Learning an internal representation of the end-effector configuration space

by   Alban Laflaquière, et al.

Current machine learning techniques proposed to automatically discover a robot kinematics usually rely on a priori information about the robot's structure, sensors 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.


page 1

page 2

page 3

page 4


Virtual Forward Dynamics Models for Cartesian Robot Control

In industrial context, admittance control represents an important scheme...

Sensor Observability Analysis for Maximizing Task-Space Observability of Articulated Robots

In this paper, we propose a novel performance metric for articulated rob...

Robust asymptotic stability of two-wheels differential drive mobile robot

The paper proposes the stable motion control law design method for non-h...

Machine Learning in Appearance-based Robot Self-localization

An appearance-based robot self-localization problem is considered in the...

Task Space Control of Robot Manipulators based on Visual SLAM

This paper aims to address the open problem of designing a globally stab...

Learning agent's spatial configuration from sensorimotor invariants

The design of robotic systems is largely dictated by our purely human in...

Please sign up or login with your details

Forgot password? Click here to reset