Several high level methodological debates among AI researchers, linguists, psychologists and philosophers, appear to be endless, e.g. about the need for and nature of representations, about the role of symbolic processes, about embodiment, about situatedness, about whether symbol-grounding is needed, and about whether a robot needs any knowledge at birth or can start simply with a powerful learning mechanism. Consideration of the variety of capabilities and development patterns on the precocial-altricial spectrum in biological organisms will help us to see these debates in a new light. 1

What kind of motivation drives child language development? This article presents a computational model and a robotic experiment to articulate the hypothesis that children discover communication as a result of exploring and playing with their environment. The considered robotic agent is intrinsically motivated towards situations in which it optimally progresses in learning. To experience optimal learning progress, it must avoid situations already familiar but also situations where nothing can be learnt. The robot is placed in an environment in which both communicating and non-communicating objects are present. As a consequence of its intrinsic motivation, the robot explores this environment in an organized manner focusing first on non-communicative activities and then discovering the learning potential of certain types of interactive behaviour. In this experiment, the agent ends up being interested by communication through vocal interactions without having a specific drive for communication.

This article describes a developmental system based on information theory implemented on a real robot that learns a model of its own sensory and actuator apparatus. There is no innate knowledge regarding the modalities or representation of the sensory input and the actuators, and the system relies on generic properties of the robot’s world such as piecewise smooth effects of movement on sensory changes. The robot develops the model of its sensorimotor system by first performing random movements to create an informational map of the sensors. Using this map the robot then learns what effects the different possible actions have on the sensors. After this developmental process the robot can perform basic visually guided movement.

Is there a way for an algorithm linked to an unknown body to infer by itself information about this body and the world it is in? Taking the case of space for example, is there a way for this algorithm to realize that its body is in a three dimensional world? Is it possible for this algorithm to discover how to move in a straight line? And more basically: do these questions make any sense at all given that the algorithm only has access to the very high-dimensional data consisting of its sensory inputs and motor outputs? We demonstrate in this article how these questions can be given a positive answer. We show that it is possible to make an algorithm that, by analyzing the law that links its motor outputs to its sensory inputs, discovers information about the structure of the world regardless of the devices constituting the body it is linked to. We present results from simulations demonstrating a way to issue motor orders resulting in "fundamental" movements of the body as regards the structure of the physical world.

When an object rolls or slides inside a hand-held tube, a variety of cues are normally available to estimate its location inside the cavity. These cues are related to the dynamics of an object subjected to the laws of physics such as gravity and friction. This may be viewed as a form of sensorymotor coupling which does not involve vision but which links motor output to acoustic and tactile inputs. The theory of sensorymotor contingency posits that humans exploit invariants about the physics of their environment and about their own sensorymotor apparatus to develop the perception of the outside world. We report on the design and the results of an experiment where subjects held an apparatus that simulated the physics of an object rolling or sliding inside a tubular cavity. The apparatus synthesized simple haptic cues resulting from rolling noise or impact on internal walls. Given these cues, subjects were asked to discriminate between the lengths of different virtual tubes. The subjects were not trained at the task and had to make judgments from a single gesture. The results support the idea that the subjects mastered invariants related to the dynamics of objects under the influence of gravity that they were able to use them to perceive the length of invisible cavities.

How can we build artificial agents that can autonomously explore and understand their environments? An immediate requirement for such an agent is to learn how its own sensory state corresponds to the external world properties: It needs to learn the semantics of its internal state (i.e., grounding). In principle, we as programmers can provide the agents with the required semantics, but this will compromise the autonomy of the agent. To overcome this problem, we may fall back on natural agents and see how they acquire meaning of their own sensory states, their neural firing patterns. We can learn a lot about what certain neural spikes mean by carefully controlling the input stimulus while observing how the neurons fire. However, neurons embedded in the brain do not have direct access to the outside stimuli, so such a stimulus-to-spike association may not be learnable at all. How then can the brain solve this problem? (We know it does.) We propose that motor interaction with the environment is necessary to overcome this conundrum. Further, we provide a simple yet powerful criterion, sensory invariance, for learning the meaning of sensory states. The basic idea is that a particular form of action sequence that maintains invariance of a sensory state will express the key property of the environmental stimulus that gave rise to the sensory state. Our experiments with a sensorimotor agent trained on natural images show that sensory invariance can indeed serve as a powerful objective for semantic grounding.

How can artificial or natural agents autonomously gain understanding of its own internal (sensory) state? This is an important question not just for physically embodied agents but also for software agents in the information technology environment. In this paper, we investigate this issue in the context of a simple biologically motivated sensorimotor agent. We observe and acknowledge, as many other researchers do, that action plays a key role in providing meaning to the sensory state.

Abstract — This paper describes a developmental system implemented on a real robot that learns a model of its own sensory and actuator apparatuses. There is no innate knowledge regarding the modality or representation of the sensoric input and the actuators, and the system relies on generic properties of the robot’s world such as piecewise smooth effects of movement on sensory changes. The robot develops the model of its sensorimotor system by first performing random movements to create an informational map of the sensors. Using this map the robot then learns what effects the different possible actions have on the sensors. After this developmental process the robot can perform simple motion tracking. Index Terms — developmental robotics, body babbling, emergence of structure I.

What is available to developmental programs in autonomous mental development, and what should be learned at the very early stages of mental development? Our observation is that sensory and motor primitives are the most basic components present at the beginning, and what developmental agents need to learn from these resources is what their internal sensory states stand for. In this paper, we investigate the question in the context of a simple biologically motivated visuomotor agent. We observe and acknowledge, as many other researchers do, that action plays a key role in providing content to the sensory state. We propose a simple, yet powerful learning criterion, that of invariance, where invariance simply means that the internal state does not change over time. We show that after reinforcement learning based on the invariance criterion, the property of action sequence based on an internal sensory state accurately reflects the property of the stimulus that triggered that internal state. That way, the meaning of the internal sensory state can be firmly grounded on the property of that particular action sequence. We expect the framing of the problem and the proposed solution presented in this paper to help shed new light on autonomous understanding in developmental agents such as humanoid robots.

Abstract—Vision is basically a sensory modality, so it is no surprise that the investigation into the brain’s visual functions has been focused on its sensory aspect. Thus, questions like (1) how can external geometric properties represented in internal states of the visual system be grounded, (2) how do the visual cortical receptive fields (RFs) form, and (3) how can visual shapes be recognized have all been addressed within the framework of sensory information processing. However, this view is being challenged on multiple fronts, with an increasing emphasis on the motor aspect of visual function. In this paper, we will review works that implicate the important role of motor function in vision, and discuss our latest results touching upon the issues of grounding, RF development, and shape recognition. Our main findings are that (1) motor primitives play a fundamental role in grounding, (2) RF learning can be biased and enhanced by the motor system, and (3) shape recognition is easier with motorbased representations than with sensor-based representations. The insights we gained here will help us better understand visual cortical function. Also, we expect the motor-oriented view of visual cortical function to be generalizable to other sensory cortices such as somatosensory and auditory cortices. I.