flight testing

This work addresses the challenges of poor early-stage safety, low sample efficiency, and limited dynamic adaptability in unmanned aerial vehicle (UAV) search-and-rescue missions under constrained simulation training. To overcome these issues, the authors propose a hierarchical decision-making framework: at the high level, a rule-driven, interpretable coaching mechanism provides action recommendations, collision-avoidance strategies, and arbitration weights; at the low level, goal-conditioned reinforcement learning with dense reward shaping is combined with pattern-aware prioritized experience replay and rule-based metadata augmentation. Notably, the approach requires no pretraining and significantly improves both early safety and sample efficiency. Evaluated on battery-aware multi-target delivery and dynamic target tracking tasks, the method effectively reduces mission termination due to collisions while maintaining robust online adaptability to environmental dynamics.

To address safety, timeliness, and dynamic adaptability challenges in multi-UAV collaborative inspection of wind turbines, this paper proposes a Signal Temporal Logic (STL)-based joint optimization framework. It uniformly encodes time-sensitive constraints, dynamical feasibility limits, and safety-critical collision avoidance as STL specifications embedded within a nonlinear optimization problem. An event-triggered re-planning mechanism and a generalized robustness scoring function are introduced to balance user preferences, multi-agent conflict mitigation, and responsiveness to unexpected disturbances. The method is validated in MATLAB/Gazebo simulations and on physical UAV prototypes, demonstrating significant improvements in trajectory physical feasibility, temporal efficiency, and operational robustness. This work establishes a verifiable and scalable STL-driven paradigm for autonomous multi-robot coordination in complex, dynamic environments.

Addressing three key challenges—navigation in dynamic environments, operation under resource constraints, and robustness against adversarial disturbances—this paper proposes a unified planning and control framework for safe, autonomous aerial robot operation in real-world scenarios. Methodologically, it introduces the first integration of model predictive control (MPC), control barrier functions (CBFs), lightweight online optimization, and embedded real-time verification, forming a multi-dimensional safety-enhanced architecture that unifies dynamic obstacle avoidance, computation-aware resource scheduling, and adaptive control under uncertainty and adversarial perturbations. All algorithms are rigorously validated on physical UAV platforms: under high-speed moving obstacles, low-compute embedded hardware, and sensor disturbances, the system achieves zero collisions throughout all experiments, demonstrating substantial improvements in both safety and practical deployability in complex real-world settings.

The success of surveillance applications involving small unmanned aerial vehicles (UAVs) depends on how long the limited on-board power would persist. To cope with this challenge, alternative renewable sources of lift are sought. One promising solution is to extract energy from rising masses of buoyant air. This paper proposes a local-global behavioral management and decision-making approach for the autonomous deployment of soaring-capable UAVs. The cooperative UAVs are modeled as non-deterministic finite state-based rational agents. In addition to a mission planning module for assigning tasks and issuing dynamic navigation waypoints for a new path planning scheme, in which the concepts of visibility and prediction are applied to avoid the collisions. Moreover, a delayed learning and tuning strategy is employed optimize the gains of the path tracking controller. Rigorous comparative analyses carried out with three benchmarking baselines and 15 evolutionary algorithms highlight the adequacy of the proposed approach for maintaining the surveillance persistency (staying aloft for longer periods without landing) and maximizing the detection of targets (two times better than non-cooperative and semi-cooperative approaches) with less power consumption (almost 6% of battery consumed in six hours).

Safety-critical small Unmanned Aircraft Systems (sUAS) lack systematic, standardized testing processes that are tightly integrated with safety analysis. Method: This paper proposes a requirement-driven coupled testing framework, introducing the novel triadic paradigm of “requirements–simulation testing–safety analysis.” It employs formal requirement modeling with bidirectional traceability, a simulation–hardware-in-the-loop cooperative testing architecture, scenario-driven test case generation, and deep integration of safety analysis methods (e.g., Fault Tree Analysis and System-Theoretic Process Analysis). Contribution/Results: Evaluated on an sUAS case study, the framework significantly improves simulation fidelity coverage and requirement coverage, enables end-to-end safety evidence generation, fills the gap in standardized sUAS testing procedures, and delivers reproducible, verifiable testing assets to support airworthiness certification.

