the QR-Enabled Autonomous Bartender system introduces a pioneering approach to revolutionize beverage service within the hospitality sector. the Makr Shakr is a notable example of robotic bartending systems, renowned ...
详细信息
ISBN:
(数字)9798350362343
ISBN:
(纸本)9798350362350
the QR-Enabled Autonomous Bartender system introduces a pioneering approach to revolutionize beverage service within the hospitality sector. the Makr Shakr is a notable example of robotic bartending systems, renowned for its sleek design and advanced automation capabilities. However, existing works in this domain are often characterized by their high cost and lack of customization options, making them inaccessible to many establishments. the objective of this paper is to present the design, construction, and implementation of a stationary robotic bartender system enabled with QR code interaction, highlighting its potential to enhance customer experience and operational efficiency in bars and restaurants. the proposed system objectives encompass the design and construction of a stationary robotic bartender, the development of a user-friendly mobile website, the implementation of a personalized ordering system, and the optimization of beverage mixing and dispensing efficiency. Utilizing chrome and wood construction, this system balances durability with cost-effectiveness. the implementation of this initiative promises to advance automation and QR technology in the food and beverage industry, offering valuable insights into robotics, automation, and web development while enhancing customer experience and operational efficiency in bars and restaurants. As for validation, the system underwent rigorous testing, with a total of 210 trials resulting in 35 trials for each drink over a period of approximately 7 hours. Impressively, the system demonstrated an overall accuracy of $96.1 \%$ with an average response time of 0.4 seconds.
this paper addresses a significant challenge within the realm of fixed wing Unmanned Aerial Vehicles (UAVs), namely obstacle avoidance of the Leader-Follower system. the proposed approach involves formulating the Lead...
详细信息
ISBN:
(数字)9798350362343
ISBN:
(纸本)9798350362350
this paper addresses a significant challenge within the realm of fixed wing Unmanned Aerial Vehicles (UAVs), namely obstacle avoidance of the Leader-Follower system. the proposed approach involves formulating the Leader-Follower problem, consisting of one leader and three followers, with control strategies utilizing the logarithm exponential Quaternion method. Subsequently, the designed control law employing quaternions is applied to boththe leader and the follower UAVs. Moreover, a notable contribution of this research lies in the incorporation of adaptive obstacle avoidance. the idea based on potential field as obstacle avoidance algorithm, with adaptive techniques for determining obstacle avoidance parameters. these parameters are dynamically adjusted based on the distance between the UAV and the obstacle through a non-linear adaptation function. the comprehensive implementation of these methods is rigorously evaluated by employing a predefined reference path for the leader and conducting numerous scenario-based tests. Random directions of followers were used in case of stuck in local minimum to avoid it; this was applied in case when potential filed force is less than small value. Experiments to test some scenarios of obstacle avoidance were conducted. the final results conclusively demonstrate the stability of the control law even in the presence of obstacles. the effectiveness of the adaptive obstacle avoidance approach is clearly evident from the trajectories of the UAV followers.
When faced with an execution failure, an intelligent robot should be able to identify the likely reasons for the failure and adapt its execution policy accordingly. this paper addresses the question of how to utilise ...
详细信息
ISBN:
(纸本)9781728190778
When faced with an execution failure, an intelligent robot should be able to identify the likely reasons for the failure and adapt its execution policy accordingly. this paper addresses the question of how to utilise knowledge about the execution process, expressed in terms of learned constraints, in order to direct the diagnosis and experience acquisition process. In particular, we present two methods for creating a synergy between failure diagnosis and execution model learning. We first propose a method for diagnosing execution failures of parameterised action execution models, which searches for action parameters that violate a learned precondition model. We then develop a strategy that uses the results of the diagnosis process for generating synthetic data that are more likely to lead to successful execution, thereby increasing the set of available experiences to learn from. the diagnosis and experience correction methods are evaluated for the problem of handle grasping, such that we experimentally demonstrate the effectiveness of the diagnosis algorithm and show that corrected failed experiences can contribute towards improving the execution success of a robot.
the use of goods-to-person robotic systems in a warehouse enhances storage density by devoting specific areas for Automated Mobile Robots (AMRs). Nevertheless, operation in narrow aisles and confined spaces presents n...
