Adaptive fuzzy command acquisition with reinforcement learning

This paper proposes a four-layered adaptive fuzzy command acquisition network (AFCAN) for adaptively acquiring fuzzy command via interactions with the user or environment. It can catch the intended information from a sentence (command) given in natural language with fuzzy predicates. The intended information includes a meaningful semantic action and the fuzzy linguistic information of that action (for example, the phrase “move forward” represents the meaningful semantic action and the phrase “very high speed” represents the linguistic information in the fuzzy command “move forward at a very high speed”). The proposed AFCAN has three important features. First, we can make no restrictions whatever on the fuzzy command input, which is used to specify the desired information, and the network requires no acoustic, prosodic, grammar, and syntactic structure. Second, the linguistic information of an action is learned adaptively and it is represented by fuzzy numbers based on level sets. Third, the network can learn during the course of performing the task. The AFCAN can perform off-line as well as on-line learning. For the off-line learning, the mutual-information (MI) supervised learning scheme and the fuzzy backpropagation (FBP) learning scheme are employed when the training data are available in advance. The former learning scheme is used to learn meaningful semantic actions and the latter learn linguistic information. The AFCAN can also perform on-line learning interactively when it is in use for fuzzy command acquisition. For the on-line learning, the MI-reinforcement learning scheme and the fuzzy reinforcement learning scheme are developed for the on-line learning of meaningful actions and linguistic information, respectively. An experimental system (fuzzy commands acquisition of a voice control system) is constructed to illustrate the performance and applicability of the proposed AFCAN.