Pub Date : 2021-12-31DOI: 10.3390/engproc2021012066
M. Hassan, Arslan Arif
Dispersion is one of the main factors that limit the development of optical fiber communication systems regarding data rate and long distance transmission of the signal. This is because of increases in dispersion with the increase in data rate and distance, resulting in signal degradation. In this work, we propose an optimal dispersion compensated optical fiber system, which is designed on the basis of Q-factor, eye height, and bit error rate. The system operates at a bit rate of 40 Gbps and a distance of 100 km. According to the optimization scheme, the system is simulated using the modulation format Non Return to Zero (NRZ) with uniform and Linear Chirped Apodized Fiber Bragg Grating (LCAFBG) as dispersion compensator. After deciding the Fiber Bragg Grating (FBG) structure, other key parameters are simulated to meet the requirements. The simulation results show that using NRZ modulation format with a LCAFBG Tanh profile gives better performance.
{"title":"Optimal Analysis of 40 Gbps Dispersion Compensated Optical Fiber System","authors":"M. Hassan, Arslan Arif","doi":"10.3390/engproc2021012066","DOIUrl":"https://doi.org/10.3390/engproc2021012066","url":null,"abstract":"Dispersion is one of the main factors that limit the development of optical fiber communication systems regarding data rate and long distance transmission of the signal. This is because of increases in dispersion with the increase in data rate and distance, resulting in signal degradation. In this work, we propose an optimal dispersion compensated optical fiber system, which is designed on the basis of Q-factor, eye height, and bit error rate. The system operates at a bit rate of 40 Gbps and a distance of 100 km. According to the optimization scheme, the system is simulated using the modulation format Non Return to Zero (NRZ) with uniform and Linear Chirped Apodized Fiber Bragg Grating (LCAFBG) as dispersion compensator. After deciding the Fiber Bragg Grating (FBG) structure, other key parameters are simulated to meet the requirements. The simulation results show that using NRZ modulation format with a LCAFBG Tanh profile gives better performance.","PeriodicalId":11748,"journal":{"name":"Engineering Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83805396","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 : 2021-12-30DOI: 10.3390/engproc2021012062
M. Mahboob, Muzaffar Ali, T. Rashid, Rabia Hassan
The energy demand of developing countries increases every year. Large amounts of energy are consumed during the production and transportation of construction materials. Conservation of energy became important in the perspective of limiting carbon emissions into the environment and for decreasing the cost of materials. This article is concentrated on some issues affecting the embodied energy of construction materials mainly in the residential sector. Energy consumption in three various wall structures has been made. The comparison demonstrated that the embodied energy of traditional wall structures is 3-times higher than the energy efficient building materials. CO2 emissions produced by conventional materials and green building materials are 54.96 Kg CO2/m2 and 35.33 Kg CO2/m2, respectively. Finally, the results revealed substantial difference in embodied energy and carbon footprints of materials for which its production involves a high amount of energy consumption.
发展中国家的能源需求每年都在增加。在建筑材料的生产和运输过程中消耗了大量的能源。从限制碳排放到环境和降低材料成本的角度来看，节约能源变得很重要。本文主要研究了住宅领域中影响建筑材料蕴含能源的一些问题。计算了三种不同墙体结构的能耗。对比表明，传统墙体结构的蕴含能量是节能建筑材料的3倍。传统材料和绿色建材的CO2排放量分别为54.96 Kg CO2/m2和35.33 Kg CO2/m2。最后，研究结果显示，生产耗能高的材料，其隐含能量和碳足迹存在显著差异。
{"title":"Assessment of Embodied Energy and Environmental Impact of Sustainable Building Materials and Technologies for Residential Sector","authors":"M. Mahboob, Muzaffar Ali, T. Rashid, Rabia Hassan","doi":"10.3390/engproc2021012062","DOIUrl":"https://doi.org/10.3390/engproc2021012062","url":null,"abstract":"The energy demand of developing countries increases every year. Large amounts of energy are consumed during the production and transportation of construction materials. Conservation of energy became important in the perspective of limiting carbon emissions into the environment and for decreasing the cost of materials. This article is concentrated on some issues affecting the embodied energy of construction materials mainly in the residential sector. Energy consumption in three various wall structures has been made. The comparison demonstrated that the embodied energy of traditional wall structures is 3-times higher than the energy efficient building materials. CO2 emissions produced by conventional materials and green building materials are 54.96 Kg CO2/m2 and 35.33 Kg CO2/m2, respectively. Finally, the results revealed substantial difference in embodied energy and carbon footprints of materials for which its production involves a high amount of energy consumption.","PeriodicalId":11748,"journal":{"name":"Engineering Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78453494","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 : 2021-12-30DOI: 10.3390/engproc2021012063
Ahsan Afraz, M. Shoukath Ali
Currently, banana fiber composites have received wide attention because of their ecofriendly properties. The overall aim of this study is to prove banana fiber as an eco-efficient construction material by checking the behavior of banana fiber-reinforced concrete during flexural loading. The length of fiber is kept 50 mm and a fiber content of 5% by the weight of cement was used for preparing banana fiber reinforced concrete. It is shown from the results that the flexural toughness index (FTI) that has a vital role in sustainable concrete increased while the modulus of rupture (MOR) of banana fiber reinforced concrete decreased as compared to ordinary concrete.
