# Particle-Based Conformal Prediction for Contact-Aware Uncertainty Calibration in Stratified Configuration Spaces

arXiv: https://arxiv.org/abs/2608.09166 · HTML: https://mlsanity.com/paper/2608.09166/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [Safe Planning in Dynamic Environments using Conformal Prediction](https://mlsanity.com/paper/2210.10254/) (2022)
- [Theoretical Foundations of Conformal Prediction](https://mlsanity.com/paper/2411.11824/) (2024)
- [Factory: Fast Contact for Robotic Assembly](https://mlsanity.com/paper/2205.03532/) (2022)
- [Adaptive Conformal Prediction for Motion Planning among Dynamic Agents](https://mlsanity.com/paper/2212.00278/) (2022)
- [Probabilistic Conformal Prediction Using Conditional Random Samples](https://mlsanity.com/paper/2206.06584/) (2022)
- [Exchangeability, Conformal Prediction, and Rank Tests](https://mlsanity.com/paper/2005.06095/) (2020)
- [Sample-Efficient Safety Assurances using Conformal Prediction](https://mlsanity.com/paper/2109.14082/) (2021)
- [Safe Perception-Based Control under Stochastic Sensor Uncertainty using Conformal Prediction](https://mlsanity.com/paper/2304.00194/) (2023)
- [Conformal Predictive Safety Filter for RL Controllers in Dynamic Environments](https://mlsanity.com/paper/2306.02551/) (2023)
- [Regression Trees for Fast and Adaptive Prediction Intervals](https://mlsanity.com/paper/2402.07357/) (2024)
- [Quantifying Aleatoric and Epistemic Dynamics Uncertainty via Local Conformal Calibration](https://mlsanity.com/paper/2409.08249/) (2024)
- [Interaction-aware Conformal Prediction for Crowd Navigation](https://mlsanity.com/paper/2502.06221/) (2025)
- [Sampling-Based Motion Planning on Sequenced Manifolds](https://mlsanity.com/paper/2006.02027/) (2020)
- [Lies We Can Trust: Quantifying Action Uncertainty with Inaccurate Stochastic Dynamics through Conformalized Nonholonomic Lie groups](https://mlsanity.com/paper/2512.10294/) (2025)
- [Planning and Resilient Execution of Policies For Manipulation in Contact with Actuation Uncertainty](https://mlsanity.com/paper/1703.10261/) (2017)
- [Robust, Compliant Assembly via Optimal Belief Space Planning](https://mlsanity.com/paper/1811.03904/) (2018)
- [Adaptive Nonlinear Model Predictive Control for a Real-World Labyrinth Game](https://mlsanity.com/paper/2406.08650/) (2024)
- [Local Conformal Calibration of Dynamics Uncertainty from Semantic Images](https://mlsanity.com/paper/2605.13028/) (2026)

## Built on by (most cited first, 1 of 1)

- [Localized Conformal Safety Monitoring with Vision-Language Models for Autonomous Driving](https://mlsanity.com/paper/2610.02765/) (2026)

## Abstract (arXiv)

Reliable uncertainty representation is essential for deploying autonomous systems that interact with their environment, as robots must reason about how uncertainty arising from both stochasticity and model mismatch is impacted by contacts with obstacles (e.g., when navigating through a cluttered environment or inserting a part into an assembly). We propose Calibrated Particle-sets for Trans-dimensional Uncertainty Representation (CaPTURe), a geometry-aware, conformal prediction-based algorithm that generates probabilistically valid prediction regions of the unknown future system configuration using particle-based models of arbitrary fidelity. While calibrated uncertainty predictions are essential for safe and efficient planning, analytical or learned motion models are often inaccurate - due to limited data, simplifying assumptions, unmodeled effects, etc. - which can lead to unsafe executions or task failure. Additionally, when a robot contacts an obstacle, the distribution of its future configurations can become multimodal or disjoint, or lie along manifolds of lower intrinsic dimension than the space of possible robot configurations. Our method uses a calibration dataset of system transitions to locally calibrate motion uncertainty estimates, constructing regions guaranteed to contain the future robot configuration at a user-set probability. Our calibration procedure captures how motion uncertainty varies between contact-rich and contactless motions, leading to sufficient coverage in both cases. We evaluate our method on two simulated planning tasks: controlling a marble around a labyrinth and performing tight-tolerance peg-in-hole insertion with a manipulator. Compared to relevant baselines, CaPTURe achieves the user-specified coverage requirement both in and out of contact and achieves up to a 30% absolute improvement in task success rate over the best baseline.