Locations and actions are interrelated: some activities tend to occur at specific places, for example a person is more likely to twist his wrist when he is close to a door (to turn the knob). We present an unsupervised fusion method that takes advantage of this characteristic to enhance the recognition of location-related actions (e.g., open, close, switch, etc.). The proposed LocAFusion algorithm acts as a post-processing filter: At run-time, it constructs a semantic map of the environment by tagging action recognitions to Cartesian coordinates. It then uses the accumulated information about a location i) to discriminate between identical actions performed at different places and ii) to correct recognitions that are unlikely, given the other observations at the same location. LocAFusion does not require prior statistics about where activities occur, which allows for seamless deployment to new environments. The fusion approach is agnostic to the sensor modalities and methods used for action recognition and localization. For evaluation, we implemented a fully wearable setup that tracks the user with a foot-mounted motion sensor and the ActionSLAM algorithm. Simultaneously, we recognize hand actions through template matching on the data of a wrist-worn inertial measurement unit. In 10 recordings with 554 performed object interactions, LocAFusion consistently outperformed location-independent action recognition (8-31% increase in F1 score), identified 96% of the objects in the semantic map and overall correctly labeled 82% of the actions in problems with up to 23 classes.

Passive Haptic Learning (PHL) is the acquisition of sensorimotor skills without active attention to learning. One method is to "teach" motor skills using vibration cues delivered by a wearable, tactile interface while the user is focusing on another, primary task. We have created a system for Passive Haptic Learning of typing skills. In a study containing 16 participants, users demonstrated significantly reduced error typing a phrase in Braille after receiving passive instruction versus control (32.85% average decline in error vs. 2.73% increase in error). PHL users were also able to recognize and read more Braille letters from the phrase (72.5% vs. 22.4%). In a second study, containing 8 participants thus far, we passively teach the full Braille alphabet over four sessions. Typing error reductions in participants receiving PHL were more rapid and consistent, with 75% of PHL vs. 0% of control users reaching zero typing error. By the end of the study, PHL participants were also able to recognize and read 93.3% of all Braille alphabet letters. These results suggest that Passive Haptic instruction facilitated by wearable computers may be a feasible method of teaching Braille typing and reading.