Autonomous agents, particularly in the field of robotics, rely on sensory information to perceive and navigate their environment. However, these sensory inputs are often imperfect, leading to distortions in the agent's internal representation of the world. This paper investigates the nature of these perceptual distortions and how they influence autonomous representation learning using a minimal robotic system. We utilize a simulated two - wheeled robot equipped with distance sensors and a compass, operating w ithin a simple square environment. Through analysis of the robot's sensor data during random exploration, we demonstrate how a distorted perceptual space emerges. Despite these distortions, we identify emergent structures within the perceptual space that c orrelate with the physical environment, revealing how the robot autonomously learns a structured representation for navigation without explicit spatial information. This work contributes to the understanding of embodied cognition, minimal agency, and the r ole of perception in self - generated navigation strategies in artificial life.

This study investigates how learners organize perceptual space in early phonetic acquisition by advancing previous studies in two key aspects. Firstly, it examines the shape of the learned hidden representation as well as its ability to categorize phonetic categories. Secondly, it explores the impact of training models on context-free acoustic information, without involving contextual cues, on phonetic acquisition, closely mimicking the early language learning stage. Using a cross-linguistic modeling approach, autoencoder models are trained on English and Mandarin and evaluated in both native and non-native conditions, following experimental conditions used in infant language perception studies. The results demonstrate that unsupervised bottom-up training on context-free acoustic information leads to comparable learned representations of perceptual space between native and non-native conditions for both English and Mandarin, resembling the early stage of universal listening in infants. These findings provide insights into the organization of perceptual space during early phonetic acquisition and contribute to our understanding of the formation and representation of phonetic categories.

This paper presents an algorithm for synthesis of human motion in specified styles. We use a theory of movement observation (Laban Movement Analysis) to describe movement styles as points in a multi-dimensional perceptual space. We cast the task of learning to synthesize desired movement styles as a regression problem: sequences generated via space-time interpolation of motion capture data are used to learn a nonlinear mapping between animation parameters and movement styles in perceptual space. We demonstrate that the learned model can apply a variety of motion styles to pre-recorded motion sequences and it can extrapolate styles not originally included in the training data.

In this study we show that humans form very similar perceptual spaces when they explore parametrically-defined shell-shaped objects visually or haptically. A physical object space was generated by varying three shape parameters. Sighted participants explored pictures of these objects while blindfolded participants haptically explored 3D printouts of the objects. Similarity ratings were performed and analyzed using multidimensional scaling (MDS) techniques. Visual and haptic similarity ratings highly correlate and resulted in very similar visual and haptic MDS maps providing evidence for one shared perceptual space underlying both modalities. To investigate to which degree these results are transferrable to natural objects, we performed the same visual and haptic similarity ratings and multidimensional scaling analyses using a set of natural sea shells.

A form of categorical perception occurs constantly outside the laboratory, as when different The history of research on speech perception is speakers produce the "same" word or when a speaker says replete with examples of nonlinearities, or threshold the "same" word quickly or slowly. This means that phenomena, relating acoustics to perception. These speech perception cannot be a simple concatenation of nonlinearities are essential in that they allow stable sound elements to yield syllables, syllables to yield communication despite variation in the acoustic signal words, or words to yield sentences. The interdependency across speakers, emphasis, background noise, etc. across scales reveals a complex system with nonlinearly Furthermore, the range of acoustic signals perceived as interacting elements that somehow allow veridical equivalent is much larger for speech sounds than for communication.

In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-based image classifier in front of a reinforcement learning algorithm. The classifier partitions the visual space according to the presence or absence of few highly informative local descriptors that are incrementally selected in a sequence of attempts to remove perceptual aliasing. We also address the problem of fighting overfitting in such a greedy algorithm. Finally, we show how high-level visual features can be generated when the power of local descriptors is insufficient for completely disambiguating the aliased states. This is done by building a hierarchy of composite features that consist of recursive spatial combinations of visual features. We demonstrate the efficacy of our algorithms by solving three visual navigation tasks and a visual version of the classical ``Car on the Hill'' control problem.