详细信息
ISBN:
(数字)9798350362343
ISBN:
(纸本)9798350362350
the use of goods-to-person robotic systems in a warehouse enhances storage density by devoting specific areas for Automated Mobile Robots (AMRs). Nevertheless, operation in narrow aisles and confined spaces presents notable challenges. this study outlines a comprehensive approach for AMRs to autonomously navigate within narrow aisles of a warehouse, ensuring safety and streamlining order completion. the goal is to independently collect and transport bins with products referred to the order, to the workstation area, where workers finalize order packing. Precise positioning of fiducial markers on the floor, initiates a fusion-based localization system that merges information from wheel odometry and fiducial detection. the markers are organized as an undirected graph to facilitate navigation purposes and Dijkstra algorithm is employed to successfully generate both safe and optimal paths. A pipeline has been established for the retrieval and positioning of bins from shelves or workstations to optimize the order picking process. the proposed method has been tested on a simulation environment with realistic constraints stem from the development of an autonomous warehouse environment.
An important component of the Mössbauer spectrometer is the Mössbauer drive, which allows, utilizing the Doppler effect, to vary the amount of energy of the emitted gamma quanta so that it corresponds to the...
详细信息
ISBN:
(数字)9798350362343
ISBN:
(纸本)9798350362350
An important component of the Mössbauer spectrometer is the Mössbauer drive, which allows, utilizing the Doppler effect, to vary the amount of energy of the emitted gamma quanta so that it corresponds to the resonance energy and energetically excites the irradiated nuclei. this paper deals with drive modelling and control in Mössbauer spectroscopy. the equations of motion of the linear drive are derived and compared in different versions. In this context, the single-mass representation proves to be a sufficiently accurate model, which shows almost identical results compared to multibody models. this leads to a reduction of the system order from n=6 to n=2, which greatly simplifies the evaluation steps in this context and the further controller design modalities. Based on this, a heuristic control concept is developed that fundamentally revises common design approaches and opens up a broad spectrum of research. the controller design provides for a combination of signal-smoothing and signal amplifying low-pass filtering in combination with dynamic input vector normalisation. this achieves the desired frequency and amplitude response of $1.1485 \cdot 10^{3} \frac{\mathrm{rad}}{\mathrm{s}}$ and 0.3 mm and optimises the dynamics for real laboratory use.
this paper presents a model and parameter estimation methods for an inland cargo catamaran. this model is used in an NMPC scheme to address the path following problem of the vessel in inland waterways. this NMPC schem...
详细信息
ISBN:
(数字)9798331518493
ISBN:
(纸本)9798331518509
this paper presents a model and parameter estimation methods for an inland cargo catamaran. this model is used in an NMPC scheme to address the path following problem of the vessel in inland waterways. this NMPC scheme derives the control action by minimizing a cost function while meeting constraints. the path consists of waypoints that define safety contours that are derived from IENC. In Addition, circular geometries are used to define safety contours around obstacles along the fairway. the model and NMPC are validated through simulation of a section of Leuven canal.
the complexity of the communication between electronic control units in contemporary vehicles is increasing withthe rising demand of customer functions such as automated driving and infotainment resulting in up to se...
