Quantifying Aleatoric and Epistemic Dynamics Uncertainty via Local Conformal Calibration

TL;DR

This paper introduces LUCCa, a conformal prediction-based method that calibrates aleatoric uncertainty estimates in robot dynamics models to account for both aleatoric and epistemic uncertainties, enabling safer planning in changing environments.

Contribution

The paper presents LUCCa, a novel local conformal calibration method that jointly quantifies aleatoric and epistemic uncertainties in dynamics models without strong assumptions.

Findings

LUCCa provides valid probabilistic prediction regions in dynamic environments.

The method improves safety in planning under uncertain and changing dynamics.

Validation on a double-integrator demonstrates effective uncertainty quantification.

Abstract

Whether learned, simulated, or analytical, approximations of a robot's dynamics can be inaccurate when encountering novel environments. Many approaches have been proposed to quantify the aleatoric uncertainty of such methods, i.e. uncertainty resulting from stochasticity, however these estimates alone are not enough to properly estimate the uncertainty of a model in a novel environment, where the actual dynamics can change. Such changes can induce epistemic uncertainty, i.e. uncertainty due to a lack of information/data. Accounting for both epistemic and aleatoric dynamics uncertainty in a theoretically-grounded way remains an open problem. We introduce Local Uncertainty Conformal Calibration (LUCCa), a conformal prediction-based approach that calibrates the aleatoric uncertainty estimates provided by dynamics models to generate probabilistically-valid prediction regions of the system's state. We account for both epistemic and aleatoric uncertainty non-asymptotically, without strong assumptions about the form of the true dynamics or how it changes. The calibration is performed locally in the state-action space, leading to uncertainty estimates that are useful for planning. We validate our method by constructing probabilistically-safe plans for a double-integrator under significant changes in dynamics.