Emergence of Spatial Coordinates via Exploration

10/29/2020
by   Alban Laflaquière, et al.
0

Spatial knowledge is a fundamental building block for the development of advanced perceptive and cognitive abilities. Traditionally, in robotics, the Euclidean (x,y,z) coordinate system and the agent's forward model are defined a priori. We show that a naive agent can autonomously build an internal coordinate system, with the same dimension and metric regularity as the external space, simply by learning to predict the outcome of sensorimotor transitions in a self-supervised way.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/02/2018

Unsupervised Emergence of Spatial Structure from Sensorimotor Prediction

Despite its omnipresence in robotics application, the nature of spatial ...
research
11/05/2021

A space of goals: the cognitive geometry of informationally bounded agents

Traditionally, Euclidean geometry is treated by scientists as a priori a...
research
10/03/2018

A Non-linear Approach to Space Dimension Perception by a Naive Agent

Developmental Robotics offers a new approach to numerous AI features tha...
research
06/04/2019

Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction

Despite its omnipresence in robotics application, the nature of spatial ...
research
06/10/2019

Self-Supervised Exploration via Disagreement

Efficient exploration is a long-standing problem in sensorimotor learnin...
research
03/15/2023

Relative coordinates are crucial for Ulam's "trick to the train of thought"

Spatial signal processing algorithms often use pre-given coordinate syst...

Please sign up or login with your details

Forgot password? Click here to reset