详细信息
ISBN:
(数字)9798331520038
ISBN:
(纸本)9798331520045
the complexity of the communication between electronic control units in contemporary vehicles is increasing withthe rising demand of customer functions such as automated driving and infotainment resulting in up to several thousand data elements (signals) per data bus. Consequently, engineers have no choice but to apply data science methods to extract meaningful insights from this high-dimensional communication data, particularly before training machine learning models. A critical step in this process is identifying the bus signals relevant for a specific data science task. Extracting them manually is not only time-consuming but it also demands a high degree of in-vehicle communication knowledge which is hard to obtain. To address this challenge, we propose an automated feature engineering approach that leverages reinforcement learning combined with state-of-the-art feature selection and engineering methods and a tunable sampling rate for the bus data. Due to the high degree of automation it requires little prior knowledge of how in-vehicle communication works. Our method enhances important key performance indicators for machine learning model quality for the task of energy consumption prognosis and significantly reduces the number of bus signals required for accurate model predictions. this approach does not only improve the understanding of relevant data but also reduces the model's size as less features are used for the prediction, leading to more efficient and interpretable machine learning solutions.
Aiming at the problem that the accuracy of pavement distress detection is easily affected by complex texture, noisy background, uneven illumination conditions and external environmental interference of highway pavemen...
详细信息
ISBN:
(数字)9798350344721
ISBN:
(纸本)9798350344738
Aiming at the problem that the accuracy of pavement distress detection is easily affected by complex texture, noisy background, uneven illumination conditions and external environmental interference of highway pavement distress images, this paper studies the methods of pavement distress detection based on object detection Convolutional Neural Network. Firstly, the methods of pavement distress detection based on Faster-RCNN, YOLO-V5s, and SSD are compared and analyzed. Secondly, three variants of CNN models are investigated for pavement distress detection, including FR-PDD, YOLO5s-PDD and SSD-PDD. Finally, the comparative experiments were conducted, and the results showed that the average of Yolov5s-PDD network is superior to the other two methods, with an average accuracy of 98.1%.
this paper presents a rigorous investigation into the efficacy of diverse preprocessing methods for bearing fault classification, leveraging the comprehensive CWRU dataset. Four distinct approaches were explored: raw ...
详细信息
ISBN:
(数字)9798350350708
ISBN:
(纸本)9798350350715
this paper presents a rigorous investigation into the efficacy of diverse preprocessing methods for bearing fault classification, leveraging the comprehensive CWRU dataset. Four distinct approaches were explored: raw data analysis, Fast Fourier Transform (FFT), Short-Time Fourier Transform (STFT), and Continuous Wavelet Transform (CWT). the study introduces a Convolutional Neural Network (CNN) as the underlying algorithm for fault classification. through extensive experimentation and analysis, we assess the performance of CNN in conjunction with each preprocessing technique. the results provide valuable insights into the strengths and limitations of raw data and frequency-domain representations, highlighting the impact on the accuracy of fault classification in machinery health monitoring applications, which was decided to be the main score in models evaluation. this comparative analysis can not only contribute to the advancement of condition monitoring but also assist practitioners in selecting optimal preprocessing methods for their specific needs.
In this paper, two ensemble machine learning-based methods, Bagging and Boosting, are applied to model the unsteady aerodynamics of an aircraft from flight test data. Bagging generates a predictive model by combining ...
详细信息
ISBN:
(数字)9798350373172
ISBN:
(纸本)9798350373189
In this paper, two ensemble machine learning-based methods, Bagging and Boosting, are applied to model the unsteady aerodynamics of an aircraft from flight test data. Bagging generates a predictive model by combining multiple decision trees that have been trained using the bootstrap on different input-output datasets. Boosting generates a predictive model by growing trees sequentially based on previously grown trees, with each decision tree fitting on a modified version of the data. the effectiveness of these two data-driven methods is investigated and validated by estimating the standard research aircraft's force and moment coefficients. the proposed methods' estimated results are statistically analysed and found to be highly correlated with measured data and to have a significantly lower root mean squared error (RMSE). Furthermore, these estimated aerodynamic force and moment coefficients are compared to the estimated coefficient model from the most commonly used maximum likelihood estimation method (MLE). the estimated results were found to be on par withthe MLE predicted aerodynamic models. Moreover, Bagging and Boosting-based methods do not require the solution of the equation of motion, which is advantageous for generalised nonlinear modelling applications such as load estimation, aeroelasticity, and fault diagnosis, detection, and identification.
暂无评论