Surprise-based developmental learning and experimental results on robots

Nadeesha Ranasinghe and Wei-Min Shen. Surprise-based developmental learning and experimental results on robots. In icdl-09, Shanghai, China, June 2009.

Download

[533.9kB pdf] 

Abstract

Learning from surprises and unexpected situations is a capability that is critical for developmental learning. This paper describes a promising approach in which a learner robot engages in a cyclic learning process consisting of prediction, action, observation, analysis (of surprise) and adaptation. In particular, the robot always predicts the consequences of its actions, detects surprises whenever there is a significant discrepancy between the prediction and the observed reality, analyzes the surprises for causes, and uses the analyzed knowledge to adapt to the unexpected situations. We tested this approach on a modular robot learning how to navigate and recover from unexpected changes in sensors, actions, goals, and environments. The results are very encouraging.

BibTeX Entry

@InProceedings{ranasinghe2009SurpriseBasedResults,
  abstract	= {Learning from surprises and unexpected situations is a capability that is critical for developmental learning. This paper describes a promising approach in which a learner robot engages in a cyclic learning process consisting of prediction, action, observation, analysis (of surprise) and adaptation. In particular, the robot always predicts the consequences of its actions, detects surprises whenever there is a significant discrepancy between the prediction and the observed reality, analyzes the surprises for causes, and uses the analyzed knowledge to adapt to the unexpected situations. We tested this approach on a modular robot learning how to navigate and recover from unexpected changes in sensors, actions, goals, and environments. The results are very encouraging.},
  address	= {Shanghai, China},
  author	= {Nadeesha Ranasinghe and Wei-Min Shen},
  booktitle	= icdl-09,
  month		= jun,
  title		= {Surprise-based developmental learning and experimental results on robots},
  year		= {2009}
}