This paper presents the method of trajectory planning for mobile manipulators considering limitations resulting from capabilities of robotic system actuators. The fulfillment of control constraints is achieved by introducing virtual control scaling of the robot trajectory in the limited periods of time. Such an approach allows researchers to obtain the trajectories fulfilling control constraints without significantly increasing the time of task execution. The proposed method generates sub-optimal trajectories maximizing the manipulability measure of the robot arm, preserves mechanical and collision avoidance limitations and can be used in real-time trajectory planning. The effectiveness of the presented solution is confirmed by computer simulations involving a mobile manipulator with parameters corresponding to KUKA youBot.
{"title":"Trajectory Planning for Mobile Manipulators with Control Constraints","authors":"G. Pająk, I. Pająk","doi":"10.14313/par_248/21","DOIUrl":"https://doi.org/10.14313/par_248/21","url":null,"abstract":"This paper presents the method of trajectory planning for mobile manipulators considering limitations resulting from capabilities of robotic system actuators. The fulfillment of control constraints is achieved by introducing virtual control scaling of the robot trajectory in the limited periods of time. Such an approach allows researchers to obtain the trajectories fulfilling control constraints without significantly increasing the time of task execution. The proposed method generates sub-optimal trajectories maximizing the manipulability measure of the robot arm, preserves mechanical and collision avoidance limitations and can be used in real-time trajectory planning. The effectiveness of the presented solution is confirmed by computer simulations involving a mobile manipulator with parameters corresponding to KUKA youBot.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115482417","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}
Predicting human actions is a very actual research field. Artificial intelligence methods are commonly used here. They enable early recognition and classification of human activities. Such knowledge is extremely needed in the work on robots and other interactive systems that communicate and cooperate with people. This ensures early reactions of such devices and proper planning of their future actions. However, due to the complexity of human actions, predicting them is a difficult task. In this article, we review state-of-the-art methods and summarize recent advances in predicting human activity. We focus in particular on four approaches using machine learning methods, namely methods using: artificial neural networks, support vector machines, probabilistic models and decision trees. We discuss the advantages and disadvantages of these approaches, as well as current challenges related to predicting human activity. In addition, we describe the types of sensors and data sets commonly used in research on predicting and recognizing human actions. We analyze the quality of the methods used, based on the prediction accuracy reported in scientific articles. We describe the importance of the data type and the parameters of machine learning models. Finally, we summarize the latest research trends. The article is intended to help in choosing the right method of predicting human activity, along with an indication of the tools and resources necessary to effectively achieve this goal.
{"title":"Predicting Human Activity – State of the Art","authors":"Ekemeyong Esther, T. Zielińska","doi":"10.14313/par_248/31","DOIUrl":"https://doi.org/10.14313/par_248/31","url":null,"abstract":"Predicting human actions is a very actual research field. Artificial intelligence methods are commonly used here. They enable early recognition and classification of human activities. Such knowledge is extremely needed in the work on robots and other interactive systems that communicate and cooperate with people. This ensures early reactions of such devices and proper planning of their future actions. However, due to the complexity of human actions, predicting them is a difficult task. In this article, we review state-of-the-art methods and summarize recent advances in predicting human activity. We focus in particular on four approaches using machine learning methods, namely methods using: artificial neural networks, support vector machines, probabilistic models and decision trees. We discuss the advantages and disadvantages of these approaches, as well as current challenges related to predicting human activity. In addition, we describe the types of sensors and data sets commonly used in research on predicting and recognizing human actions. We analyze the quality of the methods used, based on the prediction accuracy reported in scientific articles. We describe the importance of the data type and the parameters of machine learning models. Finally, we summarize the latest research trends. The article is intended to help in choosing the right method of predicting human activity, along with an indication of the tools and resources necessary to effectively achieve this goal.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124441020","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}
Arm-Z is a concept of a hyper-redundant manipulator based on linearly joined sequence of congruent modules by oblique swivel joint mechanism. Each module has one degree of freedom only, namely a twist relative to the previous module in the sequence. Although the concept of this type of manipulator is relatively old and simple, its control is very difficult an nonintuitive, which results in a limited use in industrial practice. This paper presents a simple simulation of Arm-Z in Mathematica programming environment which demonstrates a few simple but potentially useful movements.
