the proceedings contain 84 papers. the topics discussed include: modeling of thermal processes in microcontroller system by fractional order, discrete, hybrid transfer function using FOBD approximation;altruistic coor...
ISBN:
(纸本)9798350311075
the proceedings contain 84 papers. the topics discussed include: modeling of thermal processes in microcontroller system by fractional order, discrete, hybrid transfer function using FOBD approximation;altruistic coordination strategy for on-ramp merging on highway of a formation of cooperative automated vehicles;detection-segmentation convolutional neural network for autonomous vehicle perception;modeling a dynamic object with distributed parameters;new trends in Industry 4.0 – voice control;distributed control for teams of non-holonomic mobile robots executing competitive tasks;a geometric measurement system using a robot as handling system and reference system;evaluation of the effectiveness of physical protection systems with consideration of its cyber-resilience;SRPB: a benchmark for the quantitative evaluation of a social robot navigation;and artificial potential field APF-based obstacle avoidance technique for robot arm teleoperation.
Robots are increasingly performing complex tasks in industrial settings, such as welding, painting, and cutting, but their lower stiffness and repeatability, especially in the cheaper end of the market, limit performa...
详细信息
ISBN:
(纸本)9798350311075
Robots are increasingly performing complex tasks in industrial settings, such as welding, painting, and cutting, but their lower stiffness and repeatability, especially in the cheaper end of the market, limit performance. While previous research aimed to improve robot repeatability by optimizing the pose of the workpiece, these approaches were not feasible for large and complex paths. this paper proposes a novel approach of incorporating a second robot to adjust the workpieces position during the manufacturing process, thereby forming a single high-precision robotic system. this paper aims to investigate the feasibility of this approach. For this purpose, it presents a path planner to leverage the resulting additional degrees of freedom to achieve greater repeatability. the effectiveness of this planner is then compared to previous approaches.
作者：
Puchalski, BartoszGdansk Univ Technol
Fac Elect & Control Engn Dept Intelligent Control & Decis Support Syst 11-12 Gabriela Narutowicza St PL-80233 Gdansk Poland
the article examines the use of Gaussian Process models to simulate the dynamic processes of a Pressurized Water nuclear Reactor for fault detection and diagnostics. the paper illustrates the potential of Gaussian Pro...
详细信息
ISBN:
(纸本)9798350311075
the article examines the use of Gaussian Process models to simulate the dynamic processes of a Pressurized Water nuclear Reactor for fault detection and diagnostics. the paper illustrates the potential of Gaussian Process models as a tool for monitoring and predicting various fault conditions in Pressurized Water nuclear Reactor power plants, including reactor coolant flow and temperature variations, deviations from nominal working point or faulty power measurements. the article discusses the characteristics and benefits of Gaussian Process models and how they can be utilized to improve: the reliability and accuracy of nuclear power plant anomaly detection, fault diagnosis and decision making process in states of emergency. Overall, this paper highlights the capabilities of Gaussian Process models to enhance the safety, reliability and efficiency of nuclear power plants. the results of this study are expected to provide valuable insights for engineers and researchers in the fields of control engineering and nuclear power.
this paper presents an iterative learning-based model predictive controller (MPC) for trajectory tracking control of an autonomous planetary rover on unknown terrain. In order to achieve accurate trajectory tracking u...
详细信息
ISBN:
(纸本)9798350311075
this paper presents an iterative learning-based model predictive controller (MPC) for trajectory tracking control of an autonomous planetary rover on unknown terrain. In order to achieve accurate trajectory tracking under model uncertainties, a nonlinear controller and an MPC are utilized, combined with a learning-based uncertainties approximation. the model uncertainties and disturbances are learned using a deep neural network (DNN) as well as a parametric model and results are compared. For test and validation purposes, a gazebo simulation is used, which is itself already validated using data from a prototype rover. Withthat, the trajectory tracking performance of the proposed learning-based MPC is validated and compared to other well-performing controllers. the results show that the algorithm is able to learn model uncertainties and to compensate them during runtime while being practicable for the implementation and in the training phase.
Object detection in 3D is a crucial aspect in the context of autonomous vehicles and drones. However, prototyping detection algorithms is time-consuming and costly in terms of energy and environmental impact. To addre...
详细信息
ISBN:
(纸本)9798350311075
Object detection in 3D is a crucial aspect in the context of autonomous vehicles and drones. However, prototyping detection algorithms is time-consuming and costly in terms of energy and environmental impact. To address these challenges, one can check the effectiveness of different models by training on a subset of the original training set. In this paper, we present a comparison of three algorithms for selecting such a subset - random sampling, random per class sampling, and our proposed MONSPeC (Maximum Object Number Sampling per Class). We provide empirical evidence for the superior effectiveness of random per class sampling and MONSPeC over basic random sampling. By replacing random sampling with one of the more efficient algorithms, the results obtained on the subset are more likely to transfer to the results on the entire dataset. the code is available at: https://***/vision-agh/monspec.
