Impact Angle Control Guidance of Glide-Capable Munition Using a Vector Field Approach

Neural-Network-Based Path Replanning for Gliding Vehicles Considering Terminal Velocity

“…Content may change prior to final publication. planning without the replanning, i.e., nominal path described in Section III-A, ii) a model-based algorithm, APG [13] with augmentation of linear quadratic guidance (LQG) [2] for three-dimensional implementation, iii) VFG [14], a guidance algorithm that guides a vehicle to a predefined reference path in a virtual vector space, and iv) the proposed method with selected network configurations. Simulation settings including nominal initial condition, desired terminal condition, and vehicle information are summarized in Table 3.…”

“…From this comparison, the neural network with 256 number of hidden layer nodes and ReLU will be compared with other methods in Sections V-B2 and V-B3. From Section V-B1, the proposed method with the best network configuration is compared with other algorithms: i) offline path planning without the replanning, i.e., Section III-A, ii) method APG+LQG, consisting of APG [13] on the vertical plane (ED-plane) and LQG [2] on the horizontal plane (EN-plane), and iii) method VFG [14] that generates a reference path in a virtually designed vector space and form a vector field to make a vehicle follow the generated path in the vector space. Because most algorithms for terminal speed control are developed based on the vertical plane [13], [24], [36], the composition of guidance laws, APG+LQG, is selected as a compared method: APG [13] on the vertical plane takes charge of terminal speed control and vertical impact angle, and LQG [2] on the horizontal plane is designed for horizontal impact angle control.…”

“…Based on the terminal speed predicted by repeatedly performing numerical integration with predefined dynamic equations, the appropriate coefficients of a polynomial for guidance command are determined using iterative root-finding algorithms such as the secant method. Lee and Kim [14] proposed a vectorfield guidance (VFG) law to control the terminal speed and horizontal impact angle. VFG generates a reference path in a virtually designed vector space, where the initial and final points of the reference path in the vector space correspond to the initial and desired terminal conditions, respectively, including zero miss distance, desired terminal speed, and desired horizontal impact angle.…”

“…On the other hand, path replanning methods have been proposed for various missions of other aerial vehicle platforms. The path replanning framework is to update the reference path to be feasible and optimal considering in-flight uncertainties, thus it is distinguishable from reference path tracking algorithms such as VFG [14]. Some examples include online trajectory planning for a quadcopter considering slung payload [15] and adaptive path replanning for coordinated operations of drone in dynamic urban environments [16].…”

“…First, the proposed path replanner can take into account uncertainties without explicit knowledge of the dynamic model unlike model-based approaches. For example, VFG assumes that the drag and lift coefficients are constant [14], and does not explicitly take into account the wind effect. It will be demonstrated and analyzed in numerical simulation that VFG is sensitive to external disturbances in some cases, whereas the proposed method can compensate for the wind effect without sensitive behavior.…”