Contextual Affordances for Action-Effect Prediction in a Robotic-Cleaning Task

IEEE/RSJ International Conference on Intelligent Robots and Systems, Workshop Learning Object Affordances: A Fundamental Step to Allow Prediction, Planning and Tool Use? - Oct 2015.
Associated documents : Cruz_affordances_IROS2015.pdf [169Ko]  
Affordances are a useful method to anticipate the effect of an action performed by an agent. In this work, we present a robotic-cleaning task using contextual affordances implemented through a self-organizing neural network to predict the effect of the performed actions and avoid failed states. Current results on a simulated robot environment show that our architecture is able to predict future states with high accuracy.

 

@InProceedings{CPW15,
  author       = "Cruz, Francisco and Parisi, German I. and Wermter, Stefan",
  title        = "Contextual Affordances for Action-Effect Prediction in a Robotic-Cleaning Task",
  booktitle    = "IEEE/RSJ International Conference on Intelligent Robots and Systems, Workshop Learning Object Affordances: A Fundamental Step to Allow Prediction, Planning and Tool Use?",
  month        = "Oct",
  year         = "2015",
  address      = "Hamburg, DE",
  url          = "https://www2.informatik.uni-hamburg.de/wtm/publications/2015/CPW15/Cruz_affordances_IROS2015.pdf"
}

» Francisco Cruz
» German I. Parisi
» Stefan Wermter