US 8944824

Multi-modal learning system

An instruction is presented to a user for making a target gesture. The target gesture may be a portion of an exemplary or model symbol. The instruction may be presented in various ways, such as being printed on a writing surface or being played in audio format through a speaker of a smart pen device. A writing gesture made on a writing surface by the user is digitally captured using a smart pen device. The captured writing gesture is compared to the target gesture and feedback is determined based on this comparison. This feedback may indicate the correctness of the user's writing gesture. The feedback may be presented to the user through various means, including through the smart pen device. The comparison may also be used to determine a next instruction for the user to follow.