Programming full-body movements for humanoid robots by observation
By Ales Ude, Christopher G. Atkeson, Marcia Riley. 2004
191 citations recorded by the source corpus.
Subfields: Biomedical Engineering, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biomedical Engineering
- Pieter Abbeel
- Gerhard Neumann
- Jan Peters
- Aude Gemma Billard
- J. Bagnell
- Sergey Levine
- Mohamed Medhat Gaber
- Eyad Elyan
In Control and Systems Engineering
- Jan Peters
- Gerhard Neumann
- Pieter Abbeel
- Sergey Levine
- J. Bagnell
- Aude Gemma Billard
- Takayuki Osa
- Joni Pajarinen
Citations in the corpus
- An Algorithmic Perspective on Imitation Learning (2018, background): “ce problem ” in imitation learning [Billard et al., 2008]. The correspondence problem frequently appears when we try to teach humanoids how to imitate human motion obtained e.g. from motion trackers [Ude et al., 2004, Nakaoka et al., 2007]. Due to the different embodiments between a human expert and ”
- Task adaptation through exploration and action sequencing (2009, background): “Due to different kinematic and dynamic capabilities of the human demonstrator and the target humanoid robot, demonstrated trajectories cannot be simply copied as sequences of joint angles [15], but need to be adapted to the capabilities of the robot.”
- Combining Dynamical Systems control and programming by demonstration for teaching discrete bimanual coordination tasks to a humanoid robot (2008, background): “PbD operates at different levels of the task representation: from copying low-level features of the motion [3, 19] to inferring the user’s intention and using a symbolic representation [5].”
- A survey of robot learning from demonstration (2009, unknown): “NN techniques also enable a robot arm to perform a peg in hole task [49], and a set of bspline wavelets approximate time-sequenced data for full body humanoid motion [39].”
- Imitation Learning (2017, background): “Humanoid robots can learn to perform actions that utilize only part of their skeleton [Billard and Matari´c 2001; Ijspeert et al. 2002b; Vogt et al. 2014] or the entire body [Berger et al. 2008; Calinon and Billard 2007b; Ude et al. 2004].”