Midcourse guidance law with neural networks
نویسنده
چکیده
A dual neural network ‘adaptive critic approach’ is used in this study to generate midcourse guidance commands for a missile to reach a predicted impact point while maximizing its final velocity. The adaptive critic approach is based on approximate dynamic programming. The first network, called a ‘critic’, network, outputs the Lagrangian multipliers arising in an optimal control formulation while the second network, called an ‘action’ network, outputs the optimal guidance/control. While a typical adaptive critic structure consists of a single critic and a single controller, the midcourse guidance problem needs indexing in terms of the independent variable and therefore there is a cascade of critics and controllers each set for a different index. Every controller learns from the critic at the previous stage. Though the networks are trained off-line, the resulting control is in a feedback form. A midcourse guidance problem is the first testbed for this approach where the input is vector-valued. The numerical results for a number of scenarios show that the network performance is excellent. Corroboration for optimality is provided by comparisons of the numerical solutions using a shooting method for a number of scenarios. Numerical results demonstrate some attractive features of the adaptive critic approach and show that this formulation works very well in guiding the missile to its final conditions from an envelope of initial conditions. This application also demonstrates the use of adaptive critics as a tool to solve a class of ‘free final time’ problems in optimal control, which are usually very difficult.
منابع مشابه
Midcourse Trajectory Shaping for Air and Ballistic Defence Guidance Using Bezier Curves
A near-optimal midcourse trajectory shaping guidance algorithm is proposed for both air and ballistic target engagement mission attributes for generic long range interceptor missile. This guidance methodology is based on the maximum final velocity as the objective function and maximum permissible flight altitude as the in-flight state constraint as well as the head-on orientation as the termina...
متن کاملModified Generalized Explicit Guidance for Midcourse with Near-Zero Lateral Acceleration in Terminal Phase
By appropriately modifying the generalized explicit guidance and developing it further, an optimal midcourse guidance law is proposed in this paper to ensure terminal impact angle constrained engagement of missiles with near-zero lateral acceleration in the terminal phase. This guidance law generates a desired intermediate point in space as well as the desired angles which needs to be achieved ...
متن کاملOptimal Impact Angle Constrained Guidance with the Seeker’s Lock-on Condition
In this paper, an optimal guidance law with terminal angle constraint considering the seeker’s lock-on condition, in which the target is located within the field-of-view (FOV) and detection range limits at the end of the midcourse phase, is proposed. The optimal solution is obtained by solving an optimal control problem minimizing the energy cost function weighted by a power of range-to-go subj...
متن کاملA fuzzy guidance law for vertical launch interceptors
A fuzzy logic-based guidance design for longer engagement in time and beneficial interception attitudes is investigated and proposed here. The integrated fuzzy logic-based guidance scheme consisting of vertical, midcourse and terminal guidance phases can intercept the target from diverse aspects. The engagement strategy in the vertical guidance phase includes general vertical launch to handle t...
متن کامل