Research

I have been engaged in research and technology development related to autonomous/remote-controlled intelligent robots and human support systems (such as mobility and manipulation) at universities, private companies, and in robot competitions. (To be updated)

Imitation Learning for Robot Arm

ALPHA-α and Bi-ACT Are All You Need: Importance of Position and Force Control and Information in Imitation Learning for Unimanual and Bimanual Robotic Manipulation

Masato Kobayashi , Thanpimon Buamanee, Takumi Kobayashi, Osaka University
ALPHA
ALPHA-α and Bi-ACT Are All You Need: Importance of Position and Force Control and Information in Imitation Learning for Unimanual and Bimanual Robotic Manipulation, arXiv, 2024.
*paper, *website

DABI: Evaluation of Data Augmentation Methods Using Downsampling in Bilateral Control-Based Imitation Learning with Images

Masato Kobayashi , Thanpimon Buamanee, Yuki Uranishi, Osaka University
DABI
DABI: Evaluation of Data Augmentation Methods Using Downsampling in Bilateral Control-Based Imitation Learning with Images, arXiv, 2024.
*paper, *website

ILBiT: Imitation Learning for Robot Using Position and Torque Information based on Bilateral Control with Transformer

Masato Kobayashi , Thanpimon Buamanee, Yuki Uranishi, Haruo Takemura, Osaka University
ILBiT
ILBiT: Imitation Learning for Robot Using Position and Torque Information based on Bilateral Control with Transformer, arXiv, 2024.
*paper, *website

Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with Transformer
Thanpimon Buamanee*, Masato Kobayashi* , Yuki Uranishi, Haruo Takemura, Osaka University, *Co-first authors equally contributed to this work.
Bi-ACT
Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with Transformer, arXiv, 2024.
*paper, *website
LfDT:Learning Dual-Arm Manipulation from Demonstration Translated from a Human and Robotic Arm

Masato Kobayashi 1*, Jun Yamada 2*, Masashi Hamaya 3, Kazutoshi Tanaka 3 1 Osaka University, 2 University of Oxford, 3 OMRON SINIC X Corporation, * work done as an intern at OMRON SINIC and Co-first authors equally contributed to this work.
LfDT
LfDT: Learning Dual-Arm Manipulation from Demonstration Translated from a Human and Robotic Arm, IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids), 2023.
*paper, *website

MR Robot Interface

MRNaB: Mixed Reality-based Robot Navigation Interface using Optical-see-through MR-beacon
Eduardo Iglesius*, Masato Kobayashi* , Yuki Uranishi, Haruo Takemura, Osaka University, *Co-first authors equally contributed to this work.
MRNaB
MRNaB: Mixed Reality-based Robot Navigation Interface using Optical-see-through MR-beacon, arXiv, 2024.
*paper, *website

Intelligent Robot System

TRAIL

Chikaha Tsuji, Dai Komukai, Mimo Shirasaka, Hikaru Wada, Tsunekazu Omija, Aoi Horo, Daiki Furuta, Saki Yamaguchi, So Ikoma, Soshi Tsunashima, Masato Kobayashi, Koki Ishimoto, Yuya Ikeda, Tatsuya Matsushima, Yusuke Iwasawa, Yutaka Matsuo
TRAIL
TRAIL Team Description Paper for RoboCup@Home 2023, arXiv, 2023.
*paper, *website

OUXT Polaris: Autonomous Navigation System for the 2022 Maritime RobotX Challenge

Kenta Okamoto, Akihisa Nagata, Kyoma Arai, Yusei Nagao, Tatsuki Nishimura, Kento Hirogaki, Shunya Tanaka, Masato Kobayashi, Tatsuya Sanada, Masaya Kataoka
OUXT Polaris
OUXT Polaris: Autonomous Navigation System for the 2022 Maritime RobotX Challenge, arXiv, 2023.
*paper, *website

Autonomous Mobile Robot

DWV (Local Path Planning Considering Dynamic Obstacles)

Masato Kobayashi 1, Naoki Motoi 2, 1 Osaka University, 2 Kobe University
DWV
Local Path Planning: Dynamic Window Approach With Virtual Manipulators Considering Dynamic Obstacles, IEEE Access, 2022.
*paper, *website

BSL (Navigation Method Considering Blind Spots)

Masato Kobayashi 1, Naoki Motoi 2, 1 Osaka University, 2 Kobe University
BSL
BSL: Navigation Method Considering Blind Spots Based on ROS Navigation Stack and Blind Spots Layer for Mobile Robot, IEEE Transactions on Industry Applications, 2023.
*paper, *website

DQDWA (Local Path Planning Considering Congestion Environments)

Masato Kobayashi 1, Hiroka Zushi 2, Tomoaki Nkamura 2, Naoki Motoi 2, 1 Osaka University, 2 Kobe University
DQDWA
Local Path Planning: Dynamic Window Approach With Q-Learning Considering Congestion Environments for Mobile Robot, IEEE Access, 2023.
*paper, *website