Pub Date : 2020-10-11DOI: 10.1109/SMC42975.2020.9283330
Mayank Chaudhari, S. Sarkar, Divyasheel Sharma
Among all the transportation systems that people use, the public traffic-ways are most common and dangerous resulting in a significant number of fatalities per day worldwide. Statistics have shown that the mortality rates related to traffic accident are more among youth. Although various road safety strategies and rules are developed by the government and law-enforcement agencies to combat the situation, these methods mainly target design, operation, and usability of traffic-ways. Most of the recent data-driven analysis papers model the traffic patterns or predict accidents from the past data. In this paper, we consider a comprehensive, year long fatality analysis reporting system (FARS) data to analyze the role of various factors related to humans, weather and physical conditions (e.g., road surface, light condition etc.) involved in traffic accidents. We build an intelligent risk prediction model that can help decision-makers to ensure road safety. The proposed model estimates (i.) the accident risk over a future time frame, and (ii.) the risk associated with the drivers present on the traffic-way based on the driver’s behavior, history, environmental conditions and physical conditions related to traffic-way.
{"title":"Analyzing Risky Behavior in Traffic Accidents","authors":"Mayank Chaudhari, S. Sarkar, Divyasheel Sharma","doi":"10.1109/SMC42975.2020.9283330","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283330","url":null,"abstract":"Among all the transportation systems that people use, the public traffic-ways are most common and dangerous resulting in a significant number of fatalities per day worldwide. Statistics have shown that the mortality rates related to traffic accident are more among youth. Although various road safety strategies and rules are developed by the government and law-enforcement agencies to combat the situation, these methods mainly target design, operation, and usability of traffic-ways. Most of the recent data-driven analysis papers model the traffic patterns or predict accidents from the past data. In this paper, we consider a comprehensive, year long fatality analysis reporting system (FARS) data to analyze the role of various factors related to humans, weather and physical conditions (e.g., road surface, light condition etc.) involved in traffic accidents. We build an intelligent risk prediction model that can help decision-makers to ensure road safety. The proposed model estimates (i.) the accident risk over a future time frame, and (ii.) the risk associated with the drivers present on the traffic-way based on the driver’s behavior, history, environmental conditions and physical conditions related to traffic-way.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"3 1","pages":"464-471"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72785159","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 : 2020-10-11DOI: 10.1109/SMC42975.2020.9283304
Mihai David Marin, Elena Mocanu, C. Seifert
Radiologists are required to write free paper text reports for breast screenings in order to assign cancer diagnoses in a later step. The current procedure requires considerable time and needs efficiency. In this paper, to streamline the writing process and keep up with the specific vocabulary, a word prediction tool using neural language models was developed. Consequently, challenges as different languages (English, Dutch), small data sizes and low computational power have been overcome by introducing a novel English-Dutch Radiology Language Modelling process. After defining model architectures, the process involves data preparation, bilevel hyperparameters optimization, configuration transfer and evaluation. The model is able to improve the current workflow and successfully meet the computational constraints, based on both an intrinsic and extrinsic evaluation. Given its flexibility, the model opens the door for future research involving other languages and also an extensive set of real-world applications.
{"title":"Effectiveness of neural language models for word prediction of textual mammography reports","authors":"Mihai David Marin, Elena Mocanu, C. Seifert","doi":"10.1109/SMC42975.2020.9283304","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283304","url":null,"abstract":"Radiologists are required to write free paper text reports for breast screenings in order to assign cancer diagnoses in a later step. The current procedure requires considerable time and needs efficiency. In this paper, to streamline the writing process and keep up with the specific vocabulary, a word prediction tool using neural language models was developed. Consequently, challenges as different languages (English, Dutch), small data sizes and low computational power have been overcome by introducing a novel English-Dutch Radiology Language Modelling process. After defining model architectures, the process involves data preparation, bilevel hyperparameters optimization, configuration transfer and evaluation. The model is able to improve the current workflow and successfully meet the computational constraints, based on both an intrinsic and extrinsic evaluation. Given its flexibility, the model opens the door for future research involving other languages and also an extensive set of real-world applications.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"50 1","pages":"1596-1603"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73194640","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 : 2020-10-11DOI: 10.1109/SMC42975.2020.9283290
Yuki Okafuji, Toshihito Sugiura, T. Wada
Understanding the relationship between driving behavior and visual information is an important issue in order to understand driving behavior holistically. In this study, we constructed a driver model that reproduces the driver’s steering behavior from visual information based on the Convolutional Neural Network (CNN) with human physical characteristics. We obtained the driving behavior in a simulator study to train the proposed CNN model. Which region in the visual field influencing drivers’ steering behavior was analyzed using the results of the feature maps generated by the trained CNN model and the driver’s gaze behavior. The results indicate that the drivers perform steering action using the information within 20 degrees from the gaze point.
