Sensor-assisted adaptive motor control under continuously varying context

By Heiko Hoffmann, Georgios Petkos, Sebastian Bitzer, Sethu Vijayakumar. 2007

19 citations recorded by the source corpus.

Adaptive motor control under continuously varying context, like the inertia parameters of a ma- nipulated object, is an active research area that lacks a satisfactory solution. Here, we present and compare three novel strategies for learning control under varying context and show how adding tactile sensors may ease this task. The first strategy uses only dynamics information to infer the unknown inertia parameters. It is based on a probabilistic generative model of the control torques, which are linear in the inertia parameters. We demonstrate this inference in the special case of a single continuous context variable - the mass of the manipulated object. In the second strategy, instead of torques, we use tactile forces to infer the mass in a similar way. Finally, the third strategy omits this inference - which may be infeasible if the latent space is multi-dimensional - and directly maps the state, state transitions, and tactile forces onto the control torques. The additional tactile input implicitly contains all control-torque relevant properties of the manipu- lated object. In simulation, we demonstrate that this direct mapping can provide accurate control torques under multiple varying context variables.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Control and Systems Engineering, Reinforcement Learning, Robotics & Control

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

  1. George Dimitri Konidaris
  2. Bruno Castro da Silva
  3. Andrew Barto
  4. Sergey Levine
  5. Jan Peters
  6. Pierre-Yves Oudeyer
  7. Gerhard Neumann
  8. J. Urgen Schmidhuber

In Cognitive Neuroscience

  1. George Dimitri Konidaris
  2. Andrew Barto
  3. Matthew Botvinick
  4. J. Urgen Schmidhuber
  5. Peter S. Dayan
  6. Yael Niv
  7. Gianluca Baldassarre
  8. Sergey Levine

In Control and Systems Engineering

  1. George Dimitri Konidaris
  2. Andrew Barto
  3. Bruno Castro da Silva
  4. Huizhen Yu
  5. Dimitri P. Bertsekas
  6. Csaba Szepesvari
  7. Jan Peters
  8. Richard S. Sutton

In Reinforcement Learning

  1. George Dimitri Konidaris
  2. Bruno Castro da Silva
  3. Andrew Barto
  4. Sergey Levine
  5. Shie Mannor
  6. Jan Peters
  7. Philip S. Thomas
  8. Peter Stone

In Robotics & Control

  1. Andrew Barto
  2. George Dimitri Konidaris
  3. Bruno Castro da Silva
  4. Jan Peters

Citations in the corpus