5,357 Hits in 5.3 sec

Teaching Robots to Span the Space of Functional Expressive Motion [article]

Arjun Sripathy, Andreea Bobu, Zhongyu Li, Koushil Sreenath, Daniel S. Brown, Anca D. Dragan
2022 arXiv   pre-print
Our goal is to enable robots to perform functional tasks in emotive ways, be it in response to their users' emotional states, or expressive of their confidence levels.  ...  As a result 1) all user feedback can contribute to learning about every emotion; 2) the robot can generate trajectories for any emotion in the space instead of only a few predefined ones; and 3) the robot  ...  INTRODUCTION Robotics research tends to focus on generating functional motion, in service of the robot's task.  ... 
arXiv:2203.02091v2 fatcat:6ebjw3t6bzhr3pqqyl2h76ma2a

Motion Planning with Success Judgement Model based on Learning from Demonstration

Daichi Furuta, Kyo Kutsuzawa, Sho Sakaino, Toshiaki Tsuji
2020 IEEE Access  
A technique named Learning from Demonstration allows robots to learn actions in a human living environment from the demonstrations directly.  ...  By formulating the constraints of the action in a manner in mathematical optimization and combining these constraints with the learned success judgment model into a loss function, an action generation  ...  INTRODUCTION Advances in robotics are expanding the range of robot applications, from factories to human living spaces. In human living spaces, the conditions of the environment often vary.  ... 
doi:10.1109/access.2020.2987604 fatcat:w3kjdsx7sfhthhlyo3dmiymhqm

Anchoring by Imitation Learning in Conceptual Spaces [chapter]

Antonio Chella, Haris Dindo, Ignazio Infantino
2005 Lecture Notes in Computer Science  
, and in a topdown approach, in order to anchor the symbolical representations to the perceptual activities of the robotic system.  ...  In order to have a robotic system able to effectively learn by imitation, and not merely reproduce the movements of a human teacher, the system should have the capabilities of deeply understanding the  ...  Acknowledgments This research is partially supported by MIUR (Italian Ministry of Education, University and Research) under project RoboCare ("A Multi-Agent System with Intelligent Fixed and Mobile Robotic  ... 
doi:10.1007/11558590_50 fatcat:ezlmujyd75edpbtel5aqnuwulm

Novel Cost Function based Motion-planning Method for Robotic Manipulators

Daniel Szabo, Emese Gincsaine Szadeczky-Kardoss
2019 Advances in Science, Technology and Engineering Systems  
In this paper an offline motion-planning algorithm is presented for robotic manipulators.  ...  The first one is based on multidimensional Gauss functions and the second solution uses fuzzy function-approximation to determine the cost all over the configuration space.  ...  Acknowledgment The research reported in this paper was supported by the Higher Education Excellence Program in the frame of Artificial Intelligence research area of Budapest University of Technology and  ... 
doi:10.25046/aj040649 fatcat:omfmljvylzdorgircytwjiepv4

KUKA Control Toolbox

Francesco Chinello, Stefano Scheggi, Fabio Morbidi, Domenico Prattichizzo
2011 IEEE robotics & automation magazine  
T his article presents an open-source MATLAB toolbox for the motion control of KUKA robot manipulators.  ...  The KUKA Control Toolbox (KCT) is a collection of MATLAB functions developed at the University of Siena.  ...  Consider a sequence of n points The function kctpathjoint is analogous to kctpathxyz: the only difference is that the trajectory is defined here in the joint space instead of the operational space.  ... 
doi:10.1109/mra.2011.942120 fatcat:qwt4lo36rbgh3pxapzic3tcfte

Controllability of kinematic control systems on stratified configuration spaces

B. Goodwine, J.W. Burdick
2001 IEEE Transactions on Automatic Control  
Roughly speaking, such stratified systems have a configuration space which can be decomposed into submanifolds upon which the system has different sets of equations of motion.  ...  The main result in this paper is a controllability test, analogous to Chow's theorem, is based upon a construction involving distributions, and the extension thereof to robotic gaits.  ...  ACKNOWLEDGMENT The authors would like to thank the many helpful comments and remarks from an anonymous reviewer.  ... 
doi:10.1109/9.911414 fatcat:yn6o6e33nndjlloifrkcfthy3y

Teaching Image Analysis at DIKU [chapter]

Peter Johansen
2011 IFIP Advances in Information and Communication Technology  
The different disciplines in computer vision are introduced, and the principles for teaching two courses, an image analysis course, and a robot lab class are outlined.  ...  The early development of computer vision at Department of Computer Science at University of Copenhagen (DIKU) is briefly described.  ...  Enthusiastic cooperation of members from the image group at DIKU is acknowledged. I wish to thank Søren Olsen and Jon Sporring for editorial comments to this presentation.  ... 
doi:10.1007/978-3-642-23315-9_46 fatcat:b7ullajlhvdk7miiod2qkcda6i

