirements of multi-element phase-controlled transducer applied in clinical treatment.
{"title":"Design of phase control and drive system for phase-controlled transducer based on high intensity focused ultrasound","authors":"Xinyu Guo, Jinxu Tao, Jiaqi Wang","doi":"10.1145/3483845.3483859","DOIUrl":"https://doi.org/10.1145/3483845.3483859","url":null,"abstract":"In recent years, the multi-element phase-controlled transducer used in high intensity focused ultrasound (HIFU) treatment have attracted the attention of many researchers due to their advantages such as adjustable focal length. The phase control and drive system of the multi-element phase-controlled transducer is one of the key factors that determine whether it can be used in clinical treatment. In this paper, a field programmable logic gate array (FPGA), a high-speed digital-to-analog converter and an integrated power amplifier are used to design a phase control and drive system for multi-element phase-controlled transducer for high intensity focused ultrasound treatment. The system has functions of multi-channel output and real-time transmission of delay data of each channel by the personal computer. The actual measurement results show that the peak-to-peak value of the output sine wave signal of each channel of the system can reach 35.3V, the phase resolution can reach 1ns, the delay error is less than 1ns, and the output signal has no high-order harmonic interference, which meets the phase resolution and driving requirements of multi-element phase-controlled transducer applied in clinical treatment.","PeriodicalId":134636,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134646976","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}
In this paper, a novel based on event-triggered anti-disturbance dynamical tracking control is discussed for HFVs with unknown exogenous disturbances.Firstly,the event-triggered mechanism is introduced into the control system.Secondly,the external disturbance is described by T-S model and estimated by disturbance observer.Next,by combining state feedback with disturbance estimation,a PI-type feedback controller is proposed to ensure the HFV models stability and the output tracking error convergence zero.Finally,the simulation result shows the algorithm is effective.Meanwhile,it can obtain satisfactory tracking performance and anti-disturbance tracking performance.
{"title":"Based on Event-Triggered Anti-disturbance Tracking Control for Hypersonic Flight Vehicles with T-S Disturbance Modeling","authors":"Lubing Xu, Yangfei Ye, Yang Yi, W. Zheng","doi":"10.1145/3483845.3483856","DOIUrl":"https://doi.org/10.1145/3483845.3483856","url":null,"abstract":"In this paper, a novel based on event-triggered anti-disturbance dynamical tracking control is discussed for HFVs with unknown exogenous disturbances.Firstly,the event-triggered mechanism is introduced into the control system.Secondly,the external disturbance is described by T-S model and estimated by disturbance observer.Next,by combining state feedback with disturbance estimation,a PI-type feedback controller is proposed to ensure the HFV models stability and the output tracking error convergence zero.Finally,the simulation result shows the algorithm is effective.Meanwhile,it can obtain satisfactory tracking performance and anti-disturbance tracking performance.","PeriodicalId":134636,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131866559","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}
Recent face recognition strategies using deep neural networks (DNNs) mainly focus on the development of new loss functions and the evolution of network architecture. Due to the large capacity of face datasets, such DNN models usually suffer from a long training time. Motivated by freeform optics design, in this paper we propose a novel paradigm of an optical image encoder, DNN-decoder system for improved face recognition. To make the model learn better from unfamiliar samples, we introduce a covariance loss prediction module attached to the network backbone to dynamically adjust the loss objective. The model defines a nonlinear adaptive margin to measure the angular distance between high-dimensional features and utilizes a PID optimizer to update its parameters, resulting in a faster convergence. Empirical results have shown that the proposed model achieves higher training efficiency on public large training datasets such as WebFace42M, MSIMV2 and CASIA-WebFace, and enjoys state-of-the-art recognition performance on popular evaluation datasets including LFW, MegaFace and IJB-C.
