1,448 Hits in 5.0 sec

A Survey of Multifingered Robotic Manipulation: Biological Results, Structural Evolvements, and Learning Methods

Yinlin Li, Peng Wang, Rui Li, Mo Tao, Zhiyong Liu, Hong Qiao
2022 Frontiers in Neurorobotics  
Third, we report the recent progress of various learning-based multifingered manipulation methods, including but not limited to reinforcement learning, imitation learning, and other sub-class methods.  ...  Multifingered robotic hands (usually referred to as dexterous hands) are designed to achieve human-level or human-like manipulations for robots or as prostheses for the disabled.  ...  to support research in dexterous manipulation Ahn et al. (2019) D'Claw 3/9/9 127 × 127 × 226 mm N/A N/A 2019 A platform for exploring learning-based techniques in dexterous manipulation Townsend (2000  ... 
doi:10.3389/fnbot.2022.843267 pmid:35574228 pmcid:PMC9097019 fatcat:o4w5y36ej5hzhpjm6tpv2x4vf4

Learning for a Robot: Deep Reinforcement Learning, Imitation Learning, Transfer Learning

Jiang Hua, Liangcai Zeng, Gongfa Li, Zhaojie Ju
2021 Sensors  
Dexterous manipulation of the robot is an important part of realizing intelligence, but manipulators can only perform simple tasks such as sorting and packing in a structured environment.  ...  Furthermore, deep reinforcement learning, imitation learning, and transfer learning in robot control are discussed in detail.  ...  They are easy to implement and work very well for policies with a small number of parameters.  ... 
doi:10.3390/s21041278 pmid:33670109 pmcid:PMC7916895 fatcat:ehzsevmddfg5zlyc2wms6yuhui

Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost [article]

Henry Zhu, Abhishek Gupta, Aravind Rajeswaran, Sergey Levine and Vikash Kumar
2018 arXiv   pre-print
Dexterous multi-fingered robotic hands can perform a wide range of manipulation skills, making them an appealing component for general-purpose robotic manipulators.  ...  In this work, we propose deep reinforcement learning (deep RL) as a scalable solution for learning complex, contact rich behaviors with multi-fingered hands.  ...  In this work, we study the use of model-free deep reinforcement learning algorithms to learn manipulation policies for dexterous multi-finger hands.  ... 
arXiv:1810.06045v1 fatcat:h5dm7rvxj5h5lgkihznx6yelhu

Extensive Human Training for Robot Skill Synthesis: Validation on a Robotic Hand

Erhan Oztop, Li-Heng Lin, Mitsuo Kawato, Gordon Cheng
2007 Engineering of Complex Computer Systems (ICECCS), Proceedings of the IEEE International Conference on  
We propose a framework for skill synthesis for robots that exploits the human capacity to learn novel control tasks.  ...  Once this stage is achieved, the dexterity on a task exhibited with the new external limb -the robot-can be used for designing controllers for the task under consideration.  ...  So a total of seven sensors were used (three for base and four for fingers, see Figure 4 ) A.  ... 
doi:10.1109/robot.2007.363581 dblp:conf/icra/OztopLKC07 fatcat:p5qxzyf7ofh5xpdbtrttptclli

A Modular Approach to the Embodiment of Hand Motions from Human Demonstrations [article]

Alexander Fabisch, Melvin Laux, Dennis Marschner, Johannes Brust
2022 arXiv   pre-print
We propose a modular framework with an automatic embodiment mapping to transfer human hand motions to robotic systems and use motion capture to record human motion.  ...  We evaluate our approach on eight challenging tasks, in which a robotic arm with a mounted robotic hand needs to grasp and manipulate deformable objects or small, fragile material.  ...  The motion capture setup was developed in collaboration with Lisa Gutzeit, supported by a grant from the German Federal Ministry for Economic Affairs and Energy (BMWi, FKZ 50 RA 2023).  ... 
arXiv:2203.02778v1 fatcat:q4565v3gobgytmcatx4gnp4elq

Challenges and Outlook in Robotic Manipulation of Deformable Objects [article]

Jihong Zhu, Andrea Cherubini, Claire Dune, David Navarro-Alarcon, Farshid Alambeigi, Dmitry Berenson, Fanny Ficuciello, Kensuke Harada, Jens Kober, Xiang Li, Jia Pan, Wenzhen Yuan (+1 others)
2021 arXiv   pre-print
A particular focus of our paper lies in the discussions of these challenges and proposing future directions of research.  ...  However, compared to rigid object manipulation, the manipulation of deformable objects is considerably more complex, and is still an open research problem.  ...  Research can roughly be categorized into simulation-based learning [73] , [74] and imitation learning [75] approaches.  ... 
arXiv:2105.01767v2 fatcat:sap4adixnzf77gzsiy3q5tq5ni

Interactive, Collaborative Robots: Challenges and Opportunities

Danica Kragic, Joakim Gustafson, Hakan Karaoguz, Patric Jensfelt, Robert Krug
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Full robot autonomy, including natural interaction, learning from and with human, safe and flexible performance for challenging tasks in unstructured environments will remain out of reach for the foreseeable  ...  Industrial robots today are still largely preprogrammed for their tasks, not able to detect errors in their own performance or to robustly interact with a complex environment and a human worker.  ...  Acknowledgements This work was supported by the Swedish Foundation for Strategic Research (SSF) and Knut and Alice Wallenberg Foundation through the WASP project.  ... 
doi:10.24963/ijcai.2018/3 dblp:conf/ijcai/KragicGKJ018 fatcat:xhg22csfwbbifausf3o5xsoh24

Towards Learning to Play Piano with Dexterous Hands and Touch [article]

