Search Results for author: Kenji Shimada

Found 13 papers, 7 papers with code

Improving Deep Learning-based Defect Detection on Window Frames with Image Processing Strategies

no code implementations13 Sep 2023 Jorge Vasquez, Hemant K. Sharma, Tomotake Furuhata, Kenji Shimada

The paper proposes a new defect detection pipeline called InspectNet (IPT-enhanced UNET) that includes the best combination of image enhancement and augmentation techniques for pre-processing the dataset and a Unet model tuned for window frame defect detection and segmentation.

Defect Detection Image Augmentation +1

A vision-based autonomous UAV inspection framework for unknown tunnel construction sites with dynamic obstacles

1 code implementation20 Jan 2023 Zhefan Xu, Baihan Chen, Xiaoyang Zhan, Yumeng Xiu, Christopher Suzuki, Kenji Shimada

Besides, our framework contains a novel dynamic map module that can simultaneously track dynamic obstacles and represent static obstacles based on an RGB-D camera.

Navigate

A real-time dynamic obstacle tracking and mapping system for UAV navigation and collision avoidance with an RGB-D camera

1 code implementation17 Sep 2022 Zhefan Xu, Xiaoyang Zhan, Baihan Chen, Yumeng Xiu, Chenhao Yang, Kenji Shimada

Although the popular voxel-based mapping methods can efficiently represent 3D obstacles with arbitrarily complex shapes, they can hardly distinguish between static and dynamic obstacles, leading to the limited performance of obstacle avoidance.

Autonomous Driving Collision Avoidance +1

Vision-aided UAV navigation and dynamic obstacle avoidance using gradient-based B-spline trajectory optimization

1 code implementation15 Sep 2022 Zhefan Xu, Yumeng Xiu, Xiaoyang Zhan, Baihan Chen, Kenji Shimada

Although they have shown success in static environments, due to the limitation of map representation, those methods cannot reliably handle static and dynamic obstacles simultaneously.

Navigate

DPMPC-Planner: A real-time UAV trajectory planning framework for complex static environments with dynamic obstacles

1 code implementation14 Sep 2021 Zhefan Xu, Di Deng, Yiping Dong, Kenji Shimada

Although plenty of recent works achieve safe navigation in complex static environments with sophisticated mapping algorithms, such as occupancy map and ESDF map, these methods cannot reliably handle dynamic environments due to the mapping limitation from moving obstacles.

Model Predictive Control Navigate +1

Airfoil GAN: Encoding and Synthesizing Airfoils for Aerodynamic Shape Optimization

no code implementations12 Jan 2021 Yuyang Wang, Kenji Shimada, Amir Barati Farimani

Our model can (1) encode the existing airfoil into a latent vector and reconstruct the airfoil from that, (2) generate novel airfoils by randomly sampling the latent vectors and mapping the vectors to the airfoil coordinate domain, and (3) synthesize airfoils with desired aerodynamic properties by optimizing learned features via a genetic algorithm.

Generative Adversarial Network

Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation

no code implementations18 Sep 2020 Liuyue Xie, Tomotake Furuhata, Kenji Shimada

We present MuGNet, a memory-efficient, end-to-end graph neural network framework to perform semantic segmentation on large-scale pointclouds.

Graph Neural Network Segmentation +1

A Deep Reinforcement Learning Approach for Global Routing

1 code implementation20 Jun 2019 Haiguang Liao, Wentai Zhang, Xuliang Dong, Barnabas Poczos, Kenji Shimada, Levent Burak Kara

At the heart of the proposed method is deep reinforcement learning that enables an agent to produce an optimal policy for routing based on the variety of problems it is presented with leveraging the conjoint optimization mechanism of deep reinforcement learning.

reinforcement-learning Reinforcement Learning (RL)

3D Shape Synthesis for Conceptual Design and Optimization Using Variational Autoencoders

no code implementations16 Apr 2019 Wentai Zhang, Zhangsihao Yang, Haoliang Jiang, Suyash Nigam, Soji Yamakawa, Tomotake Furuhata, Kenji Shimada, Levent Burak Kara

We propose a data-driven 3D shape design method that can learn a generative model from a corpus of existing designs, and use this model to produce a wide range of new designs.

3D Shape Representation Decoder

Data-driven Upsampling of Point Clouds

no code implementations8 Jul 2018 Wentai Zhang, Haoliang Jiang, Zhangsihao Yang, Soji Yamakawa, Kenji Shimada, Levent Burak Kara

High quality upsampling of sparse 3D point clouds is critically useful for a wide range of geometric operations such as reconstruction, rendering, meshing, and analysis.

Cannot find the paper you are looking for? You can Submit a new open access paper.