{"title":"Preliminary Investigation of Visual Information Influencing Driver’s Steering Control based on CNN","authors":"Yuki Okafuji, Toshihito Sugiura, T. Wada","doi":"10.1109/SMC42975.2020.9283290","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283290","url":null,"abstract":"Understanding the relationship between driving behavior and visual information is an important issue in order to understand driving behavior holistically. In this study, we constructed a driver model that reproduces the driver’s steering behavior from visual information based on the Convolutional Neural Network (CNN) with human physical characteristics. We obtained the driving behavior in a simulator study to train the proposed CNN model. Which region in the visual field influencing drivers’ steering behavior was analyzed using the results of the feature maps generated by the trained CNN model and the driver’s gaze behavior. The results indicate that the drivers perform steering action using the information within 20 degrees from the gaze point.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"88 5 1","pages":"2263-2268"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73425273","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 : 2020-10-11DOI: 10.1109/SMC42975.2020.9282903
Mayank B. Thacker, D. Buchanan
The CMUT devices presented in this paper were fabricated using a commercially available MEMSCAPs PolyMUMPs process. The moveable membrane evolves from the available single layer polysilicon. COMSOL simulations were used to model and investigate the effects of a 140 μm and 105 μm radius membranes that are 1.5 μm and 2 μm thick respectively. The results for two different structures designed to operate below 350 kHz are demonstrated in this work. Simulations show that both the devices presented show displacement of over 40 nm. The device snap shut was observed beyond 40 V. This frequency range is suitable to have high SNR and accurate distance measurements. Reducing the size of CMUT devices for the proposed frequency range was a challenge, sorted in this paper. A device capable to generate ultrasound close to 50kHZ is also presented.
{"title":"Design and Characterization of low frequency Capacitive Micromachined Ultrasonic Transducer (CMUT)","authors":"Mayank B. Thacker, D. Buchanan","doi":"10.1109/SMC42975.2020.9282903","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9282903","url":null,"abstract":"The CMUT devices presented in this paper were fabricated using a commercially available MEMSCAPs PolyMUMPs process. The moveable membrane evolves from the available single layer polysilicon. COMSOL simulations were used to model and investigate the effects of a 140 μm and 105 μm radius membranes that are 1.5 μm and 2 μm thick respectively. The results for two different structures designed to operate below 350 kHz are demonstrated in this work. Simulations show that both the devices presented show displacement of over 40 nm. The device snap shut was observed beyond 40 V. This frequency range is suitable to have high SNR and accurate distance measurements. Reducing the size of CMUT devices for the proposed frequency range was a challenge, sorted in this paper. A device capable to generate ultrasound close to 50kHZ is also presented.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"70 1","pages":"2876-2881"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75574665","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 : 2020-10-11DOI: 10.1109/SMC42975.2020.9283389
Hiroya Kikuchi, H. Mukaidani, Ramasamy Saravanakumar, W. Zhuang
In this paper, a robust Pareto suboptimal strategy for an uncertain susceptible-infected-recovered (SIR) model with state delay is investigated, based on the static output feedback (SOF). After linearizing the original nonlinear SIR model, a sufficient condition for the existence of a proposed strategy set is derived in terms of high-order cross-coupled matrix equations (HCMEs). Using the guaranteed cost control technique, both robust stability and existence of the cost bound are attained. To avoid high complexity of directly solving the HCMEs, a recursive algorithm based on the linear matrix inequality (LMI) is presented. Finally, a practical SIR time-delay model is used to demonstrate the effectiveness and reliability of the proposed strategy.
{"title":"Robust Vaccination Strategy based on Dynamic Game for Uncertain SIR Time-Delay Model","authors":"Hiroya Kikuchi, H. Mukaidani, Ramasamy Saravanakumar, W. Zhuang","doi":"10.1109/SMC42975.2020.9283389","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283389","url":null,"abstract":"In this paper, a robust Pareto suboptimal strategy for an uncertain susceptible-infected-recovered (SIR) model with state delay is investigated, based on the static output feedback (SOF). After linearizing the original nonlinear SIR model, a sufficient condition for the existence of a proposed strategy set is derived in terms of high-order cross-coupled matrix equations (HCMEs). Using the guaranteed cost control technique, both robust stability and existence of the cost bound are attained. To avoid high complexity of directly solving the HCMEs, a recursive algorithm based on the linear matrix inequality (LMI) is presented. Finally, a practical SIR time-delay model is used to demonstrate the effectiveness and reliability of the proposed strategy.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"31 1","pages":"3427-3432"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74408558","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 : 2020-10-11DOI: 10.1109/SMC42975.2020.9282850
H. Ishibuchi, Lie Meng Pang, Ke Shang
In general, performance comparison results of optimization algorithms depend on the parameter specifications in each algorithm. For fair comparison, it may be needed to use the best specifications for each algorithm instead of using the same specifications for all algorithms. This is because each algorithm has its best specifications. However, in the evolutionary multi-objective optimization (EMO) field, performance comparison has usually been performed under the same parameter specifications for all algorithms. Especially, the same population size has always been used. In this paper, we discuss this practice from a viewpoint of fair comparison of EMO algorithms. First, we demonstrate that performance comparison results depend on the population size. Next, we explain a new trend of performance comparison where each algorithm is evaluated by selecting a pre-specified number of solutions from the examined solutions (i.e., by selecting a solution subset with a pre-specified size). Then, we discuss the selected subset size specification. Through computational experiments, we show that performance comparison results do not strongly depend on the selected subset size while they depend on the population size.
