RL-STPA: Adapting System-Theoretic Hazard Analysis for Safety-Critical Reinforcement Learning

As reinforcement learning (RL) deployments expand into safety-critical domains, existing evaluation methods fail to systematically identify hazards arising from the black-box nature of neural network enabled policies and distributional shift between training and deployment. This paper introduces Reinforcement Learning System-Theoretic Process Analysis (RL-STPA), a framework that adapts conventional STPA's systematic hazard analysis to address RL's unique challenges through three key contributions: hierarchical subtask decomposition using both temporal phase analysis and domain expertise to capture emergent behaviors, coverage-guided perturbation testing that explores the sensitivity of state-action spaces, and iterative checkpoints that feed identified hazards back into training through reward shaping and curriculum design. We demonstrate RL-STPA in the safety-critical test case of autonomous drone navigation and landing, revealing potential loss scenarios that can be missed by standard RL evaluations. The proposed framework provides practitioners with a toolkit for systematic hazard analysis, quantitative metrics for safety coverage assessment, and actionable guidelines for establishing operational safety bounds. While RL-STPA cannot provide formal guarantees for arbitrary neural policies, it offers a practical methodology for systematically evaluating and improving RL safety and robustness in safety-critical applications where exhaustive verification methods remain intractable.

"Take Me Home, Wi-Fi Drone": A Drone-based Wireless System for Wilderness Search and Rescue

Wilderness Search and Rescue (WiSAR) represents a longstanding and critical societal challenge, demanding innovative and automatic technological solutions. In this paper, we introduce Wi2SAR, a novel autonomous drone-based wireless system for long-range, through-occlusion WiSAR operations, without relying on existing infrastructure. Our basic insight is to leverage the automatic reconnection behavior of modern Wi-Fi devices to known networks. By mimicking these networks via on-drone Wi-Fi, Wi2SAR uniquely facilitates the discovery and localization of victims through their accompanying mobile devices. Translating this simple idea into a practical system poses substantial technical challenges. Wi2SAR overcomes these challenges via three distinct innovations: (1) a rapid and energy-efficient device discovery mechanism to discover and identify the target victim, (2) a novel RSS-only, long-range direction finding approach using a 3D-printed Luneburg Lens, amplifying the directional signal strength differences and significantly extending the operational range, and (3) an adaptive drone navigation scheme that guides the drone toward the target efficiently. We implement an end-to-end prototype and evaluate Wi2SAR across various mobile devices and real-world wilderness scenarios. Experimental results demonstrate Wi2SAR's high performance, efficiency, and practicality, highlighting its potential to advance autonomous WiSAR solutions. Wi2SAR is open-sourced at https://aiot-lab.github.io/Wi2SAR to facilitate further research and real-world deployment.

Precise Aggressive Aerial Maneuvers with Sensorimotor Policies

Precise aggressive maneuvers with lightweight onboard sensors remains a key bottleneck in fully exploiting the maneuverability of drones. Such maneuvers are critical for expanding the systems' accessible area by navigating through narrow openings in the environment. Among the most relevant problems, a representative one is aggressive traversal through narrow gaps with quadrotors under SE(3) constraints, which require the quadrotors to leverage a momentary tilted attitude and the asymmetry of the airframe to navigate through gaps. In this paper, we achieve such maneuvers by developing sensorimotor policies directly mapping onboard vision and proprioception into low-level control commands. The policies are trained using reinforcement learning (RL) with end-to-end policy distillation in simulation. We mitigate the fundamental hardness of model-free RL's exploration on the restricted solution space with an initialization strategy leveraging trajectories generated by a model-based planner. Careful sim-to-real design allows the policy to control a quadrotor through narrow gaps with low clearances and high repeatability. For instance, the proposed method enables a quadrotor to navigate a rectangular gap at a 5 cm clearance, tilted at up to 90-degree orientation, without knowledge of the gap's position or orientation. Without training on dynamic gaps, the policy can reactively servo the quadrotor to traverse through a moving gap. The proposed method is also validated by training and deploying policies on challenging tracks of narrow gaps placed closely. The flexibility of the policy learning method is demonstrated by developing policies for geometrically diverse gaps, without relying on manually defined traversal poses and visual features.