{"title":"Simulation of simple movements of Arm-Z oblique swivel joint chain manipulator","authors":"Ela Zawidzka, M. Zawidzki","doi":"10.14313/par_248/59","DOIUrl":"https://doi.org/10.14313/par_248/59","url":null,"abstract":"Arm-Z is a concept of a hyper-redundant manipulator based on linearly joined sequence of congruent modules by oblique swivel joint mechanism. Each module has one degree of freedom only, namely a twist relative to the previous module in the sequence. Although the concept of this type of manipulator is relatively old and simple, its control is very difficult an nonintuitive, which results in a limited use in industrial practice. This paper presents a simple simulation of Arm-Z in Mathematica programming environment which demonstrates a few simple but potentially useful movements.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"296 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123120212","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}
R. Syed, Markus Ulbricht, K. Piotrowski, M. Krstic
Asignificant rise in Artificial Intelligence (AI) has impacted many applications around us, so much so that AI has now been increasingly used in safety-critical applications. AI at the edge is the reality, which means performing the data computation closer to the source of the data, as opposed to performing it on the cloud. Safety-critical applications have strict reliability requirements; therefore, it is essential that AI models running on the edge (i.e., hardware) must fulfill the required safety standards. In the vast field of AI, Deep Neural Networks (DNNs) are the focal point of this survey as it has continued to produce extraordinary outcomes in various applications i.e. medical, automotive, aerospace, defense, etc. Traditional reliability techniques for DNNs implementation are not always practical, as they fail to exploit the unique characteristics of the DNNs. Furthermore, it is also essential to understand the targeted edge hardware because the impact of the faults can be different in ASICs and FPGAs. Therefore, in this survey, first, we have examined the impact of the fault in ASICs and FPGAs, and then we seek to provide a glimpse of the recent progress made towards the fault-tolerant DNNs. We have discussed several factors that can impact the reliability of the DNNs. Further, we have extended this discussion to shed light on many state-of-the-art fault mitigation techniques for DNNs.
{"title":"A Survey on Fault-Tolerant Methodologies for Deep Neural Networks","authors":"R. Syed, Markus Ulbricht, K. Piotrowski, M. Krstic","doi":"10.14313/par_248/89","DOIUrl":"https://doi.org/10.14313/par_248/89","url":null,"abstract":"Asignificant rise in Artificial Intelligence (AI) has impacted many applications around us, so much so that AI has now been increasingly used in safety-critical applications. AI at the edge is the reality, which means performing the data computation closer to the source of the data, as opposed to performing it on the cloud. Safety-critical applications have strict reliability requirements; therefore, it is essential that AI models running on the edge (i.e., hardware) must fulfill the required safety standards. In the vast field of AI, Deep Neural Networks (DNNs) are the focal point of this survey as it has continued to produce extraordinary outcomes in various applications i.e. medical, automotive, aerospace, defense, etc. Traditional reliability techniques for DNNs implementation are not always practical, as they fail to exploit the unique characteristics of the DNNs. Furthermore, it is also essential to understand the targeted edge hardware because the impact of the faults can be different in ASICs and FPGAs. Therefore, in this survey, first, we have examined the impact of the fault in ASICs and FPGAs, and then we seek to provide a glimpse of the recent progress made towards the fault-tolerant DNNs. We have discussed several factors that can impact the reliability of the DNNs. Further, we have extended this discussion to shed light on many state-of-the-art fault mitigation techniques for DNNs.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128831458","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}
Extremal problems for second order hyperbolic systems with multiple time-varying lags are presented. An optimal boundary control problem for distributed hyperbolic systems with boundary conditions involving multiple time-varying lags is solved. The time horizon is fixed. Making use of Dubovitski-Milyutin scheme, necessary and sufficient conditions of optimality for the Neumann problem with the quadratic performance functionals and constrained control are derived.
