- Видео 44
- Просмотров 35 843
OMRON SINIC X
Япония
Добавлен 27 сен 2019
オムロン サイニックエックス株式会社では、世の中の変化の兆しとそこから生まれる社会的課題をいち早く捉え、解決のボトルネックとなる技術的課題との重なりから、本質的な研究上の問い、魅力的な研究課題を作り出すことを目指しています。社会的課題に根ざした研究課題を共有し、アカデミアとビジネスが本気で叡智を結集することで、社会を動かし人々のライフスタイルを革新する大きなインパクトが実現できるとの信念の下、研究と社会実装に向けたオープンイノベーションを進めています。
Comp-ACT: Learning Variable Compliance Control From a Few Demonstrations
Abstract: Automating dexterous, contact-rich manipulation tasks using rigid robots is a significant challenge in robotics. Rigid robots, defined by their actuation through position commands, face issues of excessive contact forces due to their inability to adapt to contact with the environment, potentially causing damage. While compliance control schemes have been introduced to mitigate these issues by controlling forces via external sensors, they are hampered by the need for fine-tuning task-specific controller parameters. Learning from Demonstrations (LfD) offers an intuitive alternative, allowing robots to learn manipulations through observed actions. In this work, we introduce a novel...
Просмотров: 687
Видео
Integrated Task and Motion Planning for Real-World Cooking Tasks(ICRA2024 Cooking Robotics Workshop)
Просмотров 3262 месяца назад
To fully realize robots in household environments, robots would need to be able to plan and execute a variety of tasks autonomously. However, task and motion planning for multi-step manipulation tasks is still an open challenge in robotics, particularly for long-horizon tasks in dynamic environments. This work proposes an integrated task and motion planning (TAMP) robotic framework for real-wor...
Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability
Просмотров 3623 месяца назад
This study tackles the representative yet challenging contact-rich peg-in-hole task of robotic assembly, using a soft wrist that can operate more safely and tolerate lower-frequency control signals than a rigid one. Previous studies often use a fully observable formulation, requiring external setups or estimators for the peg-to-hole pose. In contrast, we use a partially observable formulation a...
An Electromagnetism-Inspired Method for Estimating In-Grasp Torque from Visuotactile Sensors
Просмотров 3113 месяца назад
Tactile sensing has become a popular sensing modality for robot manipulators, due to the promise of providing robots with the ability to measure the rich contact information that gets transmitted through its sense of touch. Among the diverse range of information accessible from tactile sensors, torques transmitted from the grasped object to the fingers through extrinsic environmental contact ma...
Benchmarking Actor-Critic DRL Algorithm for Robotics Control with Action Constraints (ICRA 2024)
Просмотров 1413 месяца назад
A presentation video for "Benchmarking Actor-Critic Deep Reinforcement Learning Algorithm for Robotics Control with Action Constraints" in ICRA 2024 Project Page: omron-sinicx.github.io/action-constrained-RL-benchmark/ Paper: ieeexplore.ieee.org/document/10146410 github: github.com/omron-sinicx/action-constrained-RL-benchmark
Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding (ICLR 2024)
Просмотров 3644 месяца назад
Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding Tatsunori Taniai, Ryo Igarashi, Yuta Suzuki, Naoya Chiba, Kotaro Saito, Yoshitaka Ushiku, and Kanta Ono In The Twelfth International Conference on Learning Representations (ICLR 2024) Paper: openreview.net/forum?id=fxQiecl9HB Project page: omron-sinicx.github.io/crystalformer/
SliceIt! - A Dual Simulator Framework for Learning Robot Food Slicing.
Просмотров 2544 месяца назад
Abstract: Cooking robots can enhance the home experience by reducing the burden of daily chores. However, these robots must perform their tasks dexterously and safely in shared human environments, especially when handling dangerous tools such as kitchen knives. This study focuses on enabling a robot to autonomously and safely learn food-cutting tasks. More specifically, our goal is to enable a ...
ViLaIn: Vision-Language Interpreter for Robot Task Planning (ICRA2024)
Просмотров 5514 месяца назад
A movie presentation for "Vision-Language Interpreter for Robot Task Planning," ICRA2024. [paper] arxiv.org/abs/2311.00967 [github] github.com/omron-sinicx/ViLaIn
Swarm Body: Embodied Swarm Robots (Video Preview, 30sec)
Просмотров 554 месяца назад
Sosuke Ichihashi, So Kuroki, Mai Nishimura, Kazumi Kasaura, Takefumi Hiraki, Kazutoshi Tanaka, and Shigeo Yoshida. 2024. Swarm Body: Embodied Swarm Robots. In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI ’24), May 11-16, 2024, Honolulu, HI, USA. ACM, New York, NY, USA, 19 pages. doi.org/10.1145/3613904.3642870 Preprint (arxiv) arxiv.org/abs/2402.15830 Abstract Th...
Swarm Body: Embodied Swarm Robots
Просмотров 1,2 тыс.4 месяца назад
Sosuke Ichihashi, So Kuroki, Mai Nishimura, Kazumi Kasaura, Takefumi Hiraki, Kazutoshi Tanaka, and Shigeo Yoshida. 2024. Swarm Body: Embodied Swarm Robots. In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI ’24), May 11-16, 2024, Honolulu, HI, USA. ACM, New York, NY, USA, 19 pages. doi.org/10.1145/3613904.3642870 Preprint (arxiv) arxiv.org/abs/2402.15830 Abstract Th...
