Quantifying Aleatoric and Epistemic Dynamics Uncertainty via Local Conformal Calibration
cs.RO, cs.SY, eess.SY
Submitted: 2024-09-12
Updated: 2025-03-12
Comments: 24 pages, 9 figures. Accepted to the 16th International Workshop on the Algorithmic Foundations of Robotics (WAFR) 2024
Journal ref: Algorithmic Foundations of Robotics XVI, Volume 2, Springer Proceedings in Advanced Robotics, vol. 38, pp. 85-103 (2026)
DOI: 10.1007/978-3-032-09970-9_5
Project page: https://um-arm-lab.github.io/lucca
License: http://creativecommons.org/licenses/by/4.0/
The gist: Whether learned, simulated, or analytical, approximations of a robot's dynamics can be inaccurate when encountering novel environments.
Terminology
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.
Sources
- A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
- Robust Safety under Stochastic Uncertainty with Discrete-Time Control Barrier Functions
- Regression Trees for Fast and Adaptive Prediction Intervals
- Split Localized Conformal Prediction
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies