This paper presents an optic flow-guided approach for achieving soft landings by resource-constrained unmanned aerial vehicles (UAVs) on dynamic platforms. An offline data-driven linear model based on Koopman operator theory is developed to describe the underlying (nonlinear) dynamics of optic flow output obtained from a single monocular camera that maps to vehicle acceleration as the control input. Moreover, a novel adaptation scheme within the Koopman framework is introduced online to handle uncertainties such as unknown platform motion and ground effect, which exert a significant influence during the terminal stage of the descent process. Further, to minimize computational overhead, an event-based adaptation trigger is incorporated into an event-driven Model Predictive Control (MPC) strategy to regulate optic flow and track a desired reference. A detailed convergence analysis ensures global convergence of the tracking error to a uniform ultimate bound. Simulation results demonstrate the algorithm’s robustness and effectiveness in landing on dynamic platforms under ground effect and sensor noise, which compares favorably to non-adaptive time-triggered and time-triggered adaptive schemes.

This study proposes a novel approximation-free observer-based control policy synthesis for achieving precise tracking based on output feedback for second-order dynamical systems subjected to matched and unmatched disturbances. In response to the challenges posed by unknown state derivatives and disturbance bounds, an adaptive super-twisting observer is adopted which estimates the state derivatives in finite time. Subsequently, the observer is coupled with a super-twisting control policy that incorporates a nonlinear transformation to ensure compliance of control inputs with the input saturation constraints. Lyapunov stability analysis is used to demonstrate the exact exponential convergence of the tracking errors to the origin. The efficacy of the proposed algorithm is verified through its application to the problem of attitude tracking of a quadrotor subject to actuator faults and saturation. A comprehensive assessment of the tracking performance is provided through comparative numerical simulations substantiating the superior performance of the proposed framework.

Due to dynamic variations such as changing payload, aerodynamic disturbances, and varying platforms, a robust solution for quadrotor trajectory tracking remains challenging. To address these challenges, we present a deep reinforcement learning (DRL) framework that achieves physical dynamics invariance by directly optimizing force/torque inputs, eliminating the need for traditional intermediate control layers. Our architecture integrates a temporal trajectory encoder, which processes finite-horizon reference positions/velocities, with a latent dynamics encoder trained on historical state-action pairs to model platform-specific characteristics. Additionally, we introduce scale-aware dynamics randomization parameterized by the quadrotor’s arm length, enabling our approach to maintain stability across drones spanning from 30g to 2.1kg and outperform other DRL baselines by 85% in tracking accuracy. Extensive real-world validation of our approach on the Crazyflie 2.1 quadrotor, encompassing over 200 flights, demonstrates robust adaptation to wind, ground effects, and swinging payloads while achieving less than 0.05m RMSE at speeds up to 2.0 m/s. This work introduces a universal quadrotor control paradigm that compensates for dynamic discrepancies across varied conditions and scales, paving the way for more resilient aerial systems.

This article proposes a novel neural control architecture that employs input-output information to compensate for the lack of knowledge about the robot model to achieve prescribed tracking performance in the presence of joint constraints. To this end, an observer-controller zeroing neural network framework is formulated that combines online estimation of the unknown model’s Jacobian with a trajectory tracking controller that implements joint angle and velocity constraints via a nonlinear map. Further, prescribed performance constraints are embedded within this architecture to achieve desired transient and steady-state performance along with added robustness to chattering. Hence, in comparison to prior studies, the proposed scheme facilitates a more robust control architecture with the added benefits of more stringent application of the input constraints and superior transient and steady-state performance. Simulation and experimental studies of trajectory tracking, including comparisons with leading alternative designs, are used to verify the efficacy and superior performance of the proposed scheme.

This article addresses the problem of finding online solutions to time-varying underdetermined linear systems with limits on states and their derivatives through a novel zeroing neural network (ZNN) implementation. The proposed model combines zeroing dynamics with user-prescribed performance constraints to ensure that the system achieves desired transient and steady-state behavior. The novelty of this approach lies in a nonlinear invertible mapping that transforms the constrained system to an unconstrained one so that the resulting error remains subsequently bounded by the performance function for all time. In particular, two different ZNN models are synthesized that rely on an exponentially convergent and finite-time convergent performance function to drive the residual error to convergence. The effectiveness of the proposed models is verified through redundancy resolution in path-tracking problems in robotics. A detailed performance comparison study with two leading alternative designs is also undertaken to further illustrate the merits of the proposed schemes.

Small-object detection and avoidance in unknown environments is a significant challenge to overcome for small autonomous vehicles that are generally highly agile and restricted in payload and computational processing power. Typical machine-vision and range measurement-based solutions suffer either from restricted fields-of-view or significant computational complexity and are, hence, not easily portable to small platforms. In order to overcome these drawbacks, in this paper, two novel bioinspired approaches are proposed to extract information about small-field objects contained in planar optic flow. The first approach, which is analogous to the small-field extraction process hypothesized to occur in the lobula plate of the fly visual system, is based on the Fourier residual analysis of instantaneous optic flow. Alternatively, the flow-of-flow method is the engineering analogue of the small-field extraction process thought to occur in the fruit-fly's medulla, and extracts high-frequency content of optic flow by means of an elementary motion detector array. Both approaches extract instantaneous relative range and bearing of small-field obstacles from planar optic flow in a local environment characterized by small and wide-field obstacles, which is then combined with an artificial potential function-based low-order steering control law. The proposed sensing and control scheme is experimentally validated with a quadrotor vehicle that is able to effectively navigate an unknown environment laden with small-field clutter. This bioinspired approach is computationally efficient, which renders extraction of vehicle velocity and local environment structure superfluous, and thus, serves as a robust, reflexive solution to the problem of small-object detection, and avoidance for small autonomous robots.

Small-object detection and avoidance in unknown environments is a significant challenge to overcome for small autonomous vehicles that are generally highly agile and restricted in payload and computational processing power. Typical machine-vision and range measurement based solutions suffer either from restricted fields-of-view or significant computational complexity and are not easily portable to small platforms. In this paper, a novel bio-inspired navigation technique is introduced that is modeled using analogues of the small-field motion-sensitive interneurons of the insect visuomotor system. The proposed technique achieves small-field object detection based on Fourier residual analysis of instantaneous optic flow. The small field signal is used to extract relative range and bearing of the nearest obstacle, which is then combined with an artificial potential function-based low-order steering control law. The proposed sensing and control scheme is experimentally validated with a quadrotor vehicle that is able to effectively navigate an unknown environment laden with small-field clutter. This bio-inspired approach is computationally efficient and serves as a robust, reflexive solution to the problem of small-object detection and avoidance for autonomous robots.

Weakly electric fish use a navigational technique called electrolocation to investigate their surroundings for predator, prey and obstacles. Obstacles and other global stimuli are perceived as perturbations to the fish's self-generated electric field, which provide relevant navigational cues to the fish. In this work a control strategy based on electrolocation for performing obstacle avoidance in electrically heterogeneous environments is presented and validated. The control strategy developed for a straight tunnel is shown to be robust to small variations in the tunnel width. This justifies its application to other heterogeneous corridor-like environments. Static output feedback control is shown to achieve the desired goal of reflexive obstacle avoidance in such environments in simulation and experimentation. The proposed approach is computationally inexpensive and readily implementable on a small scale underwater vehicle, making underwater autonomous navigation feasible in real-time.