182 results found
Wang R, Amadori PV, Demiris Y, Real-Time Workload Classification during Driving using HyperNetworks
Classifying human cognitive states from behavioral and physiological signalsis a challenging problem with important applications in robotics. The problemis challenging due to the data variability among individual users, and sensorartefacts. In this work, we propose an end-to-end framework for real-timecognitive workload classification with mixture Hyper Long Short Term MemoryNetworks, a novel variant of HyperNetworks. Evaluating the proposed approach onan eye-gaze pattern dataset collected from simulated driving scenarios ofdifferent cognitive demands, we show that the proposed framework outperformsprevious baseline methods and achieves 83.9\% precision and 87.8\% recallduring test. We also demonstrate the merit of our proposed architecture byshowing improved performance over other LSTM-based methods.
Cully A, Demiris Y, Hierarchical Behavioral Repertoires with Unsupervised Descriptors
Enabling artificial agents to automatically learn complex, versatile andhigh-performing behaviors is a long-lasting challenge. This paper presents astep in this direction with hierarchical behavioral repertoires that stackseveral behavioral repertoires to generate sophisticated behaviors. Eachrepertoire of this architecture uses the lower repertoires to create complexbehaviors as sequences of simpler ones, while only the lowest repertoiredirectly controls the agent's movements. This paper also introduces a novelapproach to automatically define behavioral descriptors thanks to anunsupervised neural network that organizes the produced high-level behaviors.The experiments show that the proposed architecture enables a robot to learnhow to draw digits in an unsupervised manner after having learned to draw linesand arcs. Compared to traditional behavioral repertoires, the proposedarchitecture reduces the dimensionality of the optimization problems by ordersof magnitude and provides behaviors with a twice better fitness. Moreimportantly, it enables the transfer of knowledge between robots: ahierarchical repertoire evolved for a robotic arm to draw digits can betransferred to a humanoid robot by simply changing the lowest layer of thehierarchy. This enables the humanoid to draw digits although it has never beentrained for this task.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.