{"title":"Effect of Banana Fiber on Flexural Properties of Fiber Reinforced Concrete for Sustainable Construction","authors":"Ahsan Afraz, M. Shoukath Ali","doi":"10.3390/engproc2021012063","DOIUrl":"https://doi.org/10.3390/engproc2021012063","url":null,"abstract":"Currently, banana fiber composites have received wide attention because of their ecofriendly properties. The overall aim of this study is to prove banana fiber as an eco-efficient construction material by checking the behavior of banana fiber-reinforced concrete during flexural loading. The length of fiber is kept 50 mm and a fiber content of 5% by the weight of cement was used for preparing banana fiber reinforced concrete. It is shown from the results that the flexural toughness index (FTI) that has a vital role in sustainable concrete increased while the modulus of rupture (MOR) of banana fiber reinforced concrete decreased as compared to ordinary concrete.","PeriodicalId":11748,"journal":{"name":"Engineering Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75525984","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 : 2021-12-30DOI: 10.3390/engproc2021013007
Timothé Krauth, J. Morio, X. Olive, Benoit Figuet, Raphael Monstein
Aircraft trajectory generation is a high stakes problem with a wide scope of applications, including collision risk estimation, capacity management and airspace design. Most generation methods focus on optimizing a criterion under constraints to find an optimal path, or on predicting aircraft trajectories. Nevertheless, little in the way of contribution has been made in the field of the artificial generation of random sets of trajectories. This work proposes a new approach to model two-dimensional flows in order to build realistic artificial flight paths. The method has the advantage of being highly intuitive and explainable. Experiments were conducted on go-arounds at Zurich Airport, and the quality of the generated trajectories was evaluated with respect their shape and statistical distribution. The last part of the study explores strategies to extend the work to non-regularly shaped trajectories.
{"title":"Synthetic Aircraft Trajectories Generated with Multivariate Density Models","authors":"Timothé Krauth, J. Morio, X. Olive, Benoit Figuet, Raphael Monstein","doi":"10.3390/engproc2021013007","DOIUrl":"https://doi.org/10.3390/engproc2021013007","url":null,"abstract":"Aircraft trajectory generation is a high stakes problem with a wide scope of applications, including collision risk estimation, capacity management and airspace design. Most generation methods focus on optimizing a criterion under constraints to find an optimal path, or on predicting aircraft trajectories. Nevertheless, little in the way of contribution has been made in the field of the artificial generation of random sets of trajectories. This work proposes a new approach to model two-dimensional flows in order to build realistic artificial flight paths. The method has the advantage of being highly intuitive and explainable. Experiments were conducted on go-arounds at Zurich Airport, and the quality of the generated trajectories was evaluated with respect their shape and statistical distribution. The last part of the study explores strategies to extend the work to non-regularly shaped trajectories.","PeriodicalId":11748,"journal":{"name":"Engineering Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82507154","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 : 2021-12-30DOI: 10.3390/engproc2021012056
Waqas Ahmed, Muhammad Kashif Sattar, Wajeeha Shahnawaz, Umair Saeed, Shahbaz Mehmood Khan, Neha Amon Khan
Artificially intelligent advances such as tech gloves allow handicapped wearers to handle daily matters as normal. A wearable hand-rehabilitation system, i.e., a robotic arm, is engineered with controlled programming to control a disabled hand with features such as movement of fingers and holding items. A life-threatening disease (stroke) is caused when brain cells start to die, causing around 50–70% of patients to face paralysis and disability. People may face after-effects such as reduced use of the hand and limb or a paralyzed hand. Many methods have been introduced to overcome these issues, including therapies, but they are not so reliable when overcoming disability issues. To overcome these issues, we proposed a smart robotic hand that encounters hand disability issues. The smart robotic hand will aid the hands of disabled people by replacing their disabled hand with the smart robotic hand and by controlling the movement of the robot with the movement of the other hand. This can also be helpful for environments where it is not feasible for humans to work, such as in nuclear reactors and in bomb disposal squads. Some people have disabilities of the hand, so this smart robotic hand can also be used in that scenario. The robotic hand is mainly controlled through a flex sensor. By using Arduino, flex sensor outputs are mapped accordingly to the servo motors. The robot is controlled by a wired arrangement.
