Task adaptation through exploration and action sequencing

By Bojan Nemec, Minija Tamosiunaite, Florentin Wörgötter, Ales Ude. 2009

29 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Biomedical Engineering

In Control and Systems Engineering

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, background): “Using only the sub-goals of primitive motions, a humanoid robot can learn a pouring task (Nemec et al., 2009).”
Learning control Lyapunov function to ensure stability of dynamical system-based robot reaching motions (2014, methodology): “DMP has been used for different robotics applications such as: walking [32], drumming [30], pouring [49], and obstacle avoidance [ 36, 37].”
Towards Deep Developmental Learning (2016, background): “There are several representations for contextual DMPs [134], [135], [131], but their common feature is that the dimension-”
Learning position and orientation dynamics from demonstrations via contraction analysis (2018, methodology): “Tasks, such as drumming (Ude et al. 2010), pouring (Nemec et al. 2009), and pick and place have been recreated using DMPs on various robotic platforms.”
Learning Partially Contracting Dynamical Systems from Demonstrations (2017, methodology): “Tasks such as drumming [29], pouring [30], and pick and place have been recreated using DMPs on various robotic platforms.”
Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives (2011, methodology): “Parameters for value function approximation employed for goal learning were taken from our previous studies [16] (for the numerical values see Appendix C).”
A Dynamical System-based Approach to Modeling Stable Robot Control Policies via Imitation Learning (2012, background): “Most of the previous works that deals with situation based adaptation of motions (Kober, Oztop, & Peters, 2010; Nemec et al., 2009) use reinforcement learning for learning to adapt to new situations through trial and error.”
Learning motion primitive goals for robust manipulation (2011, methodology): “[11] optimize the goal parameters of a DMP through reinforcement learning, by iteratively approximating a continuous value function in state space.”