Learning agent's spatial configuration from sensorimotor invariants

by   Alban Laflaquière, et al.

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 environment-independent 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.


page 1

page 2

page 3

page 4


Unsupervised Emergence of Spatial Structure from Sensorimotor Prediction

Despite its omnipresence in robotics application, the nature of spatial ...

Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction

Despite its omnipresence in robotics application, the nature of spatial ...

Space as an invention of biological organisms

The question of the nature of space around us has occupied thinkers sinc...

Discovering space - Grounding spatial topology and metric regularity in a naive agent's sensorimotor experience

In line with the sensorimotor contingency theory, we investigate the pro...

Learning abstract perceptual notions: the example of space

Humans are extremely swift learners. We are able to grasp highly abstrac...

Learning an internal representation of the end-effector configuration space

Current machine learning techniques proposed to automatically discover a...

Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity

Contemporary sensorimotor learning approaches typically start with an ex...

Please sign up or login with your details

Forgot password? Click here to reset