{"title":"Wearable Hand-Rehabilitation System with Soft Gloves for Patient with Face Paralysis and Disability","authors":"Waqas Ahmed, Muhammad Kashif Sattar, Wajeeha Shahnawaz, Umair Saeed, Shahbaz Mehmood Khan, Neha Amon Khan","doi":"10.3390/engproc2021012056","DOIUrl":"https://doi.org/10.3390/engproc2021012056","url":null,"abstract":"Artificially intelligent advances such as tech gloves allow handicapped wearers to handle daily matters as normal. A wearable hand-rehabilitation system, i.e., a robotic arm, is engineered with controlled programming to control a disabled hand with features such as movement of fingers and holding items. A life-threatening disease (stroke) is caused when brain cells start to die, causing around 50–70% of patients to face paralysis and disability. People may face after-effects such as reduced use of the hand and limb or a paralyzed hand. Many methods have been introduced to overcome these issues, including therapies, but they are not so reliable when overcoming disability issues. To overcome these issues, we proposed a smart robotic hand that encounters hand disability issues. The smart robotic hand will aid the hands of disabled people by replacing their disabled hand with the smart robotic hand and by controlling the movement of the robot with the movement of the other hand. This can also be helpful for environments where it is not feasible for humans to work, such as in nuclear reactors and in bomb disposal squads. Some people have disabilities of the hand, so this smart robotic hand can also be used in that scenario. The robotic hand is mainly controlled through a flex sensor. By using Arduino, flex sensor outputs are mapped accordingly to the servo motors. The robot is controlled by a wired arrangement.","PeriodicalId":11748,"journal":{"name":"Engineering Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80234303","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 : 2021-12-30DOI: 10.3390/engproc2021012057
Jawad Fareed, M. Zafar, M. Saleem, R. Malik, Muddassir Ali
In the current study, cellulose acetate (CA)/cellulose triacetate (CTA) nanocomposite membranes blended with zirconium dioxide (ZrO2) are prepared via phase inversion for pervaporation desalination performance. ZrO2 nanoparticles are added to enhance the hydrophilicity and porosity of the nanocomposite membranes. The fabricated nanocomposite membranes are characterized by SEM, FTIR, TGA, and DSC to study the surface morphology, chemical composition, thermal stability and strength. Nanocomposite membranes’ performance for pervaporation desalination is assessed as a function of feed concentration. Pervaporation results revealed that the nanocomposite membrane consisting of 2% ZrO2 achieved a maximum water flux of 6.5 kg/m2h, whereas the salt rejection was about 99.8%.
{"title":"Cellulose Blended Membranes for High-Salinity Water Pervaporation Desalination","authors":"Jawad Fareed, M. Zafar, M. Saleem, R. Malik, Muddassir Ali","doi":"10.3390/engproc2021012057","DOIUrl":"https://doi.org/10.3390/engproc2021012057","url":null,"abstract":"In the current study, cellulose acetate (CA)/cellulose triacetate (CTA) nanocomposite membranes blended with zirconium dioxide (ZrO2) are prepared via phase inversion for pervaporation desalination performance. ZrO2 nanoparticles are added to enhance the hydrophilicity and porosity of the nanocomposite membranes. The fabricated nanocomposite membranes are characterized by SEM, FTIR, TGA, and DSC to study the surface morphology, chemical composition, thermal stability and strength. Nanocomposite membranes’ performance for pervaporation desalination is assessed as a function of feed concentration. Pervaporation results revealed that the nanocomposite membrane consisting of 2% ZrO2 achieved a maximum water flux of 6.5 kg/m2h, whereas the salt rejection was about 99.8%.","PeriodicalId":11748,"journal":{"name":"Engineering Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83195059","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 : 2021-12-29DOI: 10.3390/engproc2021012048
Ihsan Ahmed, Wasif Muhammad, Ali Asghar, M. J. Irshad
The quick, simultaneous movements of both eyes in the same direction is called a saccade, and the process of developing an internal model for the eyes’ movement-control based on visual stimuli is called saccade learning. All humans use this type of eye motion to bring salient objects to the foveal locations of the retina, even if the objects are located randomly in the surrounding environment. To begin with, infants are not able to perform this type of eye motion, but sensory information motivates them to start learning saccadic behavior. In this paper, a sensory prediction-error-based intrinsically motivated model is proposed for learning saccadic eye movements, and this approach is more consistent with biological systems for saccade learning. Predicted Coding/Biased Competition using Divisive Input Modulation (PC/BC-DIM) network is used for saccade learning using sensory prediction errors. The quantification of sensory prediction errors provides an intrinsic reward. A simulated humanoid agent, iCub, is used to assess and quantify the performance of the proposed model. The performance metrics used for this purpose are percentage mean post-saccadic distance and standard deviation. The mean post-saccadic distance for the proposed model was less than 1°, which is biologically plausible.
