Safety Guardrails in the Sky: Realizing Control Barrier Functions on the VISTA F-16 Jet

• URL: http://arxiv.org/abs/2603.27912v1
• Date: Sun, 29 Mar 2026 23:40:46 GMT
• Title: Safety Guardrails in the Sky: Realizing Control Barrier Functions on the VISTA F-16 Jet
• Abstract summary: Guardrails is a novel runtime assurance mechanism that guarantees dynamic safety for autonomous systems.<n>It blends commands from a human or AI operator with safe control actions to guarantee safe behavior.<n>To demonstrate its capabilities, we implemented Guardrails on an F-16 fighter jet and conducted flight tests.
• Score: 16.745213227676775
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The advancement of autonomous systems -- from legged robots to self-driving vehicles and aircraft -- necessitates executing increasingly high-performance and dynamic motions without ever putting the system or its environment in harm's way. In this paper, we introduce Guardrails -- a novel runtime assurance mechanism that guarantees dynamic safety for autonomous systems, allowing them to safely evolve on the edge of their operational domains. Rooted in the theory of control barrier functions, Guardrails offers a control strategy that carefully blends commands from a human or AI operator with safe control actions to guarantee safe behavior. To demonstrate its capabilities, we implemented Guardrails on an F-16 fighter jet and conducted flight tests where Guardrails supervised a human pilot to enforce g-limits, altitude bounds, geofence constraints, and combinations thereof. Throughout extensive flight testing, Guardrails successfully ensured safety, keeping the pilot in control when safe to do so and minimally modifying unsafe pilot inputs otherwise.

Related papers

• On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment [54.30690671490447]
  Existing safety-alignment signals are largely response-level or off-policy.<n>FATE transforms verifier-scored failures into repair supervision without expert demonstrations.<n>FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%.
  arXiv  Detail & Related papers  (2026-05-12T09:56:28Z)
• Sliding Mode Control for Safe Trajectory Tracking with Moving Obstacles Avoidance: Experimental Validation on Planar Robots [1.7044368816068716]
  This paper presents a unified control framework for robust trajectory tracking and moving obstacle avoidance.<n>The proposed architecture guarantees tracking in the presence of external disturbances while strictly enforcing collision avoidance constraints.<n>The efficacy and versatility of the approach are validated through numerical simulations and extensive real-world experiments.
  arXiv  Detail & Related papers  (2026-04-27T14:20:10Z)
• Control Barrier Corridors: From Safety Functions to Safe Sets [7.396792281840145]
  Control barrier functions and safe motion corridors are two widely used but technically distinct safety methods.<n>This paper introduces a new notion of control barrier corridors, which unifies these two approaches.<n>We show that individual state safety can be extended locally over control barrier corridors for convex barrier functions.
  arXiv  Detail & Related papers  (2026-03-06T17:23:56Z)
• BarrierSteer: LLM Safety via Learning Barrier Steering [83.12893815611052]
  BarrierSteer is a novel framework that formalizes safety by embedding learned non-linear safety constraints directly into the model's latent representation space.<n>We show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.
  arXiv  Detail & Related papers  (2026-02-23T18:19:46Z)
• RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic [56.38397499463889]
  Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks.<n>However, they remain vulnerable to hazardous instructions that may trigger unsafe behaviors.<n>We propose RoboSafe, a runtime safeguard for embodied agents through executable predicate-based safety logic.
  arXiv  Detail & Related papers  (2025-12-24T15:01:26Z)
• UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models [67.91151588917396]
  Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks.<n>We propose UpSafe$circ$C, a unified framework for enhancing LLM safety through safety-aware upcycling.<n>Our results highlight a new direction for LLM safety: moving from static alignment toward dynamic, modular, and inference-aware control.
  arXiv  Detail & Related papers  (2025-10-02T16:43:33Z)
• Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation [55.02966123945644]
  We propose a hierarchical control framework leveraging neural network verification techniques to design control barrier functions (CBFs) and policy correction mechanisms.<n>Our approach relies on probabilistic enumeration to identify unsafe regions of operation, which are then used to construct a safe CBF-based control layer.<n>These experiments demonstrate the ability of the proposed solution to correct unsafe actions while preserving efficient navigation behavior.
  arXiv  Detail & Related papers  (2025-04-30T13:47:25Z)
• T-CBF: Traversability-based Control Barrier Function to Navigate Vertically Challenging Terrain [9.089399418257148]
  We introduce a novel Traversability-based Control Barrier Function (T-CBF)<n>In this work, we use neural Control Barrier Functions (CBFs) to achieve safety beyond collision avoidance on unstructured vertically challenging terrain.<n>We present experimental results in simulation and on a physical Verti-4 Wheeler (V4W) platform, demonstrating that T-CBF can provide traversability safety while reaching the goal position.
  arXiv  Detail & Related papers  (2025-03-08T06:12:38Z)
• Towards Cooperative Flight Control Using Visual-Attention [61.99121057062421]
  We propose a vision-based air-guardian system to enable parallel autonomy between a pilot and a control system. Our attention-based air-guardian system can balance the trade-off between its level of involvement in the flight and the pilot's expertise and attention.
  arXiv  Detail & Related papers  (2022-12-21T15:31:47Z)
• Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Driving [100.57791628642624]
  We introduce a safety guaranteed learning framework for vision-based end-to-end autonomous driving. We design a learning system equipped with differentiable control barrier functions (dCBFs) that is trained end-to-end by gradient descent.
  arXiv  Detail & Related papers  (2022-03-04T16:14:33Z)
• Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning [9.891207216312937]
  Obstacle avoidance for small unmanned aircraft is vital for the safety of future urban air mobility. We propose a deep reinforcement learning algorithm based on Proximal Policy Optimization (PPO) to guide autonomous UAS to their destinations. Results show that the proposed model can provide accurate and robust guidance and resolve conflict with a success rate of over 99%.
  arXiv  Detail & Related papers  (2021-11-13T04:44:53Z)
• Development of a Fuzzy-based Patrol Robot Using in Building Automation System [1.5293427903448025]
  The paper presents a novel security system in which a mobile robot is used as a patrol. The robot is equipped with fuzzy-based algorithms to allow it to avoid the obstacles in an unknown environment. The experiment results show that the system satisfies the requirements for the objective of monitoring and securing the building.
  arXiv  Detail & Related papers  (2020-05-13T07:05:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.