{"title":"Extremal Problems for Second Order Hyperbolic Systems with Boundary Conditions Involving Multiple Time-Varying Delays","authors":"A. Kowalewski","doi":"10.14313/par_248/69","DOIUrl":"https://doi.org/10.14313/par_248/69","url":null,"abstract":"Extremal problems for second order hyperbolic systems with multiple time-varying lags are presented. An optimal boundary control problem for distributed hyperbolic systems with boundary conditions involving multiple time-varying lags is solved. The time horizon is fixed. Making use of Dubovitski-Milyutin scheme, necessary and sufficient conditions of optimality for the Neumann problem with the quadratic performance functionals and constrained control are derived.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129279425","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}
The paper presents an adaptive air stream control algorithm for use in a bioreactor for waste composting. The system controls the streams of air supplied to the six ducts of the bireactor. Bioreactors of this type are characterized by the fact that the porosity of the charge is very heterogeneous throughout the volume. In addition, during the process, the charge is compacted and blockages for the gas flow often occur. The control algorithm should take into account the formation of blockages and attempt to clear them. In situations where unblocking is impossible, it should ensure proper distribution of air flow in other ducts despite the presence of blockages. The overriding goal of this algorithm is to ensure equal air flow streams in all channels, regardless of differences in flow resistance. Since the air circulation in bioreactors is forced by fans with constant capacity, the algorithm should adaptively determine the maximum average value of air streams that is possible to obtain under given conditions and adjust the control system to achieve it. The paper proposes a solution to meet these requirements.
{"title":"Adaptive Air Stream Control Algorithm","authors":"M. Rząsa","doi":"10.14313/par_248/99","DOIUrl":"https://doi.org/10.14313/par_248/99","url":null,"abstract":"The paper presents an adaptive air stream control algorithm for use in a bioreactor for waste composting. The system controls the streams of air supplied to the six ducts of the bireactor. Bioreactors of this type are characterized by the fact that the porosity of the charge is very heterogeneous throughout the volume. In addition, during the process, the charge is compacted and blockages for the gas flow often occur. The control algorithm should take into account the formation of blockages and attempt to clear them. In situations where unblocking is impossible, it should ensure proper distribution of air flow in other ducts despite the presence of blockages. The overriding goal of this algorithm is to ensure equal air flow streams in all channels, regardless of differences in flow resistance. Since the air circulation in bioreactors is forced by fans with constant capacity, the algorithm should adaptively determine the maximum average value of air streams that is possible to obtain under given conditions and adjust the control system to achieve it. The paper proposes a solution to meet these requirements.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126212180","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 article the functionalities and possibilities of using the SELF tool platform (Soneta Elevation LifeCycle Framework) are presented. The four defined layers of the platform are discussed, the process of implementing the solution and the integration of individual layers is presented. The market of ERP systems in Poland and alternative solutions available on the market are also discussed. The presented SELF platform, created in the SaaS (Software as a Service) model, is one of the key technological tools introduced in Soneta to implement an effective method of work organization within the firm and with its network of authorized partners.
{"title":"SELF Tool Platform in SaaS Model for Automation and Standardization of Solutions Generatione","authors":"Marta Kraszewska, W. Kraszewski, Jadwiga Wojtas","doi":"10.14313/par_247/111","DOIUrl":"https://doi.org/10.14313/par_247/111","url":null,"abstract":"In the article the functionalities and possibilities of using the SELF tool platform (Soneta Elevation LifeCycle Framework) are presented. The four defined layers of the platform are discussed, the process of implementing the solution and the integration of individual layers is presented. The market of ERP systems in Poland and alternative solutions available on the market are also discussed. The presented SELF platform, created in the SaaS (Software as a Service) model, is one of the key technological tools introduced in Soneta to implement an effective method of work organization within the firm and with its network of authorized partners.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129990800","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}
The paper presents some practical solutions that have been used to convert stationary laboratory workstations (used in the teaching of analog and digital electronics, microcontroller programming and embedded systems) to remote learning. The presented solutions enabled students to work in conditions similar to standard teaching in classroom – using real circuits and measuring instruments. Examples of the laboratory workstations are: stepper motor control, generation of a PWM signal, reading information from switches, using SPI and I2C buses, measuring of dynamic parameters of logic gates, measuring of active filters, measuring of dynamic parameters of a transistor switch. A characteristic feature of the described solutions is the low cost and the possibility of quickly adapting the stationary workstation to remote work (and vice-versa), which was particularly important under the conditions of the coronavirus pandemic in recent years and dynamic changes in the form of teaching method. The presented ideas can be useful for teachers working at technical universities, where the issue of providing practical skills to students is crucial.