{"title":"Population Size Specification for Fair Comparison of Multi-objective Evolutionary Algorithms","authors":"H. Ishibuchi, Lie Meng Pang, Ke Shang","doi":"10.1109/SMC42975.2020.9282850","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9282850","url":null,"abstract":"In general, performance comparison results of optimization algorithms depend on the parameter specifications in each algorithm. For fair comparison, it may be needed to use the best specifications for each algorithm instead of using the same specifications for all algorithms. This is because each algorithm has its best specifications. However, in the evolutionary multi-objective optimization (EMO) field, performance comparison has usually been performed under the same parameter specifications for all algorithms. Especially, the same population size has always been used. In this paper, we discuss this practice from a viewpoint of fair comparison of EMO algorithms. First, we demonstrate that performance comparison results depend on the population size. Next, we explain a new trend of performance comparison where each algorithm is evaluated by selecting a pre-specified number of solutions from the examined solutions (i.e., by selecting a solution subset with a pre-specified size). Then, we discuss the selected subset size specification. Through computational experiments, we show that performance comparison results do not strongly depend on the selected subset size while they depend on the population size.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"35 1","pages":"1095-1102"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75106546","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 : 2020-10-11DOI: 10.1109/SMC42975.2020.9283014
Masayuki Kobayashi, Satoshi Arai, T. Nagao
Although convolutional neural networks (CNNs) have significantly evolved and demonstrated outstanding performance, their uninterpretable nature is still considered to be a major problem. In this study, we take a closer look at CNN interpretability and propose a new method called Evolutionary Generative Contribution Mappings (EGCM). In EGCM, CNN models incorporate both a classification mechanism and an interpreting mechanism in an end-to-end training process. Specifically, the network generates the class contribution maps, which indicate the discriminative regions for the model to identify a specific class. Additionally, these maps can be directly used for classification tasks; all that is needed is a global average pooling and a softmax function. The network is represented by a directed acyclic graph and optimized using a genetic algorithm. Architecture search enables EGCM to deliver reasonable classification performance while maintaining high interpretability. We apply the EGCM framework on several datasets and empirically demonstrate that the EGCM not only achieves excellent classification performance but also maintains high interpretability.
{"title":"Evolutionary Generative Contribution Mappings","authors":"Masayuki Kobayashi, Satoshi Arai, T. Nagao","doi":"10.1109/SMC42975.2020.9283014","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283014","url":null,"abstract":"Although convolutional neural networks (CNNs) have significantly evolved and demonstrated outstanding performance, their uninterpretable nature is still considered to be a major problem. In this study, we take a closer look at CNN interpretability and propose a new method called Evolutionary Generative Contribution Mappings (EGCM). In EGCM, CNN models incorporate both a classification mechanism and an interpreting mechanism in an end-to-end training process. Specifically, the network generates the class contribution maps, which indicate the discriminative regions for the model to identify a specific class. Additionally, these maps can be directly used for classification tasks; all that is needed is a global average pooling and a softmax function. The network is represented by a directed acyclic graph and optimized using a genetic algorithm. Architecture search enables EGCM to deliver reasonable classification performance while maintaining high interpretability. We apply the EGCM framework on several datasets and empirically demonstrate that the EGCM not only achieves excellent classification performance but also maintains high interpretability.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"34 1","pages":"1657-1664"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76510285","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 : 2020-10-11DOI: 10.1109/SMC42975.2020.9283109
Nursefa Zengin, Halit Zengin, B. Fidan, A. Khajepour
Tire-road friction coefficient is an essential parameter in vehicle safety control systems. In particular, friction information is required by antilock braking systems (ABS) during deceleration and by traction control systems (TCS) during acceleration. The characteristic of the force acting on the tires has an extremum, which is dependent in the road condition. This paper develops a recursive least squares (RLS) based extremum seeking algorithm that estimates the optimum slip ratio on-line to produce maximum deceleration/acceleration. Results of simulation studies in both Matlab and CarSim environments are presented to illustrate the effectiveness of the developed algorithm and numerically compare with gradient based estimation.
