Although numerous devices exist to track and share exercise routines based on running and walking, these devices offer limited functionality for strength-training exercises. We introduce RecoFit, a system for automatically tracking repetitive exercises - such as weight training and calisthenics - via an arm-worn inertial sensor. Our goal is to provide real-time and post-workout feedback, with no user-specific training and no intervention during a workout. Toward this end, we address three challenges: (1) segmenting exercise from intermittent non-exercise periods, (2) recognizing which exercise is being performed, and (3) counting repetitions. We present cross-validation results on our training data and results from a study assessing the final system, totaling 114 participants over 146 sessions. We achieve precision and recall greater than 95% in identifying exercise periods, recognition of 99%, 98%, and 96% on circuits of 4, 7, and 13 exercises respectively, and counting that is accurate to ±1 repetition 93% of the time. These results suggest that our approach enables a new category of fitness tracking devices.

We propose an online prediction version of submodular set cover with connections to ranking and repeated active learning. In each round, the learning algorithm chooses a sequence of items. The algorithm then receives a monotone submodular function and suffers loss equal to the cover time of the function: the number of items needed, when items are selected in order of the chosen sequence, to achieve a coverage constraint. We develop an online learning algorithm whose loss converges to approximately that of the best sequence in hindsight. Our proposed algorithm is readily extended to a setting where multiple functions are revealed at each round and to bandit and contextual bandit settings.

We investigate methods for selecting sets of labeled vertices for use in predicting the labels of vertices on a graph. We specifically study methods which choose a single batch of labeled vertices (i.e. offline, non sequential methods). In this setting, we find common graph smoothness assumptions directly motivate simple label selection methods with interesting theoretical guarantees. These methods bound prediction error in terms of the smoothness of the true labels with respect to the graph. Some of these bounds give new motivations for previously proposed algorithms, and some suggest new algorithms which we evaluate. We show improved performance over baseline methods on several real world data sets.

Our understanding of social insect behavior has significantly influenced artificial intelligence (AI) and multirobot systems' research (e.g., ant algorithms and swarm robotics). In this work, however, we focus on the opposite question: "How can multirobot systems research contribute to the understanding of social animal behavior?" As we show, we are able to contribute at several levels. First, using algorithms that originated in the robotics community, we can track animals under observation to provide essential quantitative data for animal behavior research. Second, by developing and applying algorithms originating in speech recognition and computer vision, we can automatically label the behavior of animals under observation. In some cases the automatic labeling is more accurate and consistent than manual behavior identification. Our ultimate goal, however, is to automatically create, from observation, executable models of behavior. An executable model is a control program for an agent that can run in simulation (or on a robot). The representation for these executable models is drawn from research in multirobot systems programming. In this paper we present the algorithms we have developed for tracking, recognizing, and learning models of social animal behavior, details of their implementation, and quantitative experimental results using them to study social insects