Tatsuya Kamijo (@tatsukamijo)

Pinned

T

Tatsuya Kamijo@tatsukamijo · Jul 1, 2024

Happy to share that our paper has been accepted to #IROS2024. We introduce Comp-ACT, an imitation learning method for position-controlled robots to learn variable compliance control for contact-rich manipulation by predicting both Cartesian EE pose and stiffness parameters.

3

23

121

43

36.0K

Tatsuya Kamijo Retweeted

K

Kento Kawaharazuka / 河原塚健人@KKawaharazuka · Jul 22

🚀Great news! We’re organizing a #CoRL2025 workshop "Open-Source Hardware in the Era of Robot Learning"! Building, using, or curious about open hardware? Let’s come together and talk! 📅 Papers due: 08/20/2025 (TBD) 🌐 open-hardware-robots.github.io/CoRL2025/

1

26

102

31

14.0K

Tatsuya Kamijo Retweeted

T

Tatsuya Kamijo@tatsukamijo · Jul 16

上記資料の前半パート（知能ロボットシステムエンジニアリング第4回 ROS 2入門（1/2））の資料もDocswellで公開しました．こっちはスライドです． - パッケージング入門：巨人の方に乗る - ROS 2入門：基礎知識と実践という内容です． docswell.com/s/tatsukamijo/…

0

11

29

14

1.0K

Tatsuya Kamijo Retweeted

T

TRAIL (Tokyo Robotics and AI Lab)@LeRobotHackathon@trail_ut · Jun 14

Robot sushi bar is open!! 🍣 #LeRobotWorldwideHackathon #lerobot

1

16

55

6

4.0K

T

Tatsuya Kamijo@tatsukamijo · Mar 21

新しく開講した知能ロボティクス講座の講師を務めます．よろしくお願いします．

東東京大学松尾・岩澤研究室@Matsuo_Lab · Mar 21

【新講座開講】松尾研「Physical AI」募集開始！ロボット×AIをエンジニアリングの視点から、ロボティクスの基礎からAIモデルの活用までを体系的に習得する全12回の講義です。ロボットの動作原理や制御技術を学びながら、AIを活用したロボットシステムの設計・開発・運用までを実践的に学習します。…

1

7

76

4

10.0K

Tatsuya Kamijo Retweeted

K

Kai Arulkumaran@kaixhin · Nov 1

Nice work from @tatsukamijo on blending the latest in IL for robotics and traditional robotics methods (compliance) Totally agree that contact-rich manipulation is a fundamental challenge we should be retiring working on!

0

3

18

2

2.0K

T

Tatsuya Kamijo@tatsukamijo · Oct 29

Our latest work on imitation learning for contact-rich manipulation with rigid robots! Thanks to the hard work of @mkakram @tatsukamijo @mh69543540 ! Check the supplementary video here: youtu.be/77tUVfyqHrw

RRobotics Papers@OWW · Oct 28

Learning Diffusion Policies from Demonstrations For Compliant Contact-rich Manipulation. arxiv.org/abs/2410.19235

0

5

7

0

2.0K

T

Tatsuya Kamijo@tatsukamijo · Oct 25

Honored to receive the Best Poster Award (2nd) at the workshop @irosAIWS at #IROS2024 !

CCristian Beltrán@cambel07 · Oct 25

I had a great time at #IROS2024 We were awarded as the 2nd best poster in the Collecting, Managing, and Utilizing Embodied Robotics workshop! 🎉 Thank you to my co-authors for the good work! @tatsukamijo @mh69543540

3

32

0

4.0K

T

Tatsuya Kamijo@tatsukamijo · Oct 18

Our presentation starts at 10.30 AM in Room 3! #IROS2024

TTatsuya Kamijo@tatsukamijo · Jul 1, 2024

Happy to share that our paper has been accepted to #IROS2024. We introduce Comp-ACT, an imitation learning method for position-controlled robots to learn variable compliance control for contact-rich manipulation by predicting both Cartesian EE pose and stiffness parameters.