{"title":"Slip Ratio Optimization in Vehicle Safety Control Systems Using Least-Squares Based Adaptive Extremum Seeking","authors":"Nursefa Zengin, Halit Zengin, B. Fidan, A. Khajepour","doi":"10.1109/SMC42975.2020.9283109","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283109","url":null,"abstract":"Tire-road friction coefficient is an essential parameter in vehicle safety control systems. In particular, friction information is required by antilock braking systems (ABS) during deceleration and by traction control systems (TCS) during acceleration. The characteristic of the force acting on the tires has an extremum, which is dependent in the road condition. This paper develops a recursive least squares (RLS) based extremum seeking algorithm that estimates the optimum slip ratio on-line to produce maximum deceleration/acceleration. Results of simulation studies in both Matlab and CarSim environments are presented to illustrate the effectiveness of the developed algorithm and numerically compare with gradient based estimation.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"129 11 1","pages":"1445-1450"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77681025","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 : 2020-10-11DOI: 10.1109/SMC42975.2020.9283034
Akshay Ajagekar, F. You
Quantum computing and deep learning methods hold great promise to open up a new era of computing and have been receiving significant attention recently. This paper presents quantum computing (QC) based deep learning methods for fault diagnosis that are capable of overcoming the computational challenges faced by conventional techniques performed on classical computers. The shortcomings of such classical data-driven techniques are addressed by the proposed QC-based fault diagnosis model. A quantum computing assisted generative training process followed by supervised discriminative training is used to train this model. The applicability of proposed model and methods is demonstrated by applying them to process monitoring of Tennessee Eastman (TE) process. The proposed QC-based deep learning approach enjoys superior performance with an average fault diagnosis rate of 80% and tremendously low false alarm rates for the TE process.
{"title":"A Deep Learning Approach for Fault Detection and Diagnosis of Industrial Processes using Quantum Computing","authors":"Akshay Ajagekar, F. You","doi":"10.1109/SMC42975.2020.9283034","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283034","url":null,"abstract":"Quantum computing and deep learning methods hold great promise to open up a new era of computing and have been receiving significant attention recently. This paper presents quantum computing (QC) based deep learning methods for fault diagnosis that are capable of overcoming the computational challenges faced by conventional techniques performed on classical computers. The shortcomings of such classical data-driven techniques are addressed by the proposed QC-based fault diagnosis model. A quantum computing assisted generative training process followed by supervised discriminative training is used to train this model. The applicability of proposed model and methods is demonstrated by applying them to process monitoring of Tennessee Eastman (TE) process. The proposed QC-based deep learning approach enjoys superior performance with an average fault diagnosis rate of 80% and tremendously low false alarm rates for the TE process.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"26 1","pages":"2345-2350"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79986772","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 : 2020-10-11DOI: 10.1109/SMC42975.2020.9282868
F. Parisi, A. M. Mangini, M. P. Fanti
In recent years, the employment of robots has become a value-added entity in the industries in gaining their competitive advantages. Moreover, thanks to Industry 4.0 paradigm, many production tasks have grown in terms of dimensionality, complexity and higher precision and need to be performed by robots. Among them, the palletizing task is still highly dependent on the particular problem to solve, and its optimization needs to be performed basing on the ground condition. In this paper a palletizing task problem performed by a robotic manipulator is studied. More in detail, some objects have to be transported from a pre-determined storage area to a delivery area. In the storage area the objects are stacked one on the other in columns, while in the delivery area the robotic manipulator poses the objects in horizontal levels, one over another. The process is optimized by minimizing the total distance travelled by the robotic manipulator to transport all the objects from the storage area to the delivery area. An Integer Linear Programming (ILP) problem is formalized and tested by simulations and experimental results.
{"title":"Optimal Trajectory Planning for a Robotic Manipulator Palletizing Tasks *","authors":"F. Parisi, A. M. Mangini, M. P. Fanti","doi":"10.1109/SMC42975.2020.9282868","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9282868","url":null,"abstract":"In recent years, the employment of robots has become a value-added entity in the industries in gaining their competitive advantages. Moreover, thanks to Industry 4.0 paradigm, many production tasks have grown in terms of dimensionality, complexity and higher precision and need to be performed by robots. Among them, the palletizing task is still highly dependent on the particular problem to solve, and its optimization needs to be performed basing on the ground condition. In this paper a palletizing task problem performed by a robotic manipulator is studied. More in detail, some objects have to be transported from a pre-determined storage area to a delivery area. In the storage area the objects are stacked one on the other in columns, while in the delivery area the robotic manipulator poses the objects in horizontal levels, one over another. The process is optimized by minimizing the total distance travelled by the robotic manipulator to transport all the objects from the storage area to the delivery area. An Integer Linear Programming (ILP) problem is formalized and tested by simulations and experimental results.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"7 1","pages":"2901-2906"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81927965","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：