{"title":"An Optically-encoded Loss-predictive Framework for Face Recognition Using Nonlinear Adaptive Margin","authors":"Yulin Cai, Zhaoying Sun","doi":"10.1145/3483845.3483884","DOIUrl":"https://doi.org/10.1145/3483845.3483884","url":null,"abstract":"Recent face recognition strategies using deep neural networks (DNNs) mainly focus on the development of new loss functions and the evolution of network architecture. Due to the large capacity of face datasets, such DNN models usually suffer from a long training time. Motivated by freeform optics design, in this paper we propose a novel paradigm of an optical image encoder, DNN-decoder system for improved face recognition. To make the model learn better from unfamiliar samples, we introduce a covariance loss prediction module attached to the network backbone to dynamically adjust the loss objective. The model defines a nonlinear adaptive margin to measure the angular distance between high-dimensional features and utilizes a PID optimizer to update its parameters, resulting in a faster convergence. Empirical results have shown that the proposed model achieves higher training efficiency on public large training datasets such as WebFace42M, MSIMV2 and CASIA-WebFace, and enjoys state-of-the-art recognition performance on popular evaluation datasets including LFW, MegaFace and IJB-C.","PeriodicalId":134636,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133737822","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}
With the characteristics including fuzzy edges, high image noise, low pixels and contrast, X-ray images of weld defect are difficult to be effectively recognized. Various well-known deep network is used for improving image recognition performance, so that researchers pay more attention on weld defects detection by using deep network with stack structure. However, such stack structure shows some disadvantages, such as inaccuracy recognition on confusion feature, low uncertainty-handling efficiency, time-consuming and complex computation. In this paper, a propelled multiple fusion Deep Belief Network (PMF-DBN) structure with Fuzzy Classifiers (FC) is created for weld defect classification and recognition. The proposed PMF-DBN enjoy both the ability of DBN neural representation and the of capability of fuzzy representation in order to meet the requirements of variant image feature processing. Meanwhile, instead of time-consuming fine-tuning training, the outputs feature data of each layer is fused in a propelled way, by which effective feature extraction can be achieved. Experiments on weld defects multi-classification demonstrate effectiveness of the PMF-DBN. Compared with the DBN, PMF-DBN has higher recognition accuracy and better fitting performance.
{"title":"A propelled multiple fusion Deep Belief Network for weld defects detection","authors":"Mengxi Liu, Yingliang Li, Z. Wang","doi":"10.1145/3483845.3483896","DOIUrl":"https://doi.org/10.1145/3483845.3483896","url":null,"abstract":"With the characteristics including fuzzy edges, high image noise, low pixels and contrast, X-ray images of weld defect are difficult to be effectively recognized. Various well-known deep network is used for improving image recognition performance, so that researchers pay more attention on weld defects detection by using deep network with stack structure. However, such stack structure shows some disadvantages, such as inaccuracy recognition on confusion feature, low uncertainty-handling efficiency, time-consuming and complex computation. In this paper, a propelled multiple fusion Deep Belief Network (PMF-DBN) structure with Fuzzy Classifiers (FC) is created for weld defect classification and recognition. The proposed PMF-DBN enjoy both the ability of DBN neural representation and the of capability of fuzzy representation in order to meet the requirements of variant image feature processing. Meanwhile, instead of time-consuming fine-tuning training, the outputs feature data of each layer is fused in a propelled way, by which effective feature extraction can be achieved. Experiments on weld defects multi-classification demonstrate effectiveness of the PMF-DBN. Compared with the DBN, PMF-DBN has higher recognition accuracy and better fitting performance.","PeriodicalId":134636,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114390995","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}
Multi-UAVs cooperative trajectory planning (MUCTP) refers to planning a number of safe, reliable and non-collision from each UAV starting point to the target point in known, partially known or unknown environment. In the planning process, it is necessary to consider the constraints of the UAV itself and the synergistic restriction relationship. Therefore, in order to improve the efficiency of collaborative path planning, a multi-UAVs collaborative path planning algorithm based on key path points is proposed in this paper. In this algorithm, the gene location representation method of individual population was defined, the feasible domain of three-dimensional space was set, and the objective function was constructed by combining the constraint conditions. The experimental results show that the algorithm proposed in this paper has fast convergence speed and strong synergistic ability in multi-UAVs cooperative path planning, which makes the planned track group more reasonable.
{"title":"Coordinated path planning for Multi-UAVs based on critical track points","authors":"Xu Yang, Huang Gang","doi":"10.1145/3483845.3483854","DOIUrl":"https://doi.org/10.1145/3483845.3483854","url":null,"abstract":"Multi-UAVs cooperative trajectory planning (MUCTP) refers to planning a number of safe, reliable and non-collision from each UAV starting point to the target point in known, partially known or unknown environment. In the planning process, it is necessary to consider the constraints of the UAV itself and the synergistic restriction relationship. Therefore, in order to improve the efficiency of collaborative path planning, a multi-UAVs collaborative path planning algorithm based on key path points is proposed in this paper. In this algorithm, the gene location representation method of individual population was defined, the feasible domain of three-dimensional space was set, and the objective function was constructed by combining the constraint conditions. The experimental results show that the algorithm proposed in this paper has fast convergence speed and strong synergistic ability in multi-UAVs cooperative path planning, which makes the planned track group more reasonable.","PeriodicalId":134636,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129391262","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：