Rapid learning of humanoid body schemas with Kinematic Bézier Maps

نویسندگان

  • Stefan Ulbrich
  • Vicente Ruiz de Angulo
  • Tamim Asfour
  • Carme Torras
  • Rüdiger Dillmann
چکیده

This paper addresses the problem of hand-eye coordination and, more specifically, tool-eye recalibration of humanoid robots. Inspired by results from neuroscience, a novel method to learn the forward kinematics model as part of the body schema of humanoid robots is presented. By making extensive use of techniques borrowed from the field of computer-aided geometry, the proposed Kinematic Bezier Maps (KB-Maps) permit reducing this complex problem to a linearly-solvable, although high-dimensional, one. Therefore, in the absence of noise, an exact kinematic model is obtained. This leads to rapid learning which, unlike in other approaches, is combined with good extrapolation capabilities. These promising theoretical advantages have been validated through simulation, and the applicability of the method to real hardware has been demonstrated through experiments on the humanoid robot ARMAR-IIIa.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Improving Body Schema Learning with Kinematic Bézier Maps by Symmetry Constraints

In robotics, the term body schema refers to the representation of the own body and its sensorimotor relations that are obtained by machine learning, ideally, from selfobservation. It grants the robot a higher degree of autonomy as it allows the compensation of deformations of the body, for instance, those induced by holding a tool, without the need of a manually created explicit model. The forw...

متن کامل

Learning robot dynamics with Kinematic Bézier Maps

The previously presented Kinematic Bézier Maps (KBM) are a machine learning algorithm that has been tailored to efficiently learn the kinematics of redundant robots. This algorithms relies upon a representation based on projective geometry that uses a special set of polynomial functions borrowed from the field of Computer Aided Geometric Design (CAGD). So far, it has only been possible to learn...

متن کامل

Kinematic Bézier Maps

The kinematics of a robot with many degrees of freedom is a very complex function. Learning this function for a large workspace with a good precision requires a huge number of training samples, i.e., robot movements. In this paper, we introduce the Kinematic Bézier Map (KB-Map), a parameterizable model without the generality of other systems but whose structure readily incorporates some of the ...

متن کامل

Flexible Foot/Ankle Based on PKM with Force/Torque Sensor for Humanoid Robot

This paper describes the development of a novel humanoid robot foot/ankle based on an orientation Parallel Kinematic Mechanism for intelligent and flexible control. With three identical Universal-Prismatic-Spherical prismatic-actuated limbs and a central Universal-Revolute passive limb, the PKM can perform three degrees of freedom rotation motions. In order to enable the humanoid robot safely t...

متن کامل

Sensorimotor Learning for an Artificial Body Schema on Humanoid Robots

In robotics, the term body schema refers to adaptive representations of a robot’s own body and involved sensorimotor relations. Such representations are obtained by machine learning, ideally, autonomously from self-observation. The body schema grants robots much higher degrees of autonomy as it allows the compensation of changes to the body (for instance, those induced by holding a tool) withou...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2009