The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We address self-perception and object discovery by integrating multimodal tactile, proprioceptive and visual cues. Considering sensory signals as the only way to obtain relevant information about the environment, we enable a humanoid robot to infer potential usable objects relating visual self-detection with tactile cues. Hierarchical Bayesian models are combined with signal processing and protoobject...
The grid cells in the entorhinal cortex of a rodent provides the animal with a unique neurobiological based coordinate system. This coordinate system is from which cognitive maps and spatial awareness are derived. This paper presents a unique neurobiological inspired mobile robot navigation mapping system that emulates the functional characteristics of the grid cell in a field programmable gate array...
In this paper we present a neurally plausible model of human infant reaching that is based on embodied artificial intelligence, which emphasizes the importance of the sensorimotor interaction of an agent and the world. This model encompasses both learning sensorimotor correlations through motor babbling and also arm motion planning using spreading activation. This model is organized in three layers...
Problems with joint attention (JA) are core features of Autism Spectrum Disorders (ASD). Here, we investigate how typically developing (TD) children and children with ASD respond to joint attention (RJA) and initiate joint attention (IJA) with a gaze contingent avatar. Thirty-one participants with ASD and 33 TD matched controls followed and directed the avatar's gaze to a series of referent images...
Between 6 and 9 months of age, infants begin to differentiate between the actions of others that are “rational” with respect to goals and those that are not. According to the teleological stance theory, this behavior is underpinned by an innate, naive rationality principle; according to a statistical learning account, experience alone is sufficient to explain this behavior. We present a recurrent...
Word discovery is a critical part of language acquisition for infants. Human infants can discover words from human speech signals directly. However, direct word discovery from raw speech signals is still a challenging problem for recent artificial intelligence technology. This paper describes our new experimental result based on the state-of-the-art machine learning method, which we previously proposed,...
This poster presentation represents an attempt to harmonize unidirectional “mapping” from Conceptual Metaphor Theory (CMT) and cognitive linguistics with knowledge from cognitive neuroscience to explain how details of feature attribution are determined in metaphorical inferencing. Specifically, an adapted view of “mapping” (herein termed “conceptual filtering”) will be proposed. In this view, unidirectional...
Although sensorimotor exploration is a basic process within child development, clear views on the underlying computational processes remain challenging. We propose to compare eight algorithms for sensorimotor exploration, based on three components: “accommodation” performing a compromise between goal babbling and social guidance by a master, “local extrapolation” simulating local exploration of the...
Psychologists report that infants rely on shape rather than colour for object recognition, differentiation and generalisation for both verbal and non-verbal tasks. In this paper we propose a mechanism for object generalisation, based on inductive inference and differentiation using visual along with non-visual information obtained through the manipulation of various objects. Experiments are conducted...
Predictive Processing (PP) [1], [2], [3] is becoming an influential account in cognitive neuroscience, including developmental neuroscience [4]. According to PP, human brains interpret their sensory inputs by predicting them, based on a hierarchy of generative models. These predictions are then compared to the actual, observed inputs, and the difference between predictions and observations (so-called...
The ‘sense of agency’ refers to the experiential state that one's actions cause events in the world. Developing a sense of agency allows infants to learn from interacting with the social and physical world in ways that would not be possible otherwise [1]. To date, few empirical studies seem to target this phenomenon in infancy directly. Notable exceptions are the work by Rochat and colleagues (e.g...
Developmental robotics suggests that the forward and inverse kinematics should be learned through a sensory-motor mapping, instead of being programmed in advance. Motor babbling and goal babbling are two common approaches to generate training samples used to acquire a sensory-motor mapping. Motor babbling typically needs a considerable amount of training data and time to acquire a sufficient mapping,...
We present an approach that enables robots to self-organize their sensorimotor behavior from scratch without providing specific information about neither the robot nor its environment. This is achieved by a simple neural control law that increases the consistency between external sensor dynamics and internal neural dynamics of the utterly simple controller. In this way, the embodiment and the agent-environment...
We have proposed a way to simulate how communication could emerge in a simple n by n grid world task among multi-agent. We showed that by introducing simple learning communication among multi reinforcement learners, agents could reach a coordinated behavior to obtain a higher reward. We also provided a feasible way to overcome the problem of partial observability with reinforcement learning in multi-agent...
This study investigates the seamless integration of cognitive skills, such as visual recognition, attention switching, action preparation and generation for a humanoid robot. In our preliminary study [1], the deep dynamic neural network model was introduced to process spatio-temporal visuomotor patterns. In the current study, we extended the previous model further to enhance its capability of handling...
Human neonates show a natural predisposition towards biological motion: despite the limited visual information available, they can distinguish the movement of other living agents from object motion. This ability has been suggested to be the basis for identifying conspecifics from birth, hence representing a fundamental skill for the development of social interaction. Inspired by this, we propose a...
We use goal babbling to bootstrap a parametric model of speech production for a complex 3D vocal tract model. The system learns to control the articulators for producing five different vowel sounds. Ambient speech influences learning on two levels: it organizes the learning process because it is used to generate a space of goals in which exploration takes place. A distribution learned from ambient...
We propose an embodied statistical language model for learning the meaning of word sequences, which incorporate action words (i.e. push, pull, tap, etc.,). The model attempts to unify embodied grounding and dis-embodied processing by representing the meaning of word sequences in both the sensorimotor and linguistic knowledge of a humanoid robot. The modeling of word sequences enables to distinguish...
The concept of direction is one of most important capabilities of a robot in order to better understand the world and accomplish various tasks in the real environment. This paper addresses the problem on how does a robot achieve such a capability. Instead of employing information derived from vision or audition, motion cues are investigated in this study. Specifically, achieving the concept of direction...
This paper discusses lexicon word learning in high-dimensional meaning spaces from the viewpoint of referential uncertainty. We investigate various state-of-the-art Machine Learning algorithms and discuss the impact of scaling, representation and meaning space structure. We demonstrate that current Machine Learning techniques successfully deal with high-dimensional meaning spaces. In particular, we...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.