Two neural network algorithms for designing optimal terminal controllers with open final time
- Plumer, Edward S.
- Oct 1, 1992.
- Physical Description:
- 1 electronic document
- Restrictions on Access:
- Unclassified, Unlimited, Publicly available.
- Multilayer neural networks, trained by the backpropagation through time algorithm (BPTT), have been used successfully as state-feedback controllers for nonlinear terminal control problems. Current BPTT techniques, however, are not able to deal systematically with open final-time situations such as minimum-time problems. Two approaches which extend BPTT to open final-time problems are presented. In the first, a neural network learns a mapping from initial-state to time-to-go. In the second, the optimal number of steps for each trial run is found using a line-search. Both methods are derived using Lagrange multiplier techniques. This theoretical framework is used to demonstrate that the derived algorithms are direct extensions of forward/backward sweep methods used in N-stage optimal control. The two algorithms are tested on a Zermelo problem and the resulting trajectories compare favorably to optimal control results.
- NASA Technical Reports Server (NTRS) Collection.
- Document ID: 19930015948., Accession ID: 93N25137., NAS 1.26:177599., NASA-CR-177599., and A-92194.
- No Copyright.
View MARC record | catkey: 15670679