Creating an aerodynamic shape, like an airfoil wing, requires many factors to be considered, especially aerodynamic properties such as its lift-to-drag ratio (L/D). Currently, generating feasible airfoil shapes usuall...
详细信息
ISBN:
(纸本)9781665476881
Creating an aerodynamic shape, like an airfoil wing, requires many factors to be considered, especially aerodynamic properties such as its lift-to-drag ratio (L/D). Currently, generating feasible airfoil shapes usually requires computationally expensive tools, such as Computational Fluid Dynamics (CFD). In recent years, increasing work has been directed to utilizing machine learning algorithms to synthesize accurate airfoil shapes while reducing the required computational cost. Generative Adversarial Network (GAN) is one of many algorithms to see success in airfoil shape optimization and is shown to generate good airfoils given a small set of training examples. this paper focuses on implementing a conditional GAN (cGAN) based framework with various filters for airfoil inverse design problem. By labelling the training dataset with aerodynamic characteristics separated by pre-defined thresholds to lift-to-drag ratio (L/D) and shape area, the class labels will be able to guide the network to generate different classes of airfoils influenced by these characteristics. Together with layers of Savitzky-Golay (SG) filter and B-Spline Interpolation, the developed model was shown to achieve good performance in generating new airfoils. In addition, we explored the viability of adding Wasserstein loss from Wasserstein GAN into the network architecture, forming a cWGAN-GP. Testing results showed that cWGAN-GP was able to achieve better performance for a specific airfoil class.
Cognitive robots are intelligent systems that learn from their environment, adapt to dynamic changes, and make decisions without a human's direct intervention. this research studies the integration of Reinforcemen...
详细信息
ISBN:
(数字)9798350389609
ISBN:
(纸本)9798350389616
Cognitive robots are intelligent systems that learn from their environment, adapt to dynamic changes, and make decisions without a human's direct intervention. this research studies the integration of Reinforcement Learning in cognitive robots with Q-Learning for autonomous path planning. the study addresses the most critical issues in traditional A* and Dynamic Programming algorithms by devising path-planning techniques, mainly the lack of adaptability and computational efficiency in real-time and unpredictable environments. Our approach is based on Q-Learning, which is a model-free RL algorithm allowing the robots to find paths autonomously by optimizing their paths and avoiding obstacles. the Q-Learning algorithm provides the possibility of learning optimal policies for the robot through iterative interaction with its environment balanced between exploration and exploitation of the decision process. A reward system is utilized by the proposed model, encouraging the robot to explore shorter, collision-free paths and adjust based on feedback in real time from its surroundings. the model was found to be significantly better than its counterparts. In this context, as indicated, the Q-Learning model runs at 11.5 seconds, faster than A* at 18.3 seconds and Dynamic Programming at 16.7 seconds, yet with an accuracy of 94% and was found to have the highest collision avoidance rate at 98%. Additionally, the adaptability of the model about the environment presents a marked difference in terms of path length optimization, having done so with a mean path length of 12.3, compared to approaches or models. the robustness and scalability of the Q-Learning model make it highly applicable in real-world applications.
Unmanned aerial vehicles (UAVs), also known as drones, are recently gaining increased research attention across various fields due to their flexibility and application potential. Drones have become increasingly popula...
Unmanned aerial vehicles (UAVs), also known as drones, are recently gaining increased research attention across various fields due to their flexibility and application potential. Drones have become increasingly popular in recent years due to their versatility and ability to perform tasks that were previously challenging or impossible. However, the full potential of drone technology has not been realized due to limitations in their communication and control systems. the integration of drone networks into a 5G environment has the potential to transform the capabilities of drones, providing high-speed, low-latency, and reliable communication and control capabilities. In this review paper, we provide an overview of the integration of drone networks into a 5G environment, discussing the technical aspects, potential applications, and challenges of this integration. We also examine the benefits of using 5G networks for drone operations, such as increased range, improved accuracy, and enhanced safety. Finally, we identify future research directions for the integration of drone networks into a 5G environment, highlighting the need for further research in areas such as drone security, energy efficiency, and spectrum management. Overall, this review paper provides a valuable resource for understanding the potential of drones in a 5G network and the challenges that must be addressed to fully realize this potential.
In the field of geometry and computer-aided design Bézier surfaces are well known for their flexibility and effectiveness, in depicting shapes. However, dealing with real-world data and model parameters often inv...