EDFNet: Early Fusion of Edge and Depth for Thin-Obstacle Segmentation in UAV Navigation

Autonomous Unmanned Aerial Vehicles (UAVs) must reliably detect thin obstacles such as wires, poles, and branches to navigate safely in real-world environments. These structures remain difficult to perceive because they occupy few pixels, often exhibit weak visual contrast, and are strongly affected by class imbalance. Existing segmentation methods primarily target coarser obstacles and do not fully exploit the complementary multimodal cues needed for thin-structure perception. We present EDFNet, a modular early-fusion segmentation framework that integrates RGB, depth, and edge information for thin-obstacle perception in cluttered aerial scenes. We evaluate EDFNet on the Drone Depth and Obstacle Segmentation (DDOS) dataset across sixteen modality-backbone configurations using U-Net and DeepLabV3 in pretrained and non-pretrained settings. The results show that early RGB-Depth-Edge fusion provides a competitive and well-balanced baseline, with the most consistent gains appearing in boundary-sensitive and recall-oriented metrics. The pretrained RGBDE U-Net achieves the best overall performance, with the highest Thin-Structure Evaluation Score (0.244), mean IoU (0.219), and boundary IoU (0.234), while maintaining competitive runtime performance (19.62 FPS) on our evaluation hardware. However, performance on the rarest ultra-thin categories remains low across all models, indicating that reliable ultra-thin segmentation is still an open challenge. Overall, these findings position early RGB-Depth-Edge fusion as a practical and modular baseline for thin-obstacle segmentation in UAV navigation.

Vision-Based End-to-End Learning for UAV Traversal of Irregular Gaps via Differentiable Simulation

-Navigation through narrow and irregular gaps is an essential skill in autonomous drones for applications such as inspection, search-and-rescue, and disaster response. However, traditional planning and control methods rely on explicit gap extraction and measurement, while recent end-to-end approaches often assume regularly shaped gaps, leading to poor generalization and limited practicality. In this work, we present a fully vision-based, end-to-end framework that maps depth images directly to control commands, enabling drones to traverse complex gaps within unseen environments. Operating in the Special Euclidean group SE(3), where position and orientation are tightly coupled, the framework leverages differentiable simulation, a Stop-Gradient operator, and a Bimodal Initialization Distribution to achieve stable traversal through consecutive gaps. Two auxiliary prediction modules-a gap-crossing success classifier and a traversability predictor-further enhance continuous navigation and safety. Extensive simulation and real-world experiments demonstrate the approach's effectiveness, generalization capability, and practical robustness.

AeroScene: Progressive Scene Synthesis for Aerial Robotics

Generative models have shown substantial impact across multiple domains, their potential for scene synthesis remains underexplored in robotics. This gap is more evident in drone simulators, where simulation environments still rely heavily on manual efforts, which are time-consuming to create and difficult to scale. In this work, we introduce AeroScene, a hierarchical diffusion model for progressive 3D scene synthesis. Our approach leverages hierarchy-aware tokenization and multi-branch feature extraction to reason across both global layouts and local details, ensuring physical plausibility and semantic consistency. This makes AeroScene particularly suited for generating realistic scenes for aerial robotics tasks such as navigation, landing, and perching. We demonstrate its effectiveness through extensive experiments on our newly collected dataset and a public benchmark, showing that AeroScene significantly outperforms prior methods. Furthermore, we use AeroScene to generate a large-scale dataset of over 1,000 physics-ready, high fidelity 3D scenes that can be directly integrated into NVIDIA Isaac Sim. Finally, we illustrate the utility of these generated environments on downstream drone navigation tasks. Our code and dataset are publicly available at aioz-ai.github.io/AeroScene/

CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence

The convergence of low-altitude economies, embodied intelligence, and air-ground cooperative systems creates growing demand for simulation infrastructure capable of jointly modeling aerial and ground agents within a single physically coherent environment. Existing open-source platforms remain domain-segregated: driving simulators lack aerial dynamics, while multirotor simulators lack realistic ground scenes. Bridge-based co-simulation introduces synchronization overhead and cannot guarantee strict spatial-temporal consistency. We present CARLA-Air, an open-source infrastructure that unifies high-fidelity urban driving and physics-accurate multirotor flight within a single Unreal Engine process. The platform preserves both CARLA and AirSim native Python APIs and ROS 2 interfaces, enabling zero-modification code reuse. Within a shared physics tick and rendering pipeline, CARLA-Air delivers photorealistic environments with rule-compliant traffic, socially-aware pedestrians, and aerodynamically consistent UAV dynamics, synchronously capturing up to 18 sensor modalities across all platforms at each tick. The platform supports representative air-ground embodied intelligence workloads spanning cooperation, embodied navigation and vision-language action, multi-modal perception and dataset construction, and reinforcement-learning-based policy training. An extensible asset pipeline allows integration of custom robot platforms into the shared world. By inheriting AirSim's aerial capabilities -- whose upstream development has been archived -- CARLA-Air ensures this widely adopted flight stack continues to evolve within a modern infrastructure. Released with prebuilt binaries and full source: https://github.com/louiszengCN/CarlaAir