Huazhe Xu, Yuping Luo, Shaoxiong Wang, Trevor Darrell, Roberto Calandra
2021 arXiv   pre-print
In contrast to that, in this paper, we demonstrate how an agent can learn directly from machine-readable music score to play the piano with dexterous hands on a simulated piano using reinforcement learning  ...  The strongest robots that can play a piano are based on a combination of specialized robot hands/piano and hardcoded planning algorithms.  ...  However, these priors is from very intuitive based on human experience and easy to implement.  ... 
arXiv:2106.02040v2 fatcat:bfdik6mmefaj5ldanosluwts6q

Nonprehensile Manipulation of Deformable Objects: Achievements and Perspectives from the Robotic Dynamic Manipulation Project

Fabio Ruggiero, Antoine Petit, Diana Serra, Aykut C. Satici, Jonathan Cacace, Alejandro Donaire, Fanny Ficuciello, Luca R. Buonocore, Giuseppe Andrea Fontanelli, Vincenzo Lippiello, Luigi Villani, Bruno Siciliano
2018 IEEE robotics & automation magazine  
The authors are solely responsible for the content of this manuscript.  ...  conducted to develop a framework where to simplify learning strategies from human imitation.  ...  The frame-by-frame tracking framework in Fig. 4 relies on a prior visual segmentation of the object in the image, based on a graph-cut based segmentation technique using color cues.  ... 
doi:10.1109/mra.2017.2781306 fatcat:hdhbjsy7kvhdfdrsukyrdvvq6e

e_GRASP: Robotic Hand Modeling and Simulation Environment

Ebrahim Mattar
2013 Advances in Robotics & Automation  
This includes Mat lab AI Tools, optimization, as considered useful toolboxes for dexterous hands for grasping and manipulation.  ...  For meeting such demands, a dexterous robotic hand software simulator was synthesized. The developed code is dexterity characterized robotic hand modeling and simulation software environment.  ...  Particularly, this manuscript is presenting a long term research framework, which is actually focused for dexterous robotics manipulation that have gained experience and achieved over a number of years  ... 
doi:10.4172/2168-9695.1000109 fatcat:h7imaseis5czflvjledmv3s4tq

Learning Dexterous Manipulation from Suboptimal Experts [article]

Rae Jeong, Jost Tobias Springenberg, Jackie Kay, Daniel Zheng, Yuxiang Zhou, Alexandre Galashov, Nicolas Heess, Francesco Nori
2021 arXiv   pre-print
Learning dexterous manipulation in high-dimensional state-action spaces is an important open challenge with exploration presenting a major bottleneck.  ...  reference behaviors to bootstrap a complex manipulation task on a simulated bimanual robot with human-like hands.  ...  learning from suboptimal experts for complex dexterous robotic manipulation.  ... 
arXiv:2010.08587v2 fatcat:l3o7m2ht6fakhiuzxbu66trg2i

Modeling, learning, perception, and control methods for deformable object manipulation

Hang Yin, Anastasia Varava, Danica Kragic
2021 Science Robotics  
We adopt a learning perspective to unify the discussion over analytical and data-driven approaches, addressing how to use and integrate model priors and task data in perceiving and manipulating a variety  ...  Perceiving and handling deformable objects is an integral part of everyday life for humans.  ...  efficiency can also be made in policy design.  ... 
doi:10.1126/scirobotics.abd8803 pmid:34043538 fatcat:3q54vpiprrcsnpffmbduj3fjrm

Learning to Use Chopsticks in Diverse Styles [article]

Zeshi Yang, KangKang Yin, Libin Liu
2022 arXiv   pre-print
Learning dexterous manipulation skills is a long-standing challenge in computer graphics and robotics, especially when the task involves complex and delicate interactions between the hands, tools and objects  ...  Our system achieves faster learning speed and better control robustness, when compared to vanilla systems that attempt to learn chopstick-based skills without a gripping pose optimization module and/or  ...  ACKNOWLEDGMENTS We would like to thank the anonymous reviewers for their constructive suggestions and feedback.  ... 
arXiv:2205.14313v1 fatcat:7l72zfl7cnhzpd4vajwzoasqji

A Novel Soft Robotic Hand Design With Human-Inspired Soft Palm: Achieving a Great Diversity of Grasps

Haihang Wang, Fares Abu-Dakka, Tran Nguyen Le, Ville Kyrki, He Xu
2021 IEEE robotics & automation magazine  
This work is partially supported by CHIST-ERA project Interactive Perception-Action-Learning for Modelling Objects (Academy of Finland decision 326304).  ...  Acknowledgments The first author thanks the China Scholarship Council for financial support through 201906680045 and the Natural Science Foundation of China under grant 51875113.  ...  Dexterous grasping is a prerequisite for task-dependent manipulation, which requires the consideration of factors such as interaction forces, stiffness and compliance, dexterity, and the number of degrees  ... 
doi:10.1109/mra.2021.3065870 fatcat:e3uakgosdzay7bthnra3m2ecmy

Recent Advances in Deep Reinforcement Learning Applications for Solving Partially Observable Markov Decision Processes (POMDP) Problems: Part 1—Fundamentals and Applications in Games, Robotics and Natural Language Processing

Xuanchen Xiang, Simon Foo
2021 Machine Learning and Knowledge Extraction  
The first part of a two-part series of papers provides a survey on recent advances in Deep Reinforcement Learning (DRL) applications for solving partially observable Markov decision processes (POMDP) problems  ...  The fact that the agent has limited access to the information of the environment enables AI to be applied efficiently in most fields that require self-learning.  ...  For reinforcement learning, researchers made significant progress, making DRL in manipulation tasks accessible in recent years.  ... 
doi:10.3390/make3030029 fatcat:u3y7bqkoljac5not2eq5konnnm
« Previous Showing results 1 — 15 out of 1,448 results