{"title":"Predication-Error-Based Intrinsically Motivated Saccade Learning","authors":"Ihsan Ahmed, Wasif Muhammad, Ali Asghar, M. J. Irshad","doi":"10.3390/engproc2021012048","DOIUrl":"https://doi.org/10.3390/engproc2021012048","url":null,"abstract":"The quick, simultaneous movements of both eyes in the same direction is called a saccade, and the process of developing an internal model for the eyes’ movement-control based on visual stimuli is called saccade learning. All humans use this type of eye motion to bring salient objects to the foveal locations of the retina, even if the objects are located randomly in the surrounding environment. To begin with, infants are not able to perform this type of eye motion, but sensory information motivates them to start learning saccadic behavior. In this paper, a sensory prediction-error-based intrinsically motivated model is proposed for learning saccadic eye movements, and this approach is more consistent with biological systems for saccade learning. Predicted Coding/Biased Competition using Divisive Input Modulation (PC/BC-DIM) network is used for saccade learning using sensory prediction errors. The quantification of sensory prediction errors provides an intrinsic reward. A simulated humanoid agent, iCub, is used to assess and quantify the performance of the proposed model. The performance metrics used for this purpose are percentage mean post-saccadic distance and standard deviation. The mean post-saccadic distance for the proposed model was less than 1°, which is biologically plausible.","PeriodicalId":11748,"journal":{"name":"Engineering Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87220852","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 : 2021-12-29DOI: 10.3390/engproc2021012058
Mohammad Zeagham, Tariq M. Jadoon, M. Qureshi, B. Qureshi, S. Sabir
Nanofluids are considered as the next generation of dielectric fluids due to their higher thermal conductivity and dielectric properties. In this investigation, locally produced ester oils, such as rice bran oil (RBO) and jatropha oil (JO), were compared with mineral oil (MO). Initially, hydrophilic SiO2 nano particles were used to prepare nanofluids using RBO and MO. However, results showed that with loading of nanoparticles (NPs) up to 0.075 g/L, the dielectric strength (DS) of MO based NFs increased but decreased drastically with further increase in loading as these suffered agglomeration and sedimentation in less than 72 h. To overcome this drawback, NPs were functionalized under plasma discharge. These efforts also did not yield many favorable results. Instead, hydrophobic fumed silica NPs grafted with hexamethyldi-siloxane (HMDS) were utilized for further study. Plasma treated NFs exhibited improved DS, as well as excellent dispersibility and stability.
{"title":"In Search of a “Stable Green Nanofluid” for Applications in High Voltage Equipment","authors":"Mohammad Zeagham, Tariq M. Jadoon, M. Qureshi, B. Qureshi, S. Sabir","doi":"10.3390/engproc2021012058","DOIUrl":"https://doi.org/10.3390/engproc2021012058","url":null,"abstract":"Nanofluids are considered as the next generation of dielectric fluids due to their higher thermal conductivity and dielectric properties. In this investigation, locally produced ester oils, such as rice bran oil (RBO) and jatropha oil (JO), were compared with mineral oil (MO). Initially, hydrophilic SiO2 nano particles were used to prepare nanofluids using RBO and MO. However, results showed that with loading of nanoparticles (NPs) up to 0.075 g/L, the dielectric strength (DS) of MO based NFs increased but decreased drastically with further increase in loading as these suffered agglomeration and sedimentation in less than 72 h. To overcome this drawback, NPs were functionalized under plasma discharge. These efforts also did not yield many favorable results. Instead, hydrophobic fumed silica NPs grafted with hexamethyldi-siloxane (HMDS) were utilized for further study. Plasma treated NFs exhibited improved DS, as well as excellent dispersibility and stability.","PeriodicalId":11748,"journal":{"name":"Engineering Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86757639","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 : 2021-12-29DOI: 10.3390/engproc2021012052
Arslan Munir, Ali Ahmad, Muhammad Tahseen Sadiq, Ali Sarosh, Ghulam Abbas, Asad Ali
Recent development shows that carbon-based composites are proving to be the most promising materials in hydrogen energy production, storage and conversion applications. In this study, composites of the copper-based metal-organic framework with different ratios of graphite oxide have been prepared for hydrogen storage application. The developed materials are characterized by X-ray diffraction (XRD), gravimetric thermal analysis (TGA), scanning electron microscopy (SEM) and BET. The newly developed composites have an improved crystalline structure and an increased surface area. The results of the experiment showed that the composite material MOF/GO 20% can store 6.12% of hydrogen at −40 °C.
