mlsanityData to 14 Oct 2026

Towards Safe Reinforcement Learning with Reduced Conservativeness: A Case Study on Drone Flight Control

arXiv 2608.26852 ↗First posted 27 Aug 2026eess.SY cs.SYcited by 0

On the map: Deep reinforcement learning methods → Safe and constrained RL

Abstract (arXiv)

Incorporating formal methods into reinforcement learning (RL) has the potential to result in the best of both worlds, combining the robustness of formal guarantees with the adaptability and learning capabilities of RL, though careful design is needed to balance safety and exploration. In this work, we propose a framework to mitigate this loss of exploration while still allowing for the safety of the system to be ensured. Specifically, we introduce a less restrictive method that can reduce the conservativeness of formal methods by refining a disturbance model using online collected data and it evaluates the safety of a learning-based controller, using computationally efficient zonotopic reachability analysis for the safety analysis to facilitate a real-time implementation. We validate the framework in a real-world drone flight through a canyon, where the drone is subjected to unknown external disturbances and the framework is tasked with learning those disturbances online and adjusting the safety guarantees accordingly. The results show that the framework enables a less restrictive online training of learning-based controllers without compromising the safety of the system.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 18 references that are in the map. First posted on arXiv 27 Aug 2026.

Builds on

10 of 18 references.

References · 10

  1. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  2. 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 201
  3. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 163
  4. 2018Neural Lander: Stable Drone Landing Control using Learned Dynamicscited by 85
  5. 2022Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarkingcited by 34
  6. 2022Safe Reinforcement Learning Using Black-Box Reachability Analysiscited by 26
  7. 2022Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopescited by 26
  8. 2021Hybrid zonotopes: a new set representation for reachability analysis of mixed logical dynamical systemscited by 7
  9. 2021Scalable Zonotopic Under-approximation of Backward Reachable Sets for Uncertain Linear Systemscited by 3
  10. 2022Efficient Backward Reachability Using the Minkowski Difference of Constrained Zonotopescited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning over Forward-Invariant Policy Classes: Reinforcement Learning without Safety Concerns
  2. 2024Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
  3. 2024Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agents
  4. 2024A Safety Modulator Actor-Critic Method in Model-Free Safe Reinforcement Learning and Application in UAV Hovering
  5. 2026CAPSULE: Control-Theoretic Action Perturbations for Safe Uncertainty-Aware Reinforcement Learning
  6. 2024Handling Long-Term Safety and Uncertainty in Safe Reinforcement Learning
  7. 2025Safe and Near-Optimal Control with Online Dynamics Learning
  8. 2025Evaluating Reinforcement Learning Safety and Trustworthiness in Cyber-Physical Systems