Integrated Multi-Drone Task Allocation, Sequencing, and Optimal Trajectory Generation in Obstacle-Rich 3D Environments

Coordinating teams of aerial robots in cluttered three-dimensional (3D) environments requires a principled integration of discrete mission planning-deciding which robot serves which goals and in what order -- with continuous-time trajectory synthesis that enforces collision avoidance and dynamic feasibility. This paper introduces IMD-TAPP (Integrated Multi-Drone Task Allocation and Path Planning), an end-to-end framework that jointly addresses multi-goal allocation, tour sequencing, and safe trajectory generation for quadrotor teams operating in obstacle-rich spaces. IMD--TAPP first discretizes the workspace into a 3D navigation graph and computes obstacle-aware robot-to-goal and goal-to-goal travel costs via graph-search-based pathfinding. These costs are then embedded within an Injected Particle Swarm Optimization (IPSO) scheme, guided by multiple linear assignment, to efficiently explore coupled assignment/ordering alternatives and to minimize mission makespan. Finally, the resulting waypoint tours are transformed into time-parameterized minimum-snap trajectories through a generation-and-optimization routine equipped with iterative validation of obstacle clearance and inter-robot separation, triggering re-planning when safety margins are violated. Extensive MATLAB simulations across cluttered 3D scenarios demonstrate that IMD--TAPP consistently produces dynamically feasible, collision-free trajectories while achieving competitive completion times. In a representative case study with two drones serving multiple goals, the proposed approach attains a minimum mission time of 136~s while maintaining the required safety constraints throughout execution.

AeroGen: Agentic Drone Autonomy through Single-Shot Structured Prompting & Drone SDK

Designing correct UAV autonomy programs is challenging due to joint navigation, sensing and analytics requirements. While LLMs can generate code, their reliability for safety-critical UAVs remains uncertain. This paper presents AeroGen, an open-loop framework that enables consistently correct single-shot AI-generated drone control programs through structured guardrail prompting and integration with the AeroDaaS drone SDK. AeroGen encodes API descriptions, flight constraints and operational world rules directly into the system context prompt, enabling generic LLMs to produce constraint-aware code from user prompts, with minimal example code. We evaluate AeroGen across a diverse benchmark of 20 navigation tasks and 5 drone missions on urban, farm and inspection environments, using both imperative and declarative user prompts. AeroGen generates about 40 lines of AeroDaaS Python code in about 20s per mission, in both real-world and simulations, showing that structured prompting with a well-defined SDK improves robustness, correctness and deployability of LLM-generated drone autonomy programs.

WESPR: Wind-adaptive Energy-Efficient Safe Perception & Planning for Robust Flight with Quadrotors

Local wind conditions strongly influence drone performance: headwinds increase flight time, crosswinds and wind shear hinder agility in cluttered spaces, while tailwinds reduce travel time. Although adaptive controllers can mitigate turbulence, they remain unaware of the surrounding geometry that generates it, preventing proactive avoidance. Existing methods that model how wind interacts with the environment typically rely on computationally expensive fluid dynamics simulations, limiting real-time adaptation to new environments and conditions. To bridge this gap, we present WESPR, a fast framework that predicts how environmental geometry affects local wind conditions, enabling proactive path planning and control adaptation. Our lightweight pipeline integrates geometric perception and local weather data to estimate wind fields, compute cost-efficient paths, and adjust control strategies-all within 10 seconds. We validate WESPR on a Crazyflie drone navigating turbulent obstacle courses. Our results show a 12.5-58.7% reduction in maximum trajectory deviation and a 24.6% improvement in stability compared to a wind-agnostic adaptive controller.