Neural-Network Control of a Free-Flying Space Robot

Two recent developments in neural- network control are presented. First, a "Fully-Connected Architecture" (FCA) is developed for use with backpropagation (BP). This FCA has functionality beyond that of a layered network, and these capabilities are shown to be particularly beneficial for control tasks. A complexity control method is applied successfully to manage the extra connections provided, and prevent over-fitting. Second, a technique that extends BP learning to discrete-valued functions (DVFs) is presented. This algorithm is applicable whenever a gradient-based optimization is used for systems with DVFs. The modification to BP is very small, simply requiring replacement of the DVFs with continuous approximations and injection of noise on the forward sweep. The viability of both of these neural- network developments is demonstrated by applying them to a thruster-mapping problem characteristic of space robots. Real-world applicability is shown via an experimental demonstration on a 2-D laboratory model of a free-flying space robot.