Robot's play

Andrew G. Brooks, Jesse Gray, Guy Hoffman, Andrea Lockerd, Hans Lee, Cynthia Breazeal
2004 Computers in Entertainment  
Our focus is on teaching the robot via playful interaction using natural social gesture and language. We detail this in terms of two broad categories: teaching as play and teaching with play.  ...  We expect that the principal manifestation of the robots' entertainment capabilities will be socially interactive game playing.  ...  We believe that teaching a robot through game-play is a promising approach, and have applied the principle of teaching with play to our expressive humanoid robot.  ... 
doi:10.1145/1027154.1027171 fatcat:qmc3zqjxbrcebpe7k7r4xjfch4

Statistical Learning by Imitation of Competing Constraints in Joint Space and Task Space

Sylvain Calinon, Aude Billard
2009 Advanced Robotics  
In previous work, we proposed an approach based on Gaussian Mixture Regression (GMR) to find a controller for the robot reproducing the statistical characteristics of a movement in joint space and in task  ...  In this paper, we develop an alternative procedure to handle simultaneously constraints in joint space and in task space by combining directly the probabilistic representation of the task constraints with  ...  Note that the tracking problem is facilitated thanks to the kinesthetic teaching process (i.e., demonstrations of feasible motions provided to the robot).  ... 
doi:10.1163/016918609x12529294461843 fatcat:ktodcepvd5bthe6giizkriie2e

Visual servoing: a global path-planning approach

G. Chesi, Y.S. Hung
2007 Engineering of Complex Computer Systems (ICECCS), Proceedings of the IEEE International Conference on  
Second, the rotation path is parameterized through a particular extension of the Euler parameters in order to obtain an equivalent expression of the rotation matrix as a quadratic function of unconstrained  ...  This paper considers the problem of realizing visual servoing taking into account constraints such as visibility and workspace constraints while minimizing a cost function such as spanned image area and  ...  It consists of teaching the desired location for an eye-in-hand robotic system by showing the view of some reference features in such a location.  ... 
doi:10.1109/robot.2007.363629 dblp:conf/icra/ChesiH07 fatcat:5gysvhh73zcunj2h7ylzjlzure

Robot Programming by Demonstration [chapter]

Aude Billard, Sylvain Calinon, Rüdiger Dillmann, Stefan Schaal
2008 Springer Handbook of Robotics  
Yang et al [57] use HMMs to encode the motion of a robot's gripper either in the joint space or in the task space by considering either the positions or the velocities of the gripper.  ...  teaching (i.e., by manually guiding the robot's arms through the motion) [1, 14, 15].  ... 
doi:10.1007/978-3-540-30301-5_60 fatcat:abqi5btx6bhl7gbp5doqvs4icq

Robotic Choreography Inspired by the Method of Human Dance Creation

Hua Peng, Jing Li, Huosheng Hu, Changle Zhou, Yulong Ding
2018 Information  
This paper proposes a novel mechanism for a humanoid robot to create good choreography autonomously with the imagination of human dance.  ...  Such a mechanism combines innovativeness with the characteristic preservation of human dance, and enables a humanoid robot to present the characteristics of "imitation, memory, imagination, process and  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/info9100250 fatcat:iknxstpehvejjldvf2yiosh6cy

Combined pose-wrench and state machine representation for modeling Robotic Assembly Skills

Arne Wahrburg, Stefan Zeiss, Bjorn Matthias, Jan Peters, Hao Ding
2015 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
The approach is implemented on an ABB YuMi robot performing the assembly of a programmable logic controller (PLC) I/O module.  ...  This approach comes with the potential to simplify robot programming and to improve robustness in robotic assembly due to inherent quality checking.  ...  In this frame, the pose-wrench configuration of the other part is expressed. A trajectory expressed in 12D space does not explicitly depend on time.  ... 
doi:10.1109/iros.2015.7353471 dblp:conf/iros/WahrburgZMPD15 fatcat:za4hgrisnraclddwdp6l55ungu

PC-based off-line programming in the shipbuilding industry: open architecture

Chang-Sei Kim, Keum-Shik Hong, Yong-Seop Han
2005 Advanced Robotics  
The strength of the developed PC-based OLP system lies in its flexibility in handling the changes in the robot's target objects. The operator can generate robot programs very easily and quickly.  ...  Possible applications of the developed OLP can be extended to port automation, container loading/unloading processes as well as painting and grinding processes in the shipbuilding industry.  ...  Acknowledgements This work was supported by the Ministry of Science and Technology of Korea under a program of the National Research Laboratory, grant NRL M1-0302-00-0039-03-J00-00-023-10.  ... 
doi:10.1163/1568553053662582 fatcat:uj6strg3cfcxtk43wsz5d5vy4i

Taming the Beast: Guided Self-organization of Behavior in Autonomous Robots [chapter]

Georg Martius, J. Michael Herrmann
2010 Lecture Notes in Computer Science  
We show that the degree of self-organized explorativity of the robot can be regulated and that problem-specific error functions, hints, or abstract symbolic descriptions of a goal can be reconciled with  ...  the continuous robot dynamics.  ...  The project was supported by the BMBF grant #01GQ0432. References  ... 
doi:10.1007/978-3-642-15193-4_5 fatcat:atenfez3l5emdazt4ytwxx5poy
« Previous Showing results 1 — 15 out of 5,357 results