The authors present a Generative Adversarial Network (GAN) model that learns how to generate 3D models in their native format so that they can either be evaluated using complex simulation environments, or realized using methods such as additive manufacturing. Once initially trained, the GAN can create additional training data itself by generating new designs, evaluating them in a physics-based virtual environment, and adding the high performing ones to the training set. A case study involving a GAN model that is initially trained on 4045 3D aircraft models is used for demonstration, where the training data set updated with GAN-generated and evaluated designs, results in enhanced model generation, both in the geometric feasibility and performance of the designs. Z-tests on the performance scores of the generated aircraft models indicate a statistically significant improvement in the functionality of the generated models after three iterations of the training-evaluation process. In the case study, a number of techniques are explored to structure the generate-evaluate process in order to balance the need to generate feasible designs with the need for innovative designs.
Wearable robotics bring the opportunity to augment human capability and performance, be it through prosthetics, exoskeletons, or supernumerary robotic limbs. The latter concept allows enhancing human performance and assisting them in daily tasks. An important research question is, however, whether the use of such devices can lead to their eventual cognitive embodiment, allowing the user to adapt to them and use them seamlessly as any other limb of their own. This paper describes the creation of a platform to investigate this. Our supernumerary robotic 3 rd thumb was created to augment piano playing, allowing a pianist to press piano keys beyond their natural hand-span; thus leading to functional augmentation of their skills and the technical feasibility to play with 11 fingers. The robotic finger employs sensors, motors, and a human interfacing algorithm to control its movement in real-time. A proof of concept validation experiment has been conducted to show the effectiveness of the robotic finger in playing musical pieces on a grand piano, showing that naive users were able to use it for 11 finger play within a few hours.
A significant problem in Massive Open Online Courses (MOOCs) is the high rate of student dropout in these courses. An effective student dropout prediction model of MOOC courses can identify the factors responsible and provide insight on how to initiate interventions to increase student success in a MOOC. Different features and various approaches are available for the prediction of student dropout in MOOC courses. In this paper, the data derived from a self-paced math course, College Algebra and Problem Solving, offered on the MOOC platform Open edX partnering with Arizona State University (ASU) from 2016 to 2020 is considered. This paper presents a model to predict the dropout of students from a MOOC course given a set of features engineered from student daily learning progress. The Random Forest Model technique in Machine Learning (ML) is used in the prediction and is evaluated using validation metrics including accuracy, precision, recall, F1-score, Area Under the Curve (AUC), and Receiver Operating Characteristic (ROC) curve. The model developed can predict the dropout or continuation of students on any given day in the MOOC course with an accuracy of 87.5%, AUC of 94.5%, precision of 88%, recall of 87.5%, and F1-score of 87.5%, respectively. The contributing features and interactions were explained using Shapely values for the prediction of the model.
This work investigates surrogate modeling techniques for learning to approximate a computationally expensive function evaluation of 3D models. While in the past, 3D point clouds have been a data format that is too high dimensional for surrogate modeling, by leveraging advances in 3D object autoencoding neural networks, these point clouds can be mapped to a one-dimensional latent space. This leads to the fundamental research question: what surrogate modeling technique is most suitable for learning relationships between the 3D geometric features of the objects captured in the encoded latent vector and the physical phenomena captured in the evaluation software? Radial basis functions (RBFs), Kriging, and shallow 1D analogs of popular deep 2D image classification neural networks are investigated in this work. We find the nonintuitive result that departing from neural networks to decode latent representations of 3D objects into performance predictions is far more efficient than using a neural network decoder. In test cases using datasets of aircraft and watercraft 3D models, the non-neural network surrogate models achieve comparable accuracy to the neural network models. We find that an RBF surrogate model is able to approximate the lift and drag coefficients of 234 aircraft models with a mean absolute error of 1.97 × 10−3 and trains in only 3 seconds. Furthermore, the RBF surrogate model is able to rank a set of designs with an average percentile error of less than 8%. In comparison, a 1D ResNet achieves an average absolute error of 1.35 × 103 in 38 min for the same test case. We validate the comparable accuracy of the four techniques through a test case involving 214 3D watercraft models, but we also find that the distribution of the performance values of the data, in particular the presence of many outliers, has a significant negative impact on accuracy. These results contradict a common perception of neural networks as an efficient “one-size-fits-all” solution for learning black-box functions and suggests that even within systems that utilize multiple neural networks, potentially more efficient alternatives should be considered for each network in the system. Depending on the required accuracy of the application, this surrogate modeling approach could be used to approximate an expensive simulation software, or if the tolerance for error is low, it serves as a first pass which can narrow down the number of candidate designs to be analyzed more thoroughly.
In this paper, we present a method that uses a physics-based virtual environment to evaluate the feasibility of neural network-based generated designs. Deep learning models rely on large training data sets that are used for training. These training data sets are typically validated by human designers that have a conceptual understanding of the problem being solved. However, the requirement of human training data severely constrains the size and availability of training data for computer generated models due to the manual process of either creating or labeling such data sets. Furthermore, there may be misclassification errors that result from human labeling. To mitigate these challenges, we present a physics-based simulation environment that helps users discover correlations between the form of a generated design and the physical constraints that relate to its function. We hypothesize that training data that includes machine validated designs from a physics-based virtual environment will increase the probability of generative models creating functionally-feasible design concepts. A case study involving a generative model that is trained on over 70,000 human 2D boat sketches is used to test the hypothesis. Knowledge gained from testing this hypothesis will provide human designers with insights into the importance of training data in the resulting design solutions generated by deep neural networks.
This work presents a deep reinforcement learning (DRL) approach for procedural content generation (PCG) to automatically generate three-dimensional (3D) virtual environments that users can interact with. The primary objective of PCG methods is to algorithmically generate new content in order to improve user experience. Researchers have started exploring the use of machine learning (ML) methods to generate content. However, these approaches frequently implement supervised ML algorithms that require initial datasets to train their generative models. In contrast, RL algorithms do not require training data to be collected a priori since they take advantage of simulation to train their models. Considering the advantages of RL algorithms, this work presents a method that generates new 3D virtual environments by training an RL agent using a 3D simulation platform. This work extends the authors’ previous work and presents the results of a case study that supports the capability of the proposed method to generate new 3D virtual environments. The ability to automatically generate new content has the potential to maintain users’ engagement in a wide variety of applications such as virtual reality applications for education and training, and engineering conceptual design.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.