A non-linear approach to space dimension perception by a naive agent

Laflaquière, Alban; Argentieri, Sylvain; Breysse, Olivia; Genet, Stéphane; Gas, Bruno

doi:10.1109/iros.2012.6385632

Cited by 14 publications

(20 citation statements)

References 8 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Philipona and co-authors showed in [44] that under certain conditions the dimensionality of space can be estimated by analyzing only sensorimotor information that is available to the agent. This result launched a series of publications by the present authors, extending the conditions of dimension estimation [45] and applying similar ideas to different agents and robotic systems [46,47,48].…”

Section: Introductionmentioning

confidence: 85%

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

Section: Introductionmentioning

confidence: 85%

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

show abstract

“…We present a neural network-based algorithm that maps a potentially high dimensional proprioception space into a low dimensional space of internal representation. The dimension of the latter is assumed known here and can be estimated using methods like in [6], [3]. We test the quality of the mapping by making a simulated robot performing reaching movements using the Jacobian of the mapping defined by the neural network.…”

Section: Introductionmentioning

confidence: 99%

Learning an internal representation of the end-effector configuration space

Laflaquière¹,

Terekhov²,

Gas³

et al. 2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

Current machine learning techniques proposed to automatically discover a robot's kinematics usually rely on a priori information about the robot's structure, sensor properties or end-effector position. This paper proposes a method to estimate a certain aspect of the forward kinematics model with no such information. An internal representation of the end-effector configuration is generated from unstructured proprioceptive and exteroceptive data flow under very limited assumptions. A mapping from the proprioceptive space to this representational space can then be used to control the robot.

show abstract

“…It does not know that space is a manifold, even less that it is Euclidean. In this respect the current study is different from similar works [23], [24], [25] which made use of the implicit assumption that space has the structure of a vector space. II.…”

Section: A Spacementioning

confidence: 89%

Learning abstract perceptual notions: The example of space

Terekhov

Ο’Regan

2014

4th International Conference on Development and Learning and on Epigenetic Robotics

View full text Add to dashboard Cite

Humans are extremely swift learners. We are able to grasp highly abstract notions, whether they come from art perception or pure mathematics. Current machine learning techniques demonstrate astonishing results in extracting patterns in information. Yet the abstract notions we possess are more than just statistical patterns in the incoming information. Sensorimotor theory suggests that they represent functions, laws, describing how the information can be transformed, or, in other words, they represent the statistics of sensorimotor changes rather than sensory inputs themselves. The aim of our work is to suggest a way for machine learning and sensorimotor theory to benefit from each other so as to pave the way toward new horizons in learning. We show in this study that a highly abstract notion, that of space, can be seen as a collection of laws of transformations of sensory information and that these laws could in theory be learned by a naive agent. As an illustration we do a one-dimensional simulation in which an agent extracts spatial knowledge in the form of internalized ("sensible") rigid displacements. The agent uses them to encode its own displacements in a way which is isometrically related to external space. Though the algorithm allowing acquisition of rigid displacements is designed ad hoc, we believe it can stimulate the development of unsupervised learning techniques leading to similar results.

show abstract

A non-linear approach to space dimension perception by a naive agent

Cited by 14 publications

References 8 publications

Learning agent’s spatial configuration from sensorimotor invariants

Learning agent’s spatial configuration from sensorimotor invariants

Learning an internal representation of the end-effector configuration space

Learning abstract perceptual notions: The example of space

Contact Info

Product

Resources

About