{"title":"Synthesis and Characterization of Carbon-Based Composites for Hydrogen Storage Application","authors":"Arslan Munir, Ali Ahmad, Muhammad Tahseen Sadiq, Ali Sarosh, Ghulam Abbas, Asad Ali","doi":"10.3390/engproc2021012052","DOIUrl":"https://doi.org/10.3390/engproc2021012052","url":null,"abstract":"Recent development shows that carbon-based composites are proving to be the most promising materials in hydrogen energy production, storage and conversion applications. In this study, composites of the copper-based metal-organic framework with different ratios of graphite oxide have been prepared for hydrogen storage application. The developed materials are characterized by X-ray diffraction (XRD), gravimetric thermal analysis (TGA), scanning electron microscopy (SEM) and BET. The newly developed composites have an improved crystalline structure and an increased surface area. The results of the experiment showed that the composite material MOF/GO 20% can store 6.12% of hydrogen at −40 °C.","PeriodicalId":11748,"journal":{"name":"Engineering Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83685376","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 : 2021-12-29DOI: 10.3390/engproc2021012047
Jamal Shams Khanzada, Wasif Muhammad, M. J. Irshad
Quadcopters are finding their place in everything from transportation, delivery, hospitals, and to homes in almost every part of daily life. In places where human intervention for quadcopter flight control is impossible, it becomes necessary to equip drones with intelligent autopilot systems so that they can make decisions on their own. All previous reinforcement learning (RL)-based efforts for quadcopter flight control in complex, dynamic, and unstructured environments remained unsuccessful during the training phase in avoiding the trend of catastrophic failures by naturally unstable quadcopters. In this work, we propose a complementary approach for quadcopter flight control using prediction error as an effective control policy reward in the sensory space instead of rewards from unstable action spaces alike in conventional RL approaches. The proposed predictive coding biased competition using divisive input modulation (PC/BC-DIM) neural network learns prediction error-based flight control policy without physically actuating quadcopter propellers, which ensures its safety during training. The proposed network learned flight control policy without any physical flights, which reduced the training time to almost zero. The simulation results showed that the trained agent reached the destination accurately. For 20 quadcopter flight trails, the average path deviation from the ground truth was 1.495 and the root mean square (RMS) of the goal reached 1.708.
{"title":"Prediction Error-Based Action Policy Learning for Quadcopter Flight Control","authors":"Jamal Shams Khanzada, Wasif Muhammad, M. J. Irshad","doi":"10.3390/engproc2021012047","DOIUrl":"https://doi.org/10.3390/engproc2021012047","url":null,"abstract":"Quadcopters are finding their place in everything from transportation, delivery, hospitals, and to homes in almost every part of daily life. In places where human intervention for quadcopter flight control is impossible, it becomes necessary to equip drones with intelligent autopilot systems so that they can make decisions on their own. All previous reinforcement learning (RL)-based efforts for quadcopter flight control in complex, dynamic, and unstructured environments remained unsuccessful during the training phase in avoiding the trend of catastrophic failures by naturally unstable quadcopters. In this work, we propose a complementary approach for quadcopter flight control using prediction error as an effective control policy reward in the sensory space instead of rewards from unstable action spaces alike in conventional RL approaches. The proposed predictive coding biased competition using divisive input modulation (PC/BC-DIM) neural network learns prediction error-based flight control policy without physically actuating quadcopter propellers, which ensures its safety during training. The proposed network learned flight control policy without any physical flights, which reduced the training time to almost zero. The simulation results showed that the trained agent reached the destination accurately. For 20 quadcopter flight trails, the average path deviation from the ground truth was 1.495 and the root mean square (RMS) of the goal reached 1.708.","PeriodicalId":11748,"journal":{"name":"Engineering Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84771113","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：