详细信息
ISBN:
(数字)9798331528553
ISBN:
(纸本)9798331528560
In the field of geometry and computer-aided design Bézier surfaces are well known for their flexibility and effectiveness, in depicting shapes. However, dealing with real-world data and model parameters often involves uncertainty and imprecision that regular Bézier surfaces struggle to handle. this piece introduces the idea of interval-valued fuzzy Bézier Surface Approximation, an approach that combines logic and interval arithmetic to tackle uncertainty in surface modeling. In this paper, interval-valued fuzzy Bézier surface approximation is introduced. the interval-valued fuzzy control net relation is defined and introduced. Next, the surface blending function is obtained by blending the interval-valued fuzzy control net withthe Bernstein blending function. Lastly, the data points or interval-valued fuzzy control net relation of the basis function is illustrated using the approximation method withthe interval-valued fuzzy concept and features to produce an interval-valued fuzzy Bézier surface. the application of Bézier surfaces can be extended to handle a wide range of complex modeling and offers a more precise and dependable tool for engineering, graphics, and data visualization applications.
this paper proposes a video flame detection method based on Extreme Learning Machine (ELM). Visual Background Extractor++(ViBE++) algorithm is used to extract the dynamic foreground features of flame video images, and...
详细信息
Auditory information can expand the knowledge of the environment of a mobile robot. therefore, assigning sound sources to a global map is an important task. In this paper, we first form a relationship between the micr...
详细信息
ISBN:
(纸本)9789897584428
Auditory information can expand the knowledge of the environment of a mobile robot. therefore, assigning sound sources to a global map is an important task. In this paper, we first form a relationship between the microphone positions and auditory features extracted from the microphone signals to describe the 3D position of multiple static sound sources. Next, we form a Constraint Satisfaction Problem (CSP), which links all observations from different measurement positions. Classical approaches approximate these non-linear system of equations and require a good initial guess. In contrast, in this work, we solve these equations by using interval analysis in less computational effort. this enables the calculation being performed on the hardware of a robot at run time. Next, we extend the approach to model uncertainties of the microphone positions and the auditory features extracted by the microphones making the approach more robust in real applications. Last, we demonstrate the functionality of our approach by using simulated and real data.
A series elastic actuator (SEA) is mainly used in human-robot interaction applications. Especially, a reaction-force-sensing SEA (RFSEA), where the spring is located between the ground and the actuator, has been devel...
详细信息
A series elastic actuator (SEA) is mainly used in human-robot interaction applications. Especially, a reaction-force-sensing SEA (RFSEA), where the spring is located between the ground and the actuator, has been developed as a practical implementation of the SEAs, as their form-factors are superior to the conventional SEAs. However, the RFSEA has limitations on its torque control performance. the output torque of an RFSEA is estimated as the spring torque, assuming the load is fixed. However, since the load moves in human-robot interaction applications, the assumption causes significant degradation in the control performance of the RFSEA. this paper presents a precise torque estimation method for the RFSEA. the dynamics of the RFSEA were analyzed, modeling the actuator as a two-mass system. the output torque was verified as the function of two variables from the dynamic analysis: the stator angle and the angular velocity of the rotor. In this paper, the torque estimator with a single encoder is proposed to maintain the form-factor of the RFSEA. An encoder measures the stator angle, and a designed observer based on a disturbance observer estimates the angular velocity of the rotor. the performance of the proposed torque estimator was verified experimentally. From the experimental results, an error of the proposed torque estimator was reduced by 37% compared to the conventional when the load moves by mimicking the human movement. Copyright (c) 2022 the Authors. this is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)
Cooperative machines are the essence of automated systems that provide solutions in various domains, one example being the manufacturing industry. Specifically, the ability to synchronize the mission of each robot rep...
详细信息
ISBN:
(数字)9798350361230
ISBN:
(纸本)9798350361247
Cooperative machines are the essence of automated systems that provide solutions in various domains, one example being the manufacturing industry. Specifically, the ability to synchronize the mission of each robot represents a crucial decision-making factor in this domain. this paper provides a path-planning solution for an application with two collaborative robots (also known as cobots) that should fulfill individual missions under the Metric Interval Time Logic (MITL) formalism. this formalism allows us to embody spatial and time requirements. this work provides two contributions in this field, based on the two phases of the planning solution: (a) a synchronization mechanism based on a high-level planner, developed on a previously defined model denoted Composed Time Petri net, that joins boththe mission of the robots and its capabilities of movement and (b) experimental validation of the high-level planner based on a low-level path execution implemented on Robot Operating System (ROS) that facilitates the execution of the planned path to validate the simulated event sequence. the Composed Time Petri net is model-checked through simulations in the ROMEO tool, while the corroboration of the results is based on an experiment with two cobots: UR5 and LM3 with individual MITI missions, that are collaborating in a manipulating application: UR5 should pick and place pieces, while LM5 should pick up a tool, e.g., welding gun, to glue the pieces. A video withthe results can be inspected here [1].
Robot trajectory tracking is a pervasive requirement in many robotic applications and is an active area of research. there are a number of different approaches and algorithms available for tracking problems. However, ...
详细信息
Oxygen saturation (SO2, %) describes oxygen status of human blood, which is widely used for diagnosis in medical area. A photoacoustic system is designed to measure oxygen saturation by using a 638 nm single light sou...
详细信息
暂无评论