Corpus ID: 67802387

Learning with tactile feedback on a humanoid robot

@inproceedings{Sommer2012LearningWT,
  title={Learning with tactile feedback on a humanoid robot},
  author={Nicolas Sommer and Section De Microtechnique and Aude Billard},
  year={2012}
}
RESUME : La perception tactile est un facteur cle et une condition necessaire pour la prehension et la manipulation d'objets. Une approche possible pour apprendre des tâches de manipulation est le programmation par demonstration (PbD), nous l'utilisons sur un robot humanoide equippe de capteur tactiles sur le bout des doigts. Nous utilisons une seule fonction de regression basee sur un modele de melange de Gaussiennes (GMM), construite a partir des demonstrations effectuees a la main sur le… Expand
Learning externally modulated dynamical systems
TLDR
This work presents a method to modulate DS depending on an external signal, extending the previous work on Locally Modulated DS, and presents two applications of the system, which would not have been possible to achieve without taking external sensing into account in the DS motion formulation. Expand
Multi-contact tactile exploration and interaction with unknown objects
Humans rely on the sense of touch in almost every aspect of daily life, whether to tie shoelaces, place fingertips on a computer keyboard or find keys inside a bag. With robots moving intoExpand

References

SHOWING 1-10 OF 12 REFERENCES
Learning force control policies for compliant manipulation
TLDR
This work presents an approach to acquiring manipulation skills on compliant robots through reinforcement learning, and uses the Policy Improvement with Path Integrals (PI2) algorithm to learn these force/torque profiles by optimizing a cost function that measures task success. Expand
Iterative learning of grasp adaptation through human corrections
TLDR
This work introduces an approach for grasp adaptation which learns a statistical model to adapt hand posture solely based on the perceived contact between the object and fingers, and demonstrates grasp adaptation in response to changes in contact. Expand
Human-Inspired Robotic Grasp Control With Tactile Sensing
TLDR
A novel robotic grasp controller that allows a sensorized parallel jaw gripper to gently pick up and set down unknown objects once a grasp location has been selected, inspired by the control scheme that humans employ for such actions. Expand
Is imitation learning the route to humanoid robots?
  • S. Schaal
  • Psychology, Computer Science
  • Trends in Cognitive Sciences
  • 1999
TLDR
It is postulated that the study of imitation learning offers a promising route to gain new insights into mechanisms of perceptual motor control that could ultimately lead to the creation of autonomous humanoid robots. Expand
Robot programming by demonstration : a probabilistic approach
TLDR
The proposed probabilistic approach to mixture models of varying density distributions helps speed up the learning process and influences the dynamical system parameters. Expand
Learning of Gestures by Imitation in a Humanoid Robot
TLDR
This chapter addresses one major and generic issue, namely how to discover the essence of a gesture, i.e. how to find a representation of the data that encapsulates only the key aspects of the gesture, and discards the intrinsic variability across people motions. Expand
A tactile sensor for the fingertips of the humanoid robot iCub
TLDR
An improved version of the small prototype fingertip which incorporates a capacitive pressure system is shown, which has been integrated on the hand of the humanoid robot iCub. Expand
iCub: the design and realization of an open humanoid platform for cognitive and neuroscience research
TLDR
The design of the mechanisms and structures forming the basic 'body' of the iCub are described and kinematic structures dynamic design criteria, actuator specification and selection, and detailed mechanical and electronic design are considered. Expand
Incremental Online Learning in High Dimensions
TLDR
To the authors' knowledge, LWPR is the first truly incremental spatially localized learning method that can successfully and efficiently operate in very high-dimensional spaces. Expand
Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper
Vibratory power unit for vibrating conveyers and screens comprising an asynchronous polyphase motor, at least one pair of associated unbalanced masses disposed on the shaft of said motor, with theExpand
...
1
2
...