0

1

7

0

1.0K

Tatsuya Kamijo Retweeted

Y

Yifan Hou@YifanHou2 · Oct 15

Can robots learn to manipulate with both care and precision? Introducing Adaptive Compliance Policy, a framework to dynamically adjust robot compliance both spatially and temporally for given manipulation tasks from human demonstrations. Full detail at adaptive-compliance.github.io

9

29

127

50

34.0K

Tatsuya Kamijo Retweeted

O

OMRON SINIC X (OSX)@omron_sinicx · Oct 11

オムロンサイニックエックスは、#IROS2024 で最新の研究成果を7件発表します。さらに、田中一敏(@sports_robots)らの研究論文は「IROS Best Entertainment and Amusement Paper Award sponsored by JTCF」のFinalistsに選出されています。 omron.com/sinicx/activit…

1

11

48

10

6.0K

T

Tatsuya Kamijo@tatsukamijo · Oct 13

I will give an oral presentation of Comp-ACT at #IROS2024 in Abu Dabhi on Friday (Room3, FrAT03.03). Let's discuss the future of learning dexterous & contact-rich manipulation!

TTatsuya Kamijo@tatsukamijo · Jul 1, 2024

Happy to share that our paper has been accepted to #IROS2024. We introduce Comp-ACT, an imitation learning method for position-controlled robots to learn variable compliance control for contact-rich manipulation by predicting both Cartesian EE pose and stiffness parameters.

0

6

50

13

6.0K

Tatsuya Kamijo Retweeted

N

Naoaki Kanazawa / 金沢直晃@Naoaki_Kanazawa · Oct 7

Our paper "Real-World Cooking Robot System from Recipes Based on Food State Recognition Using Foundation Models and PDDL" has been accepted at Advanced Robotics! Website - kanazawanaoaki.github.io/cook-from-reci…

2

21

112

66

29.0K

T

Tatsuya Kamijo@tatsukamijo · Oct 6

今学期も一緒にかしこいロボット作りましょうー

東東京大学松尾・岩澤研究室@Matsuo_Lab · Oct 4

【東大学部後期/大学院生向け・参加者募集】松尾・岩澤研ではプロジェクト演習型講義の1つとして「人工知能応用プロジェクト」を開講します．人工知能技術を応用したロボット開発を行うチーム開発活動への参加に対して単位が認定される講義です（10/8応募〆切）． weblab.t.u-tokyo.ac.jp/education/crea…

1

3

13

1

3.0K

Tatsuya Kamijo Retweeted

C

C Zhang@ChongZitaZhang · Sep 27

from arxiv.org/abs/2409.17731

10

141

592

142

80.0K

Tatsuya Kamijo Retweeted

O

OMRON SINIC X (OSX)@omron_sinicx · Sep 9

弊社 Principal Investigator 濵屋政志(@mh69543540)らの研究グループによる、やわらかい手首で部品挿入時の大きな位置ズレを吸収するソフトロボット”Saguri-bot（サグリボット）”を紹介します。詳細はこちら： omron.com/sinicx/activit…

0

14

63

17

6.0K

T

Tatsuya Kamijo@tatsukamijo · Jul 1, 2024

学部4年次にOSX @omron_sinicx で行っていた研究がIROS2024に採択されました！硬い位置制御ロボットで可変コンプライアンス制御を模倣学習するための手法Comp-ACTを提案しています．双腕での挿入，顔文字を描かせる，ワイピングなどの難しいタスクを20-30回の教示から学習します（動画参照）．

TTatsuya Kamijo@tatsukamijo · Jul 1, 2024

Happy to share that our paper has been accepted to #IROS2024. We introduce Comp-ACT, an imitation learning method for position-controlled robots to learn variable compliance control for contact-rich manipulation by predicting both Cartesian EE pose and stiffness parameters.

5

14

107

14

17.0K