How Failure Facilitates Success

Abstract

Robotic systems that interact with real-world environments cannot capture all the underlying patterns that govern the environment’s reactions to the system’s actions. One way to deal with this uncertainty is to describe the environment probabilistically. This paper proposes another way: Failed expectations are incorporated into a deterministic model that can describe more complex dynamics than exclusively probabilistic models can. Wrong predictions from the past are used to provide a more appropriate description of the future. Unlike previous approaches, it does not suggest that transitions between hidden states can be predicted prior to the fact. Instead, effects are considered that are impossible according to the model’s current predictions. This discrepancy enables the model to self-correct in a continual coupling with the system that it describes.