no code implementations • 13 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.
1 code implementation • 20 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.
no code implementations • 1 Dec 2022 • Wentai Zhang, Joe Joseph, Yue Yin, Liuyue Xie, Tomotake Furuhata, Soji Yamakawa, Kenji Shimada, Levent Burak Kara
We test our framework in the context of semantic segmentation of text, dimension and, contour components in engineering drawings.
1 code implementation • 17 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.
1 code implementation • 15 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.
1 code implementation • 14 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.
no code implementations • 12 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.
1 code implementation • Conference on Robot Learning 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.
Ranked #26 on Semantic Segmentation on S3DIS
1 code implementation • 14 Oct 2020 • Zhefan Xu, Di Deng, Kenji Shimada
Autonomous exploration requires robots to generate informative trajectories iteratively.
no code implementations • 18 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.
1 code implementation • 20 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.
no code implementations • 16 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.
no code implementations • 8 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.