Filters








40 Hits in 4.1 sec

Sample-efficient Reinforcement Learning in Robotic Table Tennis [article]

Jonas Tebbe, Lukas Krauch, Yapeng Gao, Andreas Zell
2021 arXiv   pre-print
To make learning in few trials possible the method is embedded into our robot system. In this way we can use a one-step environment.  ...  In typical robotic applications, however, the number of feasible attempts is very limited. In this paper we present a sample-efficient RL algorithm applied to the example of a table tennis robot.  ...  The learning process is integrated into an existing robot system using a KUKA Agilus KR 6 R900 robot arm. The robot could learn an accurate return in under 200 balls.  ... 
arXiv:2011.03275v3 fatcat:giv2ni6pcvf5zk5ekt4exihxqq

Reinforcement learning to adjust parametrized motor primitives to new situations

Jens Kober, Andreas Wilhelm, Erhan Oztop, Jan Peters
2012 Autonomous Robots  
on several different real physical robots, i.e., a Barrett WAM, a BioRob, the JST-ICORP/SARCOS CBi and a Kuka KR 6.  ...  Subsequently, we apply the approach to three robot tasks, i.e., the generalization of throwing movements in darts, of hitting movements in table tennis, and of throwing balls where the tasks are learned  ...  ., (i) dart throwing with a simulated Barrett WAM, a real Kuka KR 6, and the JST-ICORP/SARCOS humanoid robot CBi (Cheng et al, 2007) , (ii) table tennis with a simulated robot arm and a real Barrett WAM  ... 
doi:10.1007/s10514-012-9290-3 fatcat:xee65qqyqbfujkwzk7vu7c6te4

Reinforcement Learning to Adjust Parametrized Motor Primitives to New Situations [chapter]

Jens Kober, Jan Peters
2014 Springer Tracts in Advanced Robotics  
on several different real physical robots, i.e., a Barrett WAM, a BioRob, the JST-ICORP/SARCOS CBi and a Kuka KR 6.  ...  Subsequently, we apply the approach to three robot tasks, i.e., the generalization of throwing movements in darts, of hitting movements in table tennis, and of throwing balls where the tasks are learned  ...  ., (i) dart throwing with a simulated Barrett WAM, a real Kuka KR 6, and the JST-ICORP/SARCOS humanoid robot CBi (Cheng et al, 2007) , (ii) table tennis with a simulated robot arm and a real Barrett WAM  ... 
doi:10.1007/978-3-319-03194-1_5 fatcat:najkkiye7bewjksqhszj6gstqm

Application of Table Tennis Ball Trajectory and Rotation-Oriented Prediction Algorithm Using Artificial Intelligence

Qiang Liu, Hairong Ding
2022 Frontiers in Neurorobotics  
table tennis robot.  ...  The experimental results demonstrate that the trained CNN can reach a detection accuracy of over 98%, with a detection response within 5.3 ms, meeting the requirements of the robot vision system of the  ...  Considering that the physical system of the seven-DOF KUKA mechanical arm used here has a slow control speed, the control system can only control the robotic arm to hit the ball through the slow mode.  ... 
doi:10.3389/fnbot.2022.820028 fatcat:4kair2y2cjayfbni36ztut4tyi

End-point impedance measurements at human hand during interactive manual welding with robot

Mustafa Suphi Erden, Aude Billard
2014 2014 IEEE International Conference on Robotics and Automation (ICRA)  
KUKA Light Weight Robot Arm (LWR).  ...  The welding torch is attached to the KUKA LWR, which is admittance controlled via a force sensor to give the feeling of a free floating mass at its endeffector.  ...  EXPERIMENTAL SETUP AND SUBJECTS The interactive manual welding system, shown in Fig. 1(a, b) , is composed of the KUKA LWR robot, an ATI force sensor attached to its end-effector, and a standard TIG  ... 
doi:10.1109/icra.2014.6906599 dblp:conf/icra/ErdenB14 fatcat:njanmpebjjagrlcy3ggjo7x27m

Design of a Flexible Capture Mechanism Inspired by Sea Anemone for Non-cooperative Targets

Jiankun Yang, Chengwei Ren, Chenghao Yang, Youyu Wang, Shumin Wan, Rongjie Kang
2021 Chinese Journal of Mechanical Engineering  
AbstractRobotic grippers have been used in industry as end-effectors but are usually limited to operations in pre-defined workspace.  ...  A robotic prototype is constructed and tested, showing the presented arm group mechanism has high adaptability to capture targets with different sizes, shapes, and incident angles.  ...  Control System As explained in Section 2.1, the presented prototype uses an arm group instead of a single arm to achieve high tolerance and adaptability in capture task.  ... 
doi:10.1186/s10033-021-00594-z fatcat:mveiefuxk5dd7d7kedm3qfwlfe

Ball Tracking and Trajectory Prediction for Table-Tennis Robots

Hsien-I Lin, Zhangguo Yu, Yi-Chen Huang
2020 Sensors  
Sports robots have become a popular research topic in recent years. For table-tennis robots, ball tracking and trajectory prediction are the most important technologies.  ...  We conducted a simulation experiment using 200 real-world trajectories as training data.  ...  KUKA AG Robotics once made a commercial in which one of their robots played table tennis against a human, and Omron once gave a demonstration with one of their suspended robotic arms playing table tennis  ... 
doi:10.3390/s20020333 pmid:31936032 pmcid:PMC7014400 fatcat:krt27vrnlragpkgbmpcefdaure

Discovering quiescent meanings in technologies: exploring the design management practices that support the development of Technology Epiphanies

