Juan Pablo Mendoza
Ph.D. Thesis Defense

Abstract:
To make intelligent decisions, robots often use models of the stochastic effects of their actions on the world. Unfortunately, in complex environments, it is often infeasible to create models that are accurate in every plausible situation, which can lead to suboptimal performance. This thesis enables robots to reason about model inaccuracies to improve their performance. The thesis focuses on model inaccuracies that are subtle –i.e., they cannot be detected from a single observation– and context-dependent –i.e., they affect particular regions of the robot’s state-action space. Furthermore, this work enables robots to react to model inaccuracies from sparse execution data.

Our approach consists of enabling robots to explicitly reason about parametric Regions of Inaccurate Modeling (RIMs) in their state-action space. We enable robots to detect these RIMs from sparse execution data, to correct their models given these detections, and to plan accounting for uncertainty with respect to these RIMs. To detect and correct RIMs, we first develop optimization-based algorithms that work effectively online in low-dimensional domains. To extend this approach to high-dimensional domains, we develop a search-based Feature Selection algorithm, which relies on the assumption that RIMs are intrinsically low-dimensional but embedded in a high-dimensional space. Finally, we enable robots to make plans that account for their uncertainty about the accuracy of their models.

We evaluate our approach on various complex robot domains. Our approach enables the CoBot mobile service robots to autonomously detect inaccuracies in their motion models, despite their high-dimensional state-action space: the CoBots detect that they are not moving correctly in particular areas of the building, and that their wheels are starting to fail when making turns. Our approach enables the CMDragons soccer robots to improve their passing and shooting models online in the presence of opponents with unknown weaknesses and strengths. Finally, our approach enables a NASA spacecraft landing simulator to detect subtle anomalies, unknown to us beforehand, in their streams of high-dimensional sensor-output and actuator-input data.

More Information

Thesis Committee Members:
Reid Simmons, Co-chair
Manuela Veloso, Co-chair
Jeff Schneider
Brian Williams, Massachusetts Institute of Technology