Aerodynamic parameter uncertainty in flight testing poses significant maneuver safety risks, yet existing abort criteria lack theoretical guarantees and struggle to handle dynamic uncertainties. Method: We propose a data-driven real-time safety alerting framework comprising three stages: trajectory prediction, nearest-neighbor safety classification, and conformal prediction–based calibration—enabling reliable quantification of short-term safety risk. Contribution/Results: To our knowledge, this is the first work to integrate conformal prediction into flight safety classification calibration, providing rigorous coverage probability guarantees under user-specified confidence levels and enabling cross-configuration generalization. Experiments on uncertain flight dynamic models demonstrate that the system accurately identifies critical hazardous scenarios, achieving significantly higher risk anticipation accuracy than baseline methods while strictly satisfying theoretical coverage requirements.

This work addresses the challenges faced by quadrotor drones in high-speed autonomous obstacle avoidance, where traditional modular pipelines suffer from high latency and pure reinforcement learning approaches lack safety guarantees. The authors propose an end-to-end reinforcement learning framework integrated with a model-driven safety mechanism: during training, physics-informed priors shape the reward function, while at deployment, a real-time safety filter projects the policy’s output onto a provably safe action set. This approach uniquely unifies high-speed flight with rigorous safety constraints within an end-to-end learning paradigm. Evaluated in both dense indoor obstacle courses and real-world forest environments, the system achieves stable flight at 7.5 m/s, outperforming conventional planners and existing end-to-end methods in both performance and robustness, while demonstrating exceptional generalization and safety.

In data-driven UAV missions, real-time decision-making—whether to wait locally or immediately proceed to the next point of interest—remains challenging due to dynamic environmental uncertainties. Method: This paper proposes a dynamic decision-making mechanism that integrates hardware-inspired branch prediction with reinforcement learning, adapting the concept of branch prediction from computer architecture to edge-based UAV decision-making. It models the temporal evolution of event occurrence probabilities in real time to dynamically optimize the stay-or-move policy. Contribution/Results: Compared to conventional regression baselines, the approach reduces worst-case mission time by 4.1× and incurs only ≤2.7% overhead over the ideal offline optimal solution in median mission time. It achieves near-optimal, probability-aware performance across diverse scenarios, significantly reducing wasteful hovering and backtracking overheads, thereby enhancing end-to-end responsiveness and operational efficiency.

This work addresses the limited generalization of existing learning-based quadrotor agile flight controllers, which rely heavily on high-fidelity simulation and system identification and often sacrifice agility to satisfy safety constraints, particularly in out-of-distribution real-world scenarios such as external disturbances or hardware degradation. To overcome these limitations, the authors propose an adaptive control framework that requires neither precise system identification nor offline simulation. The approach combines online residual learning to construct a hybrid dynamics model with a novel adaptive time scaling (ATS) mechanism that actively probes the physical limits of the platform. Integrated with a short-horizon, real-world-anchored backpropagation-through-time strategy (RASH-BPTT), the system rapidly enhances a base policy’s peak velocity from 1.9 m/s to 7.3 m/s within approximately 100 seconds, enabling reliable execution of high-agility maneuvers near actuator saturation.

This work addresses the lack of dynamic safety speed-limiting methods for indoor micro aerial vehicles (MAVs) grounded in empirically measured impact risk in human-robot coexistence scenarios. We present the first end-to-end open-source toolchain that enables reproducible impact testing via a compact experimental platform, constructs a data-driven velocity-to-impact impulse mapping model, and integrates a real-time speed-limiting node with a compliance logging system within ROS 2 to close the loop from experimentation to deployment of safety policies. The framework provides standardized procedures, a public dataset, and open-source code to support autonomous certification. Validation across multiple commercial quadrotors and representative indoor environments demonstrates that the generated policies strictly adhere to prescribed impact force constraints while effectively preserving mission execution efficiency.