Claudio Dell'Era, Naiara Altuna, Stefano Magistretti, Roberto Verganti
2016 Technology Analysis & Strategic Management  
The paper relies on four in-depth case studies developed by both primary and secondary sources: Nintendo, Kartell, Technogym and KUKA Robotics.  ...  Acknowledgements The authors would like to acknowledge all the practitioners who collaborated with us during the in-field data gathering process.  ...  With this ride, KUKA placed massive robotic arms on a track, a concept it first introduced in 2004, increased seating from two to four, and with Universal's help, KUKA immersed guests entirely in the world  ... 
doi:10.1080/09537325.2016.1210785 fatcat:uublh6nm5vci5ihzxf4shetrmq

Modeling of movement control architectures based on motion primitives using domain-specific languages

Arne Nordmann, Sebastian Wrede, Jochen Steil
2015 2015 IEEE International Conference on Robotics and Automation (ICRA)  
Using a proper tool chain, we show how to employ this modeldriven approach in a case study for the real world example of automatic laundry grasping with the KUKA LWR-IV, where executable source-code is  ...  flexible control of complex and compliant robots.  ...  The use-case comprises a complex robotics setup combining the redundant and compliant KUKA Lightweight Robot IV, 3D perception and a number of calibration, human-robot interaction, vision, and learning  ... 
doi:10.1109/icra.2015.7139899 dblp:conf/icra/NordmannWS15 fatcat:t7ulrxjn2bcvnktu6yktmjl7xu

A Bimanual Robotic Teleoperation Architecture with Anthropomorphic Hybrid Grippers for Unstructured Manipulation Tasks

Guoniu Zhu, Xiao Xiao, Changsheng Li, Jin Ma, Godwin Ponraj, A. V. Prituja, Hongliang Ren
2020 Applied Sciences  
A challenging bimanual manipulation task for an object with 5.2 kg was well addressed using the integrated teleoperation system.  ...  A Leap Motion Controller is used to track the motion of two human hands, while each hand is utilized to teleoperate one robotic gripper. The second one is the haptic devices and the robotic arms.  ...  A modified sensoric arm exoskeleton was used as a haptic master device to control a 7 DoFs (degrees of freedom) Kuka robot.  ... 
doi:10.3390/app10062086 fatcat:6ozghvf6zvfybegl2y36dlptjy

Learning motor skills: from algorithms to robot experiments

Jens Kober
2014 it - Information Technology  
For example, a forehand and a backhand could be seen as two different motor primitives of playing table tennis.  ...  Subsequently, we apply the approach to two robot tasks, i.e., the generalization of throwing movements in darts and of hitting movements in table tennis on several different real robots, i.e., a Barrett  ...  ., (i) dart throwing with a simulated Barrett WAM, a real Kuka KR 6, and the JST-ICORP/SARCOS humanoid robot CBi [Cheng et al., 2007] , (ii) table tennis with a simulated robot arm and a real Barrett  ... 
doi:10.1515/itit-2014-1039 fatcat:bmwrxrspjjdp3h2etrfarp4r4i

La inteligencia artificial como tecnología de mejora humana y el debate sobre sus aplicaciones de doble uso

Miguel Moreno Muñoz
2016 Zenodo  
Specific risks associated with the design of autonomous letal robots (LAR) with advanced AI should be carefully considered in a public and well-informed debate, giv [...]  ...  Developments in advance Artificial Intelligence (AI) have been spectacular in the last 2 years, with a better integration of electronic sensors, research in robotics, advanced algorithms and increased  ...  KUKA Robot | 10 mar. 2014 KUKA robot faces off against one of the best table tennis players of all time https://youtu.be/tIIJME8-au8://www.youtube.com/watch?  ... 
doi:10.5281/zenodo.2538316 fatcat:gktw3pqjgzexxa5niqpqugegi4

Interactive Robot for Playing Russian Checkers

Ekaterina E. Kopets, Artur I. Karimov, Georgii Y. Kolev, Lorenzo Scalera, Denis N. Butusov
2020 Robotics  
An original robot face is designed to endow the robot an ability to express its attributed emotional state.  ...  Human–robot interaction in board games is a rapidly developing field of robotics.  ...  Acknowledgments: The authors are grateful to M.Tech. student Andrey Ignatovskiy for preparing several program codes of AlphaZero algorithm used in this research.  ... 
doi:10.3390/robotics9040107 fatcat:cvh2w4nbnjfjvb2oq35cwa5rua

Stretchable, Flexible, Scalable Smart Skin Sensors for Robotic Position and Force Estimation

2018 Sensors  
The design and validation of a continuously stretchable and flexible skin sensor for collaborative robotic applications is outlined.  ...  The skin consistently provides an emergency stop command at only 0.5 N of force and is shown to maintain a collaboration force of 10 N in a collaborative control experiment.  ...  A continuously flexible and stretchable skin could be applied to robot arms such as the Kuka LBR (KUKA Roboter GmbH, Augsburg, Germany) or the Baxter, conforming to the arbitrary geometries of the robot  ... 
doi:10.3390/s18040953 pmid:29570643 pmcid:PMC5948948 fatcat:rtbg4ag3vnhh5mjxu3wxmtunju

Deep Adversarial Reinforcement Learning for Object Disentangling [article]

Melvin Laux, Oleg Arenz, Jan Peters, Joni Pajarinen
2021 arXiv   pre-print
We show that our method can generalize from training to test scenarios by training an end-to-end system for robot control to solve a challenging object disentangling task.  ...  Experiments with a KUKA LBR+ 7-DOF robot arm show that our approach outperforms the baseline method in disentangling when starting from different initial states than provided during training.  ...  Left: The KUKA LBR+ 7-DOF robot arm with attached SAKE gripper disentangling an "S-shape" object from an "O-shape" object.  ... 
arXiv:2003.03779v2 fatcat:ekewmbpqi5bitiw2y34tkppnui
« Previous Showing results 1 — 15 out of 40 results