# Improving the Resilience of Quadrotors in Underground Environments by Combining Learning-based and Safety Controllers

arXiv: https://arxiv.org/abs/2509.02808 · HTML: https://mlsanity.com/paper/2509.02808/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Builds on (most cited first, 14 of 14)

- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows](https://mlsanity.com/paper/2107.12571/) (2021)
- [Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability](https://mlsanity.com/paper/2107.06277/) (2021)
- [Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress](https://mlsanity.com/paper/2410.04640/) (2024)
- [Variational Inference MPC for Bayesian Model-based Reinforcement Learning](https://mlsanity.com/paper/1907.04202/) (2019)
- [Out-Of-Distribution Detection Is Not All You Need](https://mlsanity.com/paper/2211.16158/) (2022)
- [Efficient Out-of-Distribution Detection Using Latent Space of β-VAE for Cyber-Physical Systems](https://mlsanity.com/paper/2108.11800/) (2021)
- [Variational Inference MPC using Normalizing Flows and Out-of-Distribution Projection](https://mlsanity.com/paper/2205.04667/) (2022)
- [Provably Safe Trajectory Optimization in the Presence of Uncertain Convex Obstacles](https://mlsanity.com/paper/2003.07811/) (2020)
- [Runtime Safety Assurance Using Reinforcement Learning](https://mlsanity.com/paper/2010.10618/) (2020)
- [FIG-OP: Exploring Large-Scale Unknown Environments on a Fixed Time Budget](https://mlsanity.com/paper/2203.06316/) (2022)
- [UAVs Beneath the Surface: Cooperative Autonomy for Subterranean Search and Rescue in DARPA SubT](https://mlsanity.com/paper/2206.08185/) (2022)
- [Large-Scale Exploration of Cave Environments by Unmanned Aerial Vehicles](https://mlsanity.com/paper/2303.02972/) (2023)

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

- [Foundational World Models Accurately Detect Bimanual Manipulator Failures](https://mlsanity.com/paper/2603.06987/) (2026)

## Abstract (arXiv)

Autonomously controlling quadrotors in large-scale subterranean environments is applicable to many areas such as environmental surveying, mining operations, and search and rescue. Learning-based controllers represent an appealing approach to autonomy, but are known to not generalize well to `out-of-distribution' environments not encountered during training. In this work, we train a normalizing flow-based prior over the environment, which provides a measure of how far out-of-distribution the quadrotor is at any given time. We use this measure as a runtime monitor, allowing us to switch between a learning-based controller and a safe controller when we are sufficiently out-of-distribution. Our methods are benchmarked on a point-to-point navigation task in a simulated 3D cave environment based on real-world point cloud data from the DARPA Subterranean Challenge Final Event Dataset. Our experimental results show that our combined controller simultaneously possesses the liveness of the learning-based controller (completing the task quickly) and the safety of the safety controller (avoiding collision).