Recently, infomax methods of optimal control have begun to reshape how we think about active information gathering. We show how such methods can be used to formulate the problem of choosing where to look. We show how an optimal eye movement controller can be learned from subjective experiences of information gathering, and we explore in simulation properties of the optimal controller. This controller outperforms other eye movement strategies proposed in the literature. The learned eye movement strategies are tailored to the specific visual system of the learner-we show that agents with different kinds of eyes should follow different eye movement strategies. Then we use these insights to build an autonomous computer program that follows this approach and learns to search for faces in images faster than current state-of-the-art techniques. The context of these results is search in static scenes, but the approach extends easily, and gives further efficiency gains, to dynamic tracking tasks. A limitation of infomax methods is that they require probabilistic models of uncertainty of the sensory system, the motor system, and the external world. In the final section of this paper, we propose future avenues of research by which autonomous physical agents may use developmental experience to subjectively characterize the uncertainties they face.
VL - 2 IS - 2 ER - TY - CONF T1 - Learning to Make Facial Expressions T2 - IEEE 8th International Conference on Development and Learning, 2009. ICDL 2009 Y1 - 2009 A1 - Wu, T. A1 - Butko, N. A1 - Ruvulo, P. A1 - Bartlett, M. A1 - Movellan, J. KW - Actuators KW - Emotion recognition KW - face detection KW - face recognition KW - facial motor parameters KW - Feedback KW - Humans KW - learning (artificial intelligence) KW - Machine Learning KW - Magnetic heads KW - Pediatrics KW - real-time facial expression recognition KW - Robot sensing systems KW - robotic head KW - Robots KW - self-guided learning KW - Servomechanisms KW - Servomotors AB -This paper explores the process of self-guided learning of realistic facial expression production by a robotic head with 31 degrees of freedom. Facial motor parameters were learned using feedback from real-time facial expression recognition from video. The experiments show that the mapping of servos to expressions was learned in under one-hour of training time. We discuss how our work may help illuminate the computational study of how infants learn to make facial expressions.
JF - IEEE 8th International Conference on Development and Learning, 2009. ICDL 2009 PB - IEEE CY - Shanghai SN - 978-1-4244-4117-4 ER - TY - CONF T1 - Auditory mood detection for social and educational robots T2 - IEEE International Conference on Robotics and Automation, 2008. ICRA 2008 Y1 - 2008 A1 - Ruvolo, P. A1 - Fasel, I. A1 - Movellan, J. KW - auditory mood detection KW - Computer vision KW - educational robot KW - Educational robots KW - Emotion recognition KW - emotional speech database KW - face detection KW - hearing KW - interactive robotic application KW - learning (artificial intelligence) KW - Machine Learning KW - Mood Prototypes KW - object recognition KW - Robotics and Automation Robots KW - social mood KW - social robot KW - Speech KW - USA Councils AB -Social robots face the fundamental challenge of detecting and adapting their behavior to the current social mood. For example, robots that assist teachers in early education must choose different behaviors depending on whether the children are crying, laughing, sleeping, or singing songs. Interactive robotic applications require perceptual algorithms that both run in real time and are adaptable to the challenging conditions of daily life. This paper explores a novel approach to auditory mood detection which was born out of our experience immersing social robots in classroom environments. We propose a new set of low-level spectral contrast features that extends a class of features which have proven very successful for object recognition in the modern computer vision literature. Features are selected and combined using machine learning approaches so as to make decisions about the ongoing auditory mood. We demonstrate excellent performance on two standard emotional speech databases (the Berlin Emotional Speech [W. Burkhardt et al., 2005], and the ORATOR dataset [H. Quast, 2001]). In addition we establish strong baseline performance for mood detection on a database collected from a social robot immersed in a classroom of 18-24 months old children [J. Movellan er al., 2007]. This approach operates in real time at little computational cost. It has the potential to greatly enhance the effectiveness of social robots in daily life environments.
JF - IEEE International Conference on Robotics and Automation, 2008. ICRA 2008 PB - IEEE CY - Pasadena, CA SN - 978-1-4244-1646-2 ER - TY - CONF T1 - A discriminative approach to frame-by-frame head pose tracking T2 - 8th IEEE International Conference on Automatic Face Gesture Recognition, 2008. FG '08 Y1 - 2008 A1 - Whitehill, J. A1 - Movellan, Javier R. KW - accuracy drift KW - continuous video sequence KW - controlled illumination condition KW - discriminative approach KW - face detection KW - face recognition KW - facial appearance KW - frame-by-frame head pose tracking KW - Humans KW - Image analysis KW - Image databases KW - Laboratories KW - Lighting KW - Magnetic heads KW - mean square error methods KW - pose estimation KW - Robustness KW - root-mean-square error tracking KW - System testing KW - Video sequences AB -We present a discriminative approach to frame-by-frame head pose tracking that is robust to a wide range of illuminations and facial appearances and that is inherently immune to accuracy drift. Most previous research on head pose tracking has been validated on test datasets spanning only a small (< 20) subjects under controlled illumination conditions on continuous video sequences. In contrast, the system presented in this paper was both trained and tested on a much larger database, GENKI, spanning tens of thousands of different subjects, illuminations, and geographical locations from images on the Web. Our pose estimator achieves accuracy of 5.82deg, 5.65deg, and 2.96deg root-mean-square (RMS) error for yaw, pitch, and roll, respectively. A set of 4000 images from this dataset, labeled for pose, was collected and released for use by the research community.
JF - 8th IEEE International Conference on Automatic Face Gesture Recognition, 2008. FG '08 PB - IEEE CY - Amsterdam SN - 978-1-4244-2153-4 ER -