# Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertainty

arXiv: https://arxiv.org/abs/1812.10687 · HTML: https://mlsanity.com/paper/1812.10687/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Dec 2018.

## Built on by (most cited first, 14 of 14)

- [Driving Everywhere with Large Language Model Policy Adaptation](https://mlsanity.com/paper/2402.05932/) (2024)
- [Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control](https://mlsanity.com/paper/2206.10524/) (2022)
- [Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction](https://mlsanity.com/paper/2211.08701/) (2022)
- [In-Distribution Barrier Functions: Self-Supervised Policy Filters that Avoid Out-of-Distribution States](https://mlsanity.com/paper/2301.12012/) (2023)
- [Anomaly Detection in Multi-Agent Trajectories for Automated Driving](https://mlsanity.com/paper/2110.07922/) (2021)
- [Unsupervised Layer-wise Score Aggregation for Textual OOD Detection](https://mlsanity.com/paper/2302.09852/) (2023)
- [Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.13986/) (2022)
- [The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learning](https://mlsanity.com/paper/2405.03164/) (2024)
- [A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction](https://mlsanity.com/paper/2110.03446/) (2021)
- [Out-of-Distribution Detection for Adaptive Computer Vision](https://mlsanity.com/paper/2305.09293/) (2023)
- [Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems](https://mlsanity.com/paper/2510.21254/) (2025)
- [NeuralSympCheck: A Symptom Checking and Disease Diagnostic Neural Model with Logic Regularization](https://mlsanity.com/paper/2206.00906/) (2022)
- [Making the Flow Glow -- Robot Perception under Severe Lighting Conditions using Normalizing Flow Gradients](https://mlsanity.com/paper/2412.07565/) (2024)
- [CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning](https://mlsanity.com/paper/2406.07541/) (2024)

## Abstract (arXiv)

Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This requires a system to reason about its own uncertainty given unfamiliar, out-of-distribution observations. Approximate Bayesian approaches are commonly used to estimate uncertainty for neural network predictions, but can struggle with out-of-distribution observations. Generative models can in principle detect out-of-distribution observations as those with a low estimated density. However, the mere presence of an out-of-distribution input does not by itself indicate an unsafe situation. In this paper, we present a method for uncertainty-aware robotic perception that combines generative modeling and model uncertainty to cope with uncertainty stemming from out-of-distribution states. Our method estimates an uncertainty measure about the model's prediction, taking into account an explicit (generative) model of the observation distribution to handle out-of-distribution inputs. This is accomplished by probabilistically projecting observations onto the training distribution, such that out-of-distribution inputs map to uncertain in-distribution observations, which in turn produce uncertain task-related predictions, but only if task-relevant parts of the image change. We evaluate our method on an action-conditioned collision prediction task with both simulated and real data, and demonstrate that our method of projecting out-of-distribution observations improves the performance of four standard Bayesian and non-Bayesian neural network approaches, offering more favorable trade-offs between the proportion of time a robot can remain autonomous and the proportion of impending crashes successfully avoided.