no code implementations • 20 May 2024 • Takuzumi Nishio, Moju Zhao, Kei Okada, Masayuki Inaba
Third, we propose a motion planning method based on inverse kinematics (IK), considering specific constraints to the proposed RDMs such as perching force.
no code implementations • 6 May 2024 • Kento Kawaharazuka, Kei Okada, Masayuki Inaba
In this study, we present an implementation strategy for a robot that performs peg transfer tasks in Fundamentals of Laparoscopic Surgery (FLS) via imitation learning, aimed at the development of an autonomous robot for laparoscopic surgery.
no code implementations • 5 May 2024 • Hirokazu Ishida, Naoki Hiraoka, Kei Okada, Masayuki Inaba
During the query phase, these classifiers are utilized to select an experience that is expected to be adaptable for a given problem.
no code implementations • 13 Mar 2024 • Kento Kawaharazuka, Naoaki Kanazawa, Yoshiki Obinata, Kei Okada, Masayuki Inaba
By using models that can compute the similarity between images and texts continuously over time, we can capture the state changes of food while cooking.
1 code implementation • 9 May 2021 • Moju Zhao, Kei Okada, Masayuki Inaba
In this new architecture, features of the template image is processed by a self-attention module in the encoder part to learn strong context information, which is then sent to the decoder part to compute cross-attention with the search image features processed by another self-attention module.
no code implementations • 9 Dec 2020 • Iori Yanokura, Naoki Wake, Kazuhiro Sasabuchi, Katsushi Ikeuchi, Masayuki Inaba
We propose a Learning-from-Observation framework that splits and understands a video of a human demonstration with verbal instructions to extract accurate action sequences.
no code implementations • 21 Jan 2020 • Kentaro Wada, Kei Okada, Masayuki Inaba
We present joint learning of instance and semantic segmentation for visible and occluded region masks.
no code implementations • 21 Jan 2020 • Kentaro Wada, Shingo Kitagawa, Kei Okada, Masayuki Inaba
We present a robotic system for picking a target from a pile of objects that is capable of finding and grasping the target object by removing obstacles in the appropriate order.
no code implementations • 16 Jan 2020 • Kentaro Wada, Kei Okada, Masayuki Inaba
Probabilistic 3D map has been applied to object segmentation with multiple camera viewpoints, however, conventional methods lack of real-time efficiency and functionality of multilabel object mapping.
no code implementations • 15 Jan 2020 • Kentaro Wada, Masaki Murooka, Kei Okada, Masayuki Inaba
Picking objects in a narrow space such as shelf bins is an important task for humanoid to extract target object from environment.