# When Environments Shift: Safe Planning with Generative Priors and Robust Conformal Prediction

arXiv: https://arxiv.org/abs/2602.12616 · HTML: https://mlsanity.com/paper/2602.12616/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 32 of its 51 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 32)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?](https://mlsanity.com/paper/2006.14911/) (2020)
- [Safe Planning in Dynamic Environments using Conformal Prediction](https://mlsanity.com/paper/2210.10254/) (2022)
- [CARD: Classification and Regression Diffusion Models](https://mlsanity.com/paper/2206.07275/) (2022)
- [Robust Validation: Confident Predictions Even When Distributions Shift](https://mlsanity.com/paper/2008.04267/) (2020)
- [Adaptive Conformal Prediction for Motion Planning among Dynamic Agents](https://mlsanity.com/paper/2212.00278/) (2022)
- [Conformal Prediction Regions for Time Series using Linear Complementarity Programming](https://mlsanity.com/paper/2304.01075/) (2023)
- [Optimization-Based Collision Avoidance](https://mlsanity.com/paper/1711.03449/) (2017)
- [Copula Conformal Prediction for Multi-step Time Series Forecasting](https://mlsanity.com/paper/2212.03281/) (2022)
- [Practical and Consistent Estimation of f-Divergences](https://mlsanity.com/paper/1905.11112/) (2019)
- [Group-based Motion Prediction for Navigation in Crowded Environments](https://mlsanity.com/paper/2107.11637/) (2021)
- [Robust Conformal Prediction for STL Runtime Verification under Distribution Shift](https://mlsanity.com/paper/2311.09482/) (2023)
- [Conformal Prediction under Levy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations](https://mlsanity.com/paper/2502.14105/) (2025)
- [Reactive motion planning with probabilistic safety guarantees](https://mlsanity.com/paper/2011.03590/) (2020)
- [SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learning](https://mlsanity.com/paper/2407.17460/) (2024)
- [Multi-robot Mission Planning in Dynamic Semantic Environments](https://mlsanity.com/paper/2209.06323/) (2022)
- [Safe POMDP Online Planning among Dynamic Agents via Adaptive Conformal Prediction](https://mlsanity.com/paper/2404.15557/) (2024)
- [Risk-Sensitive Motion Planning using Entropic Value-at-Risk](https://mlsanity.com/paper/2011.11211/) (2020)
- [Learning for Robot Decision Making under Distribution Shift: A Survey](https://mlsanity.com/paper/2203.07558/) (2022)
- [Signal Temporal Logic Control Synthesis among Uncontrollable Dynamic Agents with Conformal Prediction](https://mlsanity.com/paper/2312.04242/) (2023)
- [Moving Obstacle Avoidance: a Data-Driven Risk-Aware Approach](https://mlsanity.com/paper/2203.14913/) (2022)
- [Validity Learning on Failures: Mitigating the Distribution Shift in Autonomous Vehicle Planning](https://mlsanity.com/paper/2406.01544/) (2024)
- [Statistical Guarantees in Data-Driven Nonlinear Control: Conformal Robustness for Stability and Safety](https://mlsanity.com/paper/2506.06228/) (2025)
- [Safe Navigation in Human Occupied Environments Using Sampling and Control Barrier Functions](https://mlsanity.com/paper/2105.01204/) (2021)
- [Risk Bounded Nonlinear Robot Motion Planning With Integrated Perception & Control](https://mlsanity.com/paper/2201.01483/) (2022)
- [Data-Driven Risk-sensitive Model Predictive Control for Safe Navigation in Multi-Robot Systems](https://mlsanity.com/paper/2209.07793/) (2022)
- [Evaluation of autonomous systems under data distribution shifts](https://mlsanity.com/paper/2406.20046/) (2024)
- [Egocentric Conformal Prediction for Safe and Efficient Navigation in Dynamic Cluttered Environments](https://mlsanity.com/paper/2504.00447/) (2025)
- [Probabilistic Collision Constraint for Motion Planning in Dynamic Environments](https://mlsanity.com/paper/2104.01659/) (2021)

## Built on by (most cited first, 2 of 2)

- [Explainable Wastewater Digital Twins: Adaptive Context-Conditioned Structured Simulators with Self-Falsifying Decision Support](https://mlsanity.com/paper/2605.19826/) (2026)
- [Adaptive Safety Filtering for Frozen ACC Policies via Conformal Residual Calibration](https://mlsanity.com/paper/2609.35415/) (2026)

## Abstract (arXiv)

Autonomous systems operate in environments that may change over time. An example is the control of a self-driving vehicle among pedestrians and human-controlled vehicles whose behavior may change based on factors such as traffic density, road visibility, and social norms. Therefore, the environment encountered during deployment rarely mirrors the environment and data encountered during training -- a phenomenon known as distribution shift -- which can undermine the safety of autonomous systems. Conformal prediction (CP) has recently been used along with data from the training environment to provide prediction regions that capture the behavior of the environment with a desired probability. When embedded within a model predictive controller (MPC), one can provide probabilistic safety guarantees, but only when the deployment and training environments coincide. Once a distribution shift occurs, these guarantees collapse. We propose a planning framework that is robust under distribution shifts by: (i) assuming that the underlying data distribution of the environment is parameterized by a nuisance parameter, i.e., an observable, interpretable quantity such as traffic density, (ii) training a conditional diffusion model that captures distribution shifts as a function of the nuisance parameter, (iii) observing the nuisance parameter online and generating cheap, synthetic data from the diffusion model for the observed nuisance parameter, and (iv) designing an MPC that embeds CP regions constructed from such synthetic data. Importantly, we account for discrepancies between the underlying data distribution and the diffusion model by using robust CP. Thus, the plans computed using robust CP enjoy probabilistic safety guarantees, in contrast with plans obtained from a single, static set of training data. We empirically demonstrate safety under diverse distribution shifts in the ORCA simulator.