We present a comparative case study of machine learning models, evaluating their efficiency in a practical task of multiclass classification of samples being submissions to a recruitment survey and assigning them scor...
详细信息
ISBN:
(纸本)9798350311075
We present a comparative case study of machine learning models, evaluating their efficiency in a practical task of multiclass classification of samples being submissions to a recruitment survey and assigning them scores denoting the match level for a given candidate to a given workgroup (committee) in the AGH Students' Council. this research is based on the Council's recruitment applications that carried candidates' responses to a set of 10 hypothetical Council member activity scenarios, where they were to choose one of four given solutions to the problems. the data was collected from a web quiz in 2020, validated on a voluntary insider control group's responses to these questions and finally the best-performing model was evaluated in practice in the 2021's recruitment inside an in-browser adventure minigame. this work provides insight into how models ranging from classical methods to deep learning perform in a very specific not yet well-explored in literature, practical non-linear problem that is dependent on individual features of the participants, withthe data volume being very limited due to a restricted population of candidates. this information may provide a starting point for applications of machine learning in decision support systems in recruitment processes.
When studying or designing a large-scale network system, a simpler representation of the dynamics of the system is often needed. this is because, for a very large scale system where the dynamics of all the nodes are c...
详细信息
ISBN:
(纸本)9798350311075
When studying or designing a large-scale network system, a simpler representation of the dynamics of the system is often needed. this is because, for a very large scale system where the dynamics of all the nodes are coupled, the system of differential equations describing the system are very high order. In such cases, engineers are faced with determining a "lower-order" model that provides a good enough representation of the large-scale dynamics. Prior work by the author has identified fractional-order dynamics in large, scale-free networks and noted that fractional-order models often better match the dynamic response of the network when the stiffness relationship (a spring constant) in the relationship between nodes in the network is larger. this work extends those results by systematically determining what parameters in the network are statistically significantly correlated with fractional-order models better matching the large-scale dynamics than integer-order models. Specifically we find a weak correlation between the degree of connectivity of the network, the spring constant, the distance in the network between the two nodes, and the size of the network to be statistically significantly correlated to whether fractional-models are better. Interestingly, in contrast to the stiffness, the damping is statistically uncorrelated with fractional-dynamics.
In this paper spatially interconnected (ladder) systems have been discussed. First, the multidimensional, in that case, 2D - continuous in time and discrete in the spatial variable, has been introduced. Next, the temp...
详细信息
Breast cancer is the most frequent female cancer. Its early diagnosis increases the chances of a complete cure for the patient. Suitably designed deep learning algorithms can be an excellent tool for quick screening a...
详细信息
ISBN:
(纸本)9798350311075
Breast cancer is the most frequent female cancer. Its early diagnosis increases the chances of a complete cure for the patient. Suitably designed deep learning algorithms can be an excellent tool for quick screening analysis and support radiologists and oncologists in diagnosing breast cancer. the design of a deep learning-based system for automated breast cancer diagnosis is not easy due to the lack of annotated data, especially at pixel level, the large size of the images with relatively small cancer lesion sizes and class imbalance, a wide diversity of cancerous lesions, a variety of breasts, both in size and density, make the training of the neural models challenging. Moreover, clinicians are often concerned about using these black-box models because of the lack of transparency in their inference. To address these issues, we propose an approach taking advantage of Multiple Instance Learning (MIL), supported by attention mechanisms. We researched Attention-based MIL (AMIL), Gated AMIL (GAMIL), Dual Stream MIL (DSMIL) and CLustering-constrained AMIL (CLAM) models trained in a weakly-supervised manner and compared them with a common model in image classification tasks, ResNet18. the approach described in this paper is multimodal and combines two mammographic projections (CC and MLO) in the training process. the developed neural system achieved high classification efficiency. Furthermore, exploiting the generated attentional maps allowed the localisation of cancerous lesions, thus increasing the interpretability of the algorithm. thanks to this mechanism, we were also able to detect artifacts in the analyzed database, difficult to spot but drastically skewing the algorithm's performance.
the problem of partially hinged partially free rectangular plate that aims to represent a suspension bridge subject to some external forces (for example the wind) is considered in order to model and simulate the unsta...
详细信息
ISBN:
(纸本)9798350362350;9798350362343
the problem of partially hinged partially free rectangular plate that aims to represent a suspension bridge subject to some external forces (for example the wind) is considered in order to model and simulate the unstable end behavior. Such a problem can be modeled by a plate evolution equation, which is nonlinear with a nonlocal stretching effect in the spanwise direction. the external forces are periodic in time and cause the vortex shedding on the structure (on the surface of the plate) and thus it may cause damage to the material. Numerical study of the behavior of steady state solutions for different values of the force velocity are provided with two finite element methods of different type.
暂无评论