In this study, we propose a neural network based model for learning a robot's drawing sequences in an unsupervised manner. We focus on the ability to learn visual-motor relationships, which can work as a reusable memory in association of drawing motion from a picture image. Assuming that a humanoid robot can draw a shape on a pen tablet, the proposed model learns drawing sequences, which comprises drawing motion and drawn picture image frames. To learn raw pixel data without any given specific features, we utilized a deep neural network for compressing large dimensional picture images and a continuous time recurrent neural network for integration of motion and picture images. To confirm the ability of the proposed model, we performed an experiment for learning 15 sequences comprising three types of shapes. The model successfully learns all the sequences and can associate a drawing motion from a not trained picture image and a trained picture with similar success. We also show that the proposed model self-organizes its behavior according to types shapes.

Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for reliable speech recognition, particularly when the audio is corrupted by noise. However, cautious selection of sensory features is crucial for attaining high recognition performance. In the machine-learning community, deep learning approaches have recently attracted increasing attention because deep neural networks can effectively extract robust latent features that enable various recognition algorithms to demonstrate revolutionary generalization capabilities under diverse application conditions. This study introduces a connectionist-hidden Markov model (HMM) system for noise-robust AVSR. First, a deep denoising autoencoder is utilized for acquiring noise-robust audio features. By preparing the training data for the network with pairs of consecutive multiple steps of deteriorated audio features and the corresponding clean features, the network is trained to output denoised audio features from the corresponding features deteriorated by noise. Second, a convolutional neural network (CNN) is utilized to extract visual features from raw mouth area images. By preparing the training data for the CNN as pairs of raw images and the corresponding phoneme label outputs, the network is trained to predict phoneme labels from the corresponding mouth area input images. Finally, a multi-stream HMM (MSHMM) is applied for integrating the acquired audio and visual HMMs independently trained with the respective features. By comparing the cases when normal and denoised mel-frequency cepstral coefficients (MFCCs) are utilized as audio features to the HMM, our unimodal isolated word recognition results demonstrate that approximately 65 % word recognition rate gain is attained with denoised MFCCs under 10 dB signal-to-noise-ratio (SNR) for the audio signal input. Moreover, our multimodal isolated word recognition results utilizing MSHMM with denoised MFCCs and acquired visual features demonstrate that an additional word recognition rate gain is attained for the SNR conditions below 10 dB.

This paper presents a novel computational approach for modeling and generating multiple object manipulation behaviors by a humanoid robot. The contribution of this paper is that deep learning methods are applied not only for multimodal sensor fusion but also for sensory-motor coordination. More specifically, a time-delay deep neural network is applied for modeling multiple behavior patterns represented with multi-dimensional visuomotor temporal sequences. By using the efficient training performance of Hessian-free optimization, the proposed mechanism successfully models six different object manipulation behaviors in a single network. The generalization capability of the learning mechanism enables the acquired model to perform the functions of cross-modal memory retrieval and temporal sequence prediction. The experimental results show that the motion patterns for object manipulation behaviors are successfully generated from the corresponding image sequence, and vice versa. Moreover, the temporal sequence prediction enables the robot to interactively switch multiple behaviors in accordance with changes in the displayed objects.

Our brain is known to enhance perceptual precision and reduce ambiguity about sensory environment by integrating multiple sources of sensory information acquired from different modalities, such as vision, auditory and somatic sensation. From an engineering perspective, building a computational model that replicates this ability to integrate multimodal information and to self-organize the causal dependency among them, represents one of the central challenges in robotics. In this study, we propose such a model based on a deep learning framework and we evaluate the proposed model by conducting a bell ring task using a small humanoid robot. Our experimental results demonstrate that (1) the cross-modal memory retrieval function of the proposed method succeeds in generating visual sequence from the corresponding sound and bell ring motion, and (2) the proposed method leads to accurate causal dependencies among the sensory-motor sequence.

We propose neural models for segmenting the area of a body from visual scene based on predictability. Neuroscience has shown that a prediction model in brain, which predicts sensory-feedback from motor command, can divide the sensory-feedback into the self-motion derived feedback and other derived feedback. The prediction model is important for prediction control of the body. Previous studies in robotics of the prediction model assumed that a robot can recognize the position of its body (e.g. its hand) and that the view contains only that body part. In our models, motor commands and visual feedback (pixel image that includes not only a hand but also object and background) are input into a neural network model and then the body area is segmented and prediction model of body is acquired. Our model contains two parts: 1) An object detection model obtains a conversion system between object positions and the pixel image. 2) A movement prediction model predicts hand-object positions from motor commands and identifies the body. We confirmed that our models can segment the body/object area based on their pixel textures and discriminate between them by using prediction error.

Recent studies on embodied cognitive science have shown us the possibility of emergence of more complex and nontrivial behaviors with quite simple designs if the designer takes the dynamics of the system-environment interaction into account properly. In this paper, we report our tentative classification experiments of several objects using the human-like autonomous robot, "WAMOEBA-2Ri". As modeling the environment, we focus on not only static aspects of the environment but also dynamic aspects of it including that of the system own. The visualized result of this experiment shows the integration of multimodal sensor dataset acquired by the system-environment interaction ("grasping") enable robust categorization of several objects. Finally, in discussion, we demonstrate a possible application to making "invariance in motion" emerge consequently by extending this approach.

This paper aims to clarify the cooperation intelligence of robots. This paper describes the autonomous robot named WAMOEBA-2R which can communicate with humans by both an informational and physical way. WAMOEBA-2R has two arms of which each joint has a torque sensor to realize the physical interaction with humans, the function of the voice recognition and the face recognition. The arms are controlled by a distributed agent network system. The network architecture is acquired in a neural network by the feedback-error-learning algorithm. We surveyed 150 visitors at the '99 International Robot Exhibition held in Tokyo (Oct. 1999) to evaluate their psychological impressions of WAMOEBA-2R. As a result, some factors of the human-robot emotional communication were discovered.