Error detection and surprise in stochastic robot actions

For an autonomous robot to accomplish tasks when the outcome of actions is non-deterministic it is often necessary to detect and correct errors. In this work we introduce a general framework that stores fine-grained event transitions so that failures can be detected and handled early in a task. These failures are then recovered through two different approaches based on whether the error is "surprising" to the robot or not. Surprise transitions are used to create new models that capture observations previously not in the model. We demonstrate how the framework is capable of handling uncertainties encountered by a robot in "pick-and-place" tasks on the uBot-6 mobile manipulator using both visual and haptic sensor feedback.