Learning an internal representation of the end-effector configuration space

Laflaquière, Alban; Terekhov, Alexander V.; Gas, Bruno; Ο’Regan, J. Kevin

doi:10.1109/iros.2013.6696507

Cited by 9 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Perceived 3D space is simply a species-specific perceptual interface, not an insight into objective reality; we have argued for this on evolutionary grounds, and researchers in embodied cognition have arrived at a similar conclusion (Laflaquiere et al, 2013; Terekhov and O'Regan, 2013). Space as modeled in physics extends perceived space via the action of groups, e.g., the Euclidean group, Poincare group, or arbitrary differentiable coordinate transformations (Singh and Hoffman, 2013).…”

Section: Objections and Repliesmentioning

confidence: 77%

Objects of consciousness

Hoffman

Prakash

2014

Front. Psychol.

View full text Add to dashboard Cite

Current models of visual perception typically assume that human vision estimates true properties of physical objects, properties that exist even if unperceived. However, recent studies of perceptual evolution, using evolutionary games and genetic algorithms, reveal that natural selection often drives true perceptions to extinction when they compete with perceptions tuned to fitness rather than truth: Perception guides adaptive behavior; it does not estimate a preexisting physical truth. Moreover, shifting from evolutionary biology to quantum physics, there is reason to disbelieve in preexisting physical truths: Certain interpretations of quantum theory deny that dynamical properties of physical objects have definite values when unobserved. In some of these interpretations the observer is fundamental, and wave functions are compendia of subjective probabilities, not preexisting elements of physical reality. These two considerations, from evolutionary biology and quantum physics, suggest that current models of object perception require fundamental reformulation. Here we begin such a reformulation, starting with a formal model of consciousness that we call a “conscious agent.” We develop the dynamics of interacting conscious agents, and study how the perception of objects and space-time can emerge from such dynamics. We show that one particular object, the quantum free particle, has a wave function that is identical in form to the harmonic functions that characterize the asymptotic dynamics of conscious agents; particles are vibrations not of strings but of interacting conscious agents. This allows us to reinterpret physical properties such as position, momentum, and energy as properties of interacting conscious agents, rather than as preexisting physical truths. We sketch how this approach might extend to the perception of relativistic quantum objects, and to classical objects of macroscopic scale.

show abstract

Section: Objections and Repliesmentioning

confidence: 77%

Objects of consciousness

Hoffman

Prakash

2014

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…It can be argued that such an explicit internal representation is unnecessary. As suggested in [48], the constraints could of course be captured implicitly in the system. The explicit internal representation will however be useful for an algorithmic / semantic agent, as opposed to a distributed neural-networks-based agent.…”

Section: Formalization and Definitionsmentioning

confidence: 99%

“…Note once again that building an explicit internal representation of the captured structure is not mandatory. This knowledge could be captured implicitly in the system, as in the neural network presented in [48]. However, having some explicit internal representation of the sets M i and a metric defined on them is useful for an algorithmic / semantic system as opposed to a neural network system.…”

Section: Algorithm For the Generation Of The Internal Representationmentioning

confidence: 99%

“…Note that the naive agent does not know this Jacobian, and that it is introduced here only to accelerate the simulation. A more realistic scenario, in which these manifolds are estimated purely on the basis of unlabelled sensorimotor data, is described in [48]. A sampling of the 2500 manifolds M i corresponding to the outputs m i is illustrated in Fig.…”

Section: Algorithm For the Generation Of The Internal Representationmentioning

confidence: 99%

See 1 more Smart Citation

Learning agent’s spatial configuration from sensorimotor invariants

Laflaquière

Ο’Regan

Argentieri

et al. 2015

Robotics and Autonomous Systems

Self Cite

View full text Add to dashboard Cite

The design of robotic systems is largely dictated by our purely human intuition about how we perceive the world. This intuition has been proven incorrect with regard to a number of critical issues, such as visual change blindness. In order to develop truly autonomous robots, we must step away from this intuition and let robotic agents develop their own way of perceiving. The robot should start from scratch and gradually develop perceptual notions, under no prior assumptions, exclusively by looking into its sensorimotor experience and identifying repetitive patterns and invariants. One of the most fundamental perceptual notions, space, cannot be an exception to this requirement. In this paper we look into the prerequisites for the emergence of simplified spatial notions on the basis of a robot's sensorimotor flow. We show that the notion of space as environmentindependent cannot be deduced solely from exteroceptive information, which is highly variable and is mainly determined by the contents of the environment. The environment-independent definition of space can be approached by looking into the functions that link the motor commands to changes in exteroceptive inputs. In a sufficiently rich environment, the kernels of these functions correspond uniquely to the spatial configuration of the agent's exteroceptors. We simulate a redundant robotic arm with a retina installed at its end-point and show how this agent can learn the configuration space of its retina. The resulting manifold has the topology of the Cartesian product of a plane and a circle, and corresponds to the planar position and orientation of the retina.

show abstract

“…Because each set M is potentially infinite in the case of continuous motor commands, we propose to approximate it by a finite number N = 100 of motor states m ∈ M. The search for these samples could be performed by exhaustively (and/or randomly) exploring the motor space M and tracking which motor states generate the same sensory input. Other approaches could also be proposed like for instance the use of a neural network to directly build an internal space of points of view by capturing the topology of the sensory space(s) (see previous work [19]). Although these options are more realistic in terms of data accessible to the naive agent, we propose instead to use an analytic approach for the sake of computational efficiency.…”

Section: Capturing the Topological Structure Of Spacementioning

confidence: 99%

Discovering space — Grounding spatial topology and metric regularity in a naive agent’s sensorimotor experience

et al. 2018

Self Cite

View full text Add to dashboard Cite

In line with the sensorimotor contingency theory, we investigate the problem of the perception of space from a fundamental sensorimotor perspective. Despite its pervasive nature in our perception of the world, the origin of the concept of space remains largely mysterious. For example in the context of artificial perception, this issue is usually circumvented by having engineers pre-define the spatial structure of the problem the agent has to face. We here show that the structure of space can be autonomously discovered by a naive agent in the form of sensorimotor regularities, that correspond to so called compensable sensory experiences: these are experiences that can be generated either by the agent or its environment. By detecting such compensable experiences the agent can infer the topological and metric structure of the external space in which its body is moving. We propose a theoretical description of the nature of these regularities and illustrate the approach on a simulated robotic arm equipped with an eye-like sensor, and which interacts with an object. Finally we show how these regularities can be used to build an internal representation of the sensor's external spatial configuration.

show abstract

Learning an internal representation of the end-effector configuration space

Cited by 9 publications

References 11 publications

Objects of consciousness

Objects of consciousness

Learning agent’s spatial configuration from sensorimotor invariants

Discovering space — Grounding spatial topology and metric regularity in a naive agent’s sensorimotor experience

Contact Info

Product

Resources

About