# Marginal Calibration Does Not Compose: Hidden Dependence in Modular Robot Navigation

arXiv: https://arxiv.org/abs/2609.23731 · HTML: https://mlsanity.com/paper/2609.23731/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [Safe Planning in Dynamic Environments using Conformal Prediction](https://mlsanity.com/paper/2210.10254/) (2022)
- [Adaptive Conformal Prediction for Motion Planning among Dynamic Agents](https://mlsanity.com/paper/2212.00278/) (2022)
- [Metrics of calibration for probabilistic predictions](https://mlsanity.com/paper/2205.09680/) (2022)
- [Injecting Planning-Awareness into Prediction and Detection Evaluation](https://mlsanity.com/paper/2110.03270/) (2021)
- [Risk-Calibrated Human-Robot Interaction via Set-Valued Intent Prediction](https://mlsanity.com/paper/2403.15959/) (2024)
- [Provably Safe Trajectory Optimization in the Presence of Uncertain Convex Obstacles](https://mlsanity.com/paper/2003.07811/) (2020)
- [Compositional Verification for Autonomous Systems with Deep Learning Components](https://mlsanity.com/paper/1810.08303/) (2018)
- [Risk-Driven Design of Perception Systems](https://mlsanity.com/paper/2205.10677/) (2022)

## Abstract (arXiv)

Robotic systems are typically composed of multiple independently developed modules that work together to perceive, predict, and act in the environment. Although each module may perform reliably in isolation, composing them does not necessarily preserve uncertainty calibration at the system level. In this work, we show that well-calibrated component interfaces do not necessarily produce calibrated downstream behavior after composition. Using a moving-obstacle prediction pipeline, we demonstrate that position and velocity estimators can each appear well calibrated individually, yet differences in how their error are correlated lead to substantially different estimates of future-state uncertainty. Consequently, assuming independence can make the system either overly confident or unnecessarily conservative, directly influencing downstream planning decisions and safety. Through simulations, we show that modeling the joint covariance restores downstream calibration and improves system performance, whereas dependence-robust uncertainty bounds enhance safety at the cost of increased conservatism. Our findings reveal a fundamental limitation of independently validating robotic modules and highlight the need for interfaces that communicate dependence information or support direct system-level calibration.