Showing papers by "Alan Liu published in 2022"

Online Path Planning Framework for UAV in Rural Areas

Abstract: A motion strategy plays an important role in supporting autonomous Unmanned Aerial Vehicle (UAV) movement. Many studies have been conducted to improve the motion frameworks in terms of its robustness, safety and performance. Most of them worked on the prior known maps scenario where the area information was collected by Global Positioning System (GPS) and satellite cameras. Even though the scheme can provide high quality map, the computation of motion planning remains dependent on the communication signal. In the rural areas such as forests and mountains, where communication signal does not perform well, unclear and noisy terrain maps can be generated and lead to mission failure. Therefore, it is significant that an alternative framework to enhance autonomous UAV motion performance in these certain conditions should be developed. Our work focuses on developing a high performance path planner for autonomous UAV motion when communication signal does not work well in rural areas. The search mission problem in forest terrain has been implemented in 3D simulation as an evaluation. By conducting a simulation process repeatedly with different test cases for positions, time constraints, flight speed (3-11 m/s) and flight range, our path planning framework can achieve completeness between 90-100% and better performance compared to others.

What Everyone Says: Public Perceptions of the Humanities in the Media

Abstract: Abstract Using computational means to understand patterns in how the humanities are mentioned in U.S. journalism, the WhatEvery1Says project brings into focus challenging problems in the perception of the humanities. This essay reports on the project's findings and some of the further questions that emerged from them. For example, how does the “humanities crisis” appear among the many crises of our time? Why do the humanities figure so often in connection with concrete, ordinary life yet also seem abstract in value? How can more of the substance of humanistic research be communicated as opposed to appearing as just academic business? And why is there so little focus in the media on how underrepresented populations are positioned in relation to the humanities by comparison to science and social, political, or economic issues? The essay concludes by recommending that the humanities reframe their crisis as part of larger human crises requiring multidisciplinary “grand challenge” approaches.

Effective Construction of a Reflection Angle Prediction Model for Reflectarrays Using the Hadamard Product Self-Attention Mechanism

Abstract: In this paper, we propose an efficient method for constructing a model which predicts the angle of a beam reflected by a reflectarray. The method includes an effective calculation method for preprocessing phase data and a design of a suitable deep learning model. We use the vibration displacement data instead of phase data with feature scaling. We claim that the numerical value of vibration displacement data is more meaningful than original numerical values of phase data. Referring to the transformer model originally proposed in natural language processing, we propose a simple network mechanism, the Hadamard product self-attention mechanism, for regression analysis of reflectarray antenna. We compare the results of experiments on the proposed method to the models with fully-connect neural network and Convolutional Neural Network, respectively. The experiment results show that methods and mechanism proposed by this research have a significant improvement in the accuracy of predicting the reflection angle, and the model convergence speed is also faster. The model can be applied to design a reflectarray to meet the requirements of a given pair of incoming and outgoing beam angles.