Topics





〈Name of award and short explanation about the award〉
IEEE Robotics and Automation Society (RAS) Japan Joint Chapter Young Award

The International Conference on Robotics and Automation (ICRA) is the IEEE Robotics and Automation Society's biggest conference and one of the leading international forums for robotics researchers. IEEE Robotics and Automation Society (RAS) Japan Joint Chapter Young Award, which is supported from IEEE Japan Council since 2003, targets the Japanese students who are the ICRA presenter of that year. Novelty, usability, presentation and total count are items of evaluation. In this year, the five most outstanding students were commended.

About awarded research〉
This research proposes a novel method for estimating 3D information from a 2D acoustic image. By realizing this, it becomes possible to understand the underwater environment more accurately even in turbid water. It is useful for underwater robot navigation.
In the awarded research, it is difficult for 3D reconstruction due to the unique projection principle of acoustic cameras. In particular, each pixel of the image corresponds to multiple missing elevation angles. This study proposes a pseudo front view depth for the first time which learned by a convolutional neural network. The dataset is generated from the simulator and the realistic data is constructed by a generative adversarial network. It outperforms previous methods.

〈Your impression & future plan〉
I am honored and pleased to receive the award. I would like to express my deep gratitude to the professors and collaborative researchers. In the future, I would like to develop the method and strive to contribute to the world.