| 研究課題/領域番号 |
20KK0086
|
|---|
| 研究種目 |
国際共同研究加速基金(国際共同研究強化(B))
|
| 配分区分 | 基金 |
|---|
| 審査区分 |
中区分20:機械力学、ロボティクスおよびその関連分野
|
|---|
| 研究機関 | 大阪大学 |
|---|
研究代表者 |
ラサミー ポチャラ 大阪大学, サイバーメディアセンター, 招へい教員 (50772448)
|
|---|
| 研究分担者 |
浦西 友樹 大阪大学, サイバーメディアセンター, 准教授 (00533738)
ORLOSKY JASON 大阪大学, サイバーメディアセンター, 特任准教授(常勤) (10815111)
三輪 昌史 徳島大学, 大学院社会産業理工学研究部(理工学域), 准教授 (40283957)
竹村 治雄 大阪大学, サイバーメディアセンター, 教授 (60263430)
|
|---|
| 研究期間 (年度) |
2020-10-27 – 2024-03-31
|
| 研究課題ステータス |
交付 (2022年度)
|
| 配分額 *注記 |
18,720千円 (直接経費: 14,400千円、間接経費: 4,320千円)
2022年度: 1,560千円 (直接経費: 1,200千円、間接経費: 360千円)
2021年度: 2,600千円 (直接経費: 2,000千円、間接経費: 600千円)
2020年度: 14,560千円 (直接経費: 11,200千円、間接経費: 3,360千円)
|
|---|
| キーワード | ATA mapping / point cloud estimation / panoptic / transition / ATA mechanic / docking station / releasing mechanism / fire blanket / aerial robot / aquatic robot / seamless transition / multi-legged robot / ATA / Aerial / Terrestrial / Aquatic |
|---|
| 研究開始時の研究の概要 |
We propose Aerial-Terrestrial-Aquatic Robots (ATA-Robots) that are capable of search and rescue in an ATA Extreme Environment (specifically a flooded cave) extreme conditions such as zero visibility, strong disturbances from water/wind flow and strong waves at the water’s surface.
We will develop new concept of ATA Control, ATA Sensing and ATA Interface concept to enable robot to have seamless aerial-terrestrial-aquatic transition. The dataset will be collected at several cave in the world for training testing and optimization.
|
| 研究実績の概要 |
This year, we completed a major part of our project, focusing on ATA mapping. To estimate point clouds during aerial-aquatic transitions, we developed a new multi-box interpolation method. We based our proposed method on studying the noise characteristics of aerial and aquatic point clouds. We also developed an image processing technique to predict whether we should fuse point clouds or not. This allows the robot to avoid collisions during transitions. We mapped the environment using a thermal camera, which helps the robot to see in dark underwater areas by developed a machine learning-based panoptic perception-based generative adversarial network for thermal-to-color image translation.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
We have been able to advance the development of ATA mapping in Japan, specifically in several domestic caves. Despite the challenges posed by Covid-19, we were unable to conduct experiments abroad as planned. However, we have successfully conducted experiments in local caves in Japan and we hope to conduct experiments abroad by the end of this year.
|
| 今後の研究の推進方策 |
Our main focus this year is the development of the ATA control part for the ATA robot. Our goal is to design a robot that can adapt its leg to allow for smoother movement from aquatic to aerial environments. First, we will conduct simulations to verify the control algorithm. Later, we plan to test the robot in an indoor pool and eventually move on to an outdoor pool.
Additionally, we have a student who is interested in using a thermal camera in different scenarios. As a result, we are planning to improve ATA mapping by implementing an active water jet.
|
