Abstract
We present a two-stage method for solving the terrain following (TF)/terrain avoidance (TA) path-planning problem for unmanned combat air vehicles (UCAVs). The 1st stage of planning takes an optimization approach for generating a 2D path on a horizontal plane with no collision with the terrain. In the 2nd stage of planning, an optimal control approach is adopted to generate a 3D flyable path for the UCAV that is as close as possible to the terrain. An approximate dynamic programming (ADP) algorithm is used to solve the optimal control problem in the 2nd stage by training an action network to approximate the optimal solution and training a critical network to approximate the value function. Numerical simulations indicate that ADP can determine the optimal control variables for UCAVs; relative to the conventional optimization method, the optimal control approach with ADP shows a better performance under the same conditions.
Highlights
Unmanned combat air vehicles (UCAVs) constitute an experimental class of unmanned aerial vehicle
We present a two-stage method for solving the terrain following (TF)/terrain avoidance (TA) path-planning problem for unmanned combat air vehicles (UCAVs)
The digital map used in this study was built on geographic information system (GIS) data from the National Geomatics Center of China (NGCC), covered an area of 33 × 33 km2 and had a sample distance of 0.03 km
Summary
Unmanned combat air vehicles (UCAVs) constitute an experimental class of unmanned aerial vehicle. Mathematical Problems in Engineering for 2D path planning with a chromosome of variable length, this approach cannot be applied to 3D TF/TA missions, and Samar et al [6] proposed integrated guidance and control for flight height, which can accommodate TF missions while considering robustness, but the solution is not optimal. Some authors have used dynamic programming (DP) to solve the optimal control problem by calculating the control variables based on a path comprising discrete segments, which has provided optimal solutions with relatively strong robustness [1]; the large scales of intermediate data restoration and processing—the so called “curse of dimensionality”—has limited the calculation efficiency. ADP, as an effective intelligent control method, solves the curse of dimensionality using an approximate function to replace the actual cost function in DP and has been applied to optimal control problems in path planning [8]. An analysis of a comparison with the conventional method indicates the superiority of the proposed method in certain respects
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.