Abstract not found

This study presents experiments on the learning of object handling behaviors by a small humanoid robot using a dynamic neural network model, the recurrent neural network with parametric bias (RNNPB). The first experiment showed that after the robot learned different types of ball handling behaviors using human direct teaching, the robot was able to generate adequate ball handling motor sequences situated to the relative position between the robot’s hands and the ball. The same scheme was applied to a block handling learning task where it was shown that the robot can switch among learned different block handling sequences, situated to the ways of interaction by human supporters. Our analysis showed that entrainment of the internal memory structures of the RNNPB through the interactions of the objects and the human supporters are the essential mechanisms for those observed situated behaviors of the robot.

The paper examines characteristics of interactive learning between human tutors and a robot having a dynamic neural network model which is inspired by human parietal cortex functions. A humanoid robot, with a recurrent neural network that has a hierarchical structure, learns to manipulate objects. Robots learn tasks in repeated self-trials with the assistance of human interaction which provides physical guidance until tasks are mastered and learning is consolidated within neural networks. Experimental results and the analyses showed that 1) codevelopmental shaping of task behaviors stems from interactions between the robot and tutor, 2) dynamic structures for articulating and sequencing of behavior primitives are selforganized in the hierarchically organized network, and 3) such structures can afford both generalization and context-dependency in generating skilled behaviors.

Abstract. We present a review of recent trends in cognitive robotics that deal with online learning approaches to the acquisition of knowledge, control strategies and behaviors of a cognitive robot or agent. Along this line we focus on the topics of object recognition in cognitive vision, trajectory learning and adaptive control of multi-DOF robots, task learning from demonstration, and general developmental approaches in robotics. We argue for the relevance of online learning as a key ability for future intelligent robotic systems to allow flexible and adaptive behavior within a changing and unpredictable environment. 1

Abstract — This paper introduces the early stages of a study designed to understand the development of dance interactions between QRIO and toddlers in a classroom environment. The study is part of a project to explore the potential use of interactive robots as instructional tools in education. After 3 months observation period, we are starting the experiment. After explaining the experimental environment, component technologies used in it are described: an interactive dance with visual feedback, exploiting the active detection of contingency and robotic emotion expression. Index Terms — humanoid robot, QRIO, the RUBI/QRIO project, toddlers, long-term interaction, engaging interaction,

The paper introduces a model that accounts for cognitive mechanisms of learning and generating multiple goal-directed actions. The model employs a novel idea of so-called the “sensory forward model” which is assumed to function in inferior parietal cortex for generation of skilled behaviors in humans and monkeys. A set of different goal-directed actions can be generated by the sensory forward model by utilizing the initial sensitivity characteristics of its acquired forward dynamics. The analyses on our robotics experiments show qualitatively that (1) how generalization in learning can be achieved for situational variances, (2) how the top-down intention toward a specific goal state can reconcile with the bottom-up sensation from the reality.

Abstract — This paper introduces the early stages of a study designed to understand the development of dance interactions between QRIO and toddlers in a classroom environment. The study is part of a project to explore the potential use of interactive robots as instructional tools in education. After 3 months observation period, we are starting the experiment. The experimental environment, component technologies, and plans for evaluating interaction are described. Index Terms — humanoid robot, QRIO, the RUBI project, toddlers, long-term interaction, engaging interaction, interactive dance, contingency detection I.

The brain’s decoding of fast sensory streams is currently impossible to emulate, even approximately, with artificial agents. For example, robust speech recognition is relatively easy for humans but exceptionally difficult for artificial speech recognition systems. In this paper, we propose that recognition can be simplified with an internal model of how sensory input is generated, when formulated in a Bayesian framework. We show that a plausible candidate for an internal or generative model is a hierarchy of ‘stable heteroclinic channels’. This model describes continuous dynamics in the environment as a hierarchy of sequences, where slower sequences cause faster sequences. Under this model, online recognition corresponds to the dynamic decoding of causal sequences, giving a representation of the environment with predictive power on several timescales. We illustrate the ensuing decoding or recognition scheme using synthetic sequences of syllables, where syllables are sequences of phonemes and phonemes are sequences of sound-wave modulations. By presenting anomalous stimuli, we find that the resulting recognition dynamics disclose inference at multiple time scales and are reminiscent of neuronal dynamics seen in the real brain.

Abstract not found

Abstract: The authors have proposed a very simple autonomous learning system consisting of one neural network (NN), whose inputs are raw sensor signals and whose outputs are directly passed to actuators as control signals, and which is trained by using reinforcement learning (RL). However, the current opinion seems that such simple learning systems do not actually work on complicated tasks in the real world. In this paper, with a view to developing higher functions in robots, the authors bring up the necessity to introduce autonomous learning of a massively parallel and cohesively flexible system with massive inputs based on the consideration about the brain architecture and the sequential property of our consciousness. The authors also bring up the necessity to place more importance on “optimization ” of the total system under a uniform criterion than “understandability ” for humans. Thus, the authors attempt to stress the importance of their proposed system when considering the future research on robot intelligence. The experimental result in a realworld-like environment shows that image recognition from as many as 6240 visual signals can be acquired through RL under various backgrounds and light conditions without providing any knowledge about image processing or the target object. It works even for camera image inputs that were not experienced in learning. In the hidden layer, template-like representation, division of roles between hidden neurons, and representation to detect the target uninfluenced by light condition or background were observed after learning. The autonomous acquisition of such useful representations or functions makes us feel the potential towards avoidance of the frame problem and the development of higher functions. Key Words: reinforcement learning, neural network, function emergence, robot, image recognition. 1.