{"title":"Overview of the Laboratory Workstation Solutions Used during Remote Learning","authors":"M. Raczyński, A. Biedka","doi":"10.14313/par_247/99","DOIUrl":"https://doi.org/10.14313/par_247/99","url":null,"abstract":"The paper presents some practical solutions that have been used to convert stationary laboratory workstations (used in the teaching of analog and digital electronics, microcontroller programming and embedded systems) to remote learning. The presented solutions enabled students to work in conditions similar to standard teaching in classroom – using real circuits and measuring instruments. Examples of the laboratory workstations are: stepper motor control, generation of a PWM signal, reading information from switches, using SPI and I2C buses, measuring of dynamic parameters of logic gates, measuring of active filters, measuring of dynamic parameters of a transistor switch. A characteristic feature of the described solutions is the low cost and the possibility of quickly adapting the stationary workstation to remote work (and vice-versa), which was particularly important under the conditions of the coronavirus pandemic in recent years and dynamic changes in the form of teaching method. The presented ideas can be useful for teachers working at technical universities, where the issue of providing practical skills to students is crucial.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131582609","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 survey paper some issues concerning a singularity concept in robotics are addressed. Singularities are analyzed in the scope of inverse kinematics for serial manipulator, a motion planning task of nonholonomic systems and the optimal control covering a large area of practical robotic systems. An attempt has been made to define the term singularity, which is independent on a specific task. A few classifications of singularities with respect to different criteria are proposed and illustrated on simple examples. Singularities are analyzed from a numerical and physical point of view. Generally, singularities pose some problems in motion planning and/or control of robots. However, as illustrated on the example on force/momenta transformation in serial manipulators, they can also be desirable is some cases. Singularity detection techniques and some methods to cope with them are also provided. The paper is intended to be didactic and to help robotic researchers to get a general view on the singularity issue.
{"title":"Many Faces of Singularities in Robotics","authors":"I. Dulęba, I. Karcz-Dulęba","doi":"10.14313/par_247/19","DOIUrl":"https://doi.org/10.14313/par_247/19","url":null,"abstract":"In this survey paper some issues concerning a singularity concept in robotics are addressed. Singularities are analyzed in the scope of inverse kinematics for serial manipulator, a motion planning task of nonholonomic systems and the optimal control covering a large area of practical robotic systems. An attempt has been made to define the term singularity, which is independent on a specific task. A few classifications of singularities with respect to different criteria are proposed and illustrated on simple examples. Singularities are analyzed from a numerical and physical point of view. Generally, singularities pose some problems in motion planning and/or control of robots. However, as illustrated on the example on force/momenta transformation in serial manipulators, they can also be desirable is some cases. Singularity detection techniques and some methods to cope with them are also provided. The paper is intended to be didactic and to help robotic researchers to get a general view on the singularity issue.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123454282","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}
Kamil Bialik, M. Kowalczyk, Krzysztof Błachut, T. Kryjak
This paper proposes the use of an event camera as a component of a vision system that enables counting of fast-moving objects – in this case, falling corn grains. These cameras transmit, in an asynchronous manner, information about the change in brightness of individual pixels and are characterised by low latency, no motion blur, and correct operation in different lighting conditions, as well as very low power consumption. The proposed counting algorithm processes events in real time. The operation of the solution was demonstrated on a stand consisting of a chute with a vibrating feeder, which allowed the number of falling grains to be adjusted. The objective of the control system with a PID controller was to maintain a constant average number of falling objects. The proposed solution was subjected to a series of tests to determine the correctness of the developed method operation. On their basis, the validity of using an event camera to count small, fast-moving objects and the associated wide range of potential industrial applications can be confirmed.
{"title":"Fast Object Counting with an Event Camera","authors":"Kamil Bialik, M. Kowalczyk, Krzysztof Błachut, T. Kryjak","doi":"10.14313/par_247/79","DOIUrl":"https://doi.org/10.14313/par_247/79","url":null,"abstract":"This paper proposes the use of an event camera as a component of a vision system that enables counting of fast-moving objects – in this case, falling corn grains. These cameras transmit, in an asynchronous manner, information about the change in brightness of individual pixels and are characterised by low latency, no motion blur, and correct operation in different lighting conditions, as well as very low power consumption. The proposed counting algorithm processes events in real time. The operation of the solution was demonstrated on a stand consisting of a chute with a vibrating feeder, which allowed the number of falling grains to be adjusted. The objective of the control system with a PID controller was to maintain a constant average number of falling objects. The proposed solution was subjected to a series of tests to determine the correctness of the developed method operation. On their basis, the validity of using an event camera to count small, fast-moving objects and the associated wide range of potential industrial applications can be confirmed.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"397 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115993676","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：