LfDT: Learning Dual-Arm Manipulation from Demonstration Translated from a Human and Robotic Arm
Просмотров 2329 месяцев назад
M. Kobayashi, J. Yamada, M. Hamaya, K. Tanaka, ``LfDT: Learning Dual-Arm Manipulation from Demonstration Translated from a Human and Robotic Arm,'' The 2023 IEEE-RAS International Conference on Humanoid Robots (Humanoids 2023), 2023.
Reference-based Dense Pose Estimation via Partial 3D Point Cloud Matching
Просмотров 1899 месяцев назад
ACM Multimedia 2023 Demo Track Paper.
When to Replan? An Adaptive Replanning Strategy for Autonomous Navigation
Просмотров 23010 месяцев назад
paper: arxiv.org/abs/2304.12046
Learning Robotic Assembly by Leveraging Physical Softness and Tactile Sensing
Просмотров 68911 месяцев назад
Learning Robotic Assembly by Leveraging Physical Softness and Tactile Sensing
Learning Robotic Powder Weighing from Simulation for Laboratory Automation
Просмотров 48111 месяцев назад
Learning Robotic Powder Weighing from Simulation for Laboratory Automation
Robotic Powder Grinding with Audio-Visual Feedback for Laboratory Automation in Materials Science
Просмотров 41611 месяцев назад
Robotic Powder Grinding with Audio-Visual Feedback for Laboratory Automation in Materials Science
(IJCV) View Biridification in the Crowd: Ground-Plane Localization from Perceived Movements
Просмотров 97Год назад
(IJCV) View Biridification in the Crowd: Ground-Plane Localization from Perceived Movements
Robotic Powder Grinding with a Soft Jig for Laboratory Automation in Material Science
Просмотров 358Год назад
Robotic Powder Grinding with a Soft Jig for Laboratory Automation in Material Science
ViewBirdiformer: Learning to recover crowd trajectories and ego-motion from an ego-centric view
Просмотров 203Год назад
ViewBirdiformer: Learning to recover crowd trajectories and ego-motion from an ego-centric view
Learning Food Picking without Food: Fracture Anticipation by Breaking Reusable Fragile Objects
Просмотров 210Год назад
Learning Food Picking without Food: Fracture Anticipation by Breaking Reusable Fragile Objects
[Presentation] Learning Food Picking without Food
Просмотров 67Год назад
[Presentation] Learning Food Picking without Food
Risk-aware Path Planning for Planetary Rovers on Heterogeneous Terrains (ICRA 2023)
Просмотров 296Год назад
Risk-aware Path Planning for Planetary Rovers on Heterogeneous Terrains (ICRA 2023)
Twist Snake: Plastic table-top cable-driven robotic arm with all motors located at the base link
Просмотров 16 тыс.Год назад
Twist Snake: Plastic table-top cable-driven robotic arm with all motors located at the base link
Simulation: learning robotic contact juggling
Просмотров 81Год назад
Simulation: learning robotic contact juggling
Presentation: Learning Robotic Contact Juggling
Просмотров 112Год назад
Presentation: Learning Robotic Contact Juggling
Body of a high-speed anthropomorphic table-tennis robot with a linkage mechanism
Просмотров 3 тыс.Год назад
Body of a high-speed anthropomorphic table-tennis robot with a linkage mechanism
TRANS-AM: Transfer Learning by Aggregating Dynamics Models for Soft Robotic Assembly
Просмотров 70Год назад
TRANS-AM: Transfer Learning by Aggregating Dynamics Models for Soft Robotic Assembly
A Compact, Cable driven, Activatable Soft Wrist with Six Degrees of Freedom for Assembly Tasks
Просмотров 255Год назад
A Compact, Cable driven, Activatable Soft Wrist with Six Degrees of Freedom for Assembly Tasks
Quasistatic contact-rich manipulation via linear complementarity quadratic programming (IROS 2022)
Просмотров 300Год назад
Quasistatic contact-rich manipulation via linear complementarity quadratic programming (IROS 2022)
this is amazing an relatively simple, with good performance, thank you for this!
yes!!!
I want to see a fully functional humanoid robot comprised of a single torso unit with 50 servo motors, and all movement cable driven. I believe you are almost there! #stringbot
Amazing, I was searching to see if someone has done this! Very cool to see it working.
Duel-Arm Manipulation is an excellent advent of cutting edge robotics, and aligns with the caliber of developments in this Nexus Phase of current Robotics.
Hi, nice robotic arm. I made one with a similar principle, but it looks completely different. May I ask, if the source code is available and how you did the inverse kinematics ?
My kittens are learning to climb in a tree and to descend from it. What a time to be alive.
both links dead
Nice!
Nice work! I'm really interested in this! There is a way that we can talk about this project? It's possible to capture more complex maneuvers? There is a way that we can collaborate in some way? Thanks for your time! Keep Juggling Dídac
We plan on releasing an OpenAI gym environment to learn more complex maneuvers. Feel free to email us with details on your ideas for collaboration!
@@omronsinicx9931 Thank you. But I have not yet found a third-party environment relating to diabolo under this url: github.com/openai/gym/blob/master/docs/environments.md#third-party-environments I was wondering is this url the right place to look for a possible release? Thank you for your time.
@@frycomfort4002 There has been no release yet, but we are working on it and will announce progress on our website and social networks. Do get in touch if you have a specific interest and wish to collaborate! -> contact@sinicx.com
What a time to be alive
Wow Devwrat! Such cool work! Congratulations!