Attitude control of fixed-wing unmanned aerial vehicles (UAVs) is a difficult control problem in part due to uncertain nonlinear dynamics, actuator constraints, and coupled longitudinal and lateral motions. Current state-of-the-art autopilots are based on linear control and are thus limited in their effectiveness and performance. drl is a machine learning method to automatically discover optimal control laws through interaction with the controlled system that can handle complex nonlinear dynamics. We show in this article that deep reinforcement learning (DRL) can successfully learn to perform attitude control of a fixed-wing UAV operating directly on the original nonlinear dynamics, requiring as little as 3 min of flight data. We initially train our model in a simulation environment and then deploy the learned controller on the UAV in flight tests, demonstrating comparable performance to the state-of-the-art ArduPlane proportional-integral-derivative (PID) attitude controller with no further online learning required. Learning with significant actuation delay and diversified simulated dynamics were found to be crucial for successful transfer to control of the real UAV. In addition to a qualitative comparison with the ArduPlane autopilot, we present a quantitative assessment based on linear analysis to better understand the learning controller’s behavior.

This paper presents nonlinear, singularity-free autopilot designs for multivariable reduced-attitude control of fixed-wing aircraft. To control roll and pitch angles, we employ vector coordinates constrained to the unit two-sphere and that are independent of the yaw/heading angle. The angular velocity projected onto this vector is enforced to satisfy the coordinated-turn equation. We exploit model structure in the design and prove almost global asymptotic stability using Lyapunov-based tools. Slowly-varying aerodynamic disturbances are compensated for using adaptive backstepping. To emphasize the practical application of our result, we also establish the ultimate boundedness of the solutions under a simplified controller that only depends on rough estimates of the control-effectiveness matrix. The controller design can be used with state-of-the-art guidance systems for fixed-wing unmanned aerial vehicles (UAVs) and is implemented in the open-source autopilot ArduPilot for validation through realistic software-in-the-loop (SITL) simulations.

Given the increasing complexity of maritime traffic, particularly with the growing integration of autonomous vessels alongside conventional vessels, the need for enhanced coordination and decision support systems has become critical to ensure safety and efficiency. This article presents a concept for a centralised decision support system for local maritime traffic and can be used in centres for remote operations or vessel traffic services. By formalising a non-zero-sum asymmetric polymatrix game, we achieve collision and grounding avoidance of non-cooperative agents. Time-varying and state-dependent payoff matrices are constructed using a reward framework that combines metrics for compliance with maritime traffic rules, global collision risk, grounding risk, and an operational efficiency metric for speed and route optimisation. A pure Nash equilibrium is reached in a polymatrix game, a fully connected graph of traffic participants on vertices with bimatrix games on the edges. Strategy probability distributions in infinite populations located on the graph’s vertices are updated with the replicator revision protocol. The equilibrium constitutes a control message consisting of advised speed and heading commands broadcast to all traffic participants. To validate the proposed idea, we have developed a scalable multi-agent system simulator and present results from a collision avoidance scenario with three vessels and 49 strategies available to each. Engaged vessels achieved safe and efficient passage, guided by the advised speed and heading changes.

Motivated by aircraft applications, we revisit the path-following guidance problem in three dimensions. First, by formulating the path-following error directly in the inertial frame, we propose a class of guidance laws for regular parameterized paths that, unlike most approaches existing in the literature, do not require the explicit construction of a path frame. Based on an inner-outer loop control paradigm, the guidance law generates a normal acceleration command that is normal to the flow-relative velocity vector (as the lift force). This allows for a natural decomposition of the desired vehicle acceleration for aerial vehicles in coordinated turns: tangential acceleration for airspeed control and normal acceleration for guidance generated through bank-to-turn maneuvers, i.e., by tilting the lift vector. By using cascade arguments, we show that the proposed design leads to almost global stability results and thus relaxes the set of feasible initial conditions compared to existing methods. The efficacy of the proposed guidance law is demonstrated in a simulation study.