Learning Global Properties of Nonredundant Kinematic Mappings

@article{DeMers1998LearningGP,
  title={Learning Global Properties of Nonredundant Kinematic Mappings},
  author={David DeMers and Kenneth Kreutz-Delgado},
  journal={The International Journal of Robotics Research},
  year={1998},
  volume={17},
  pages={547 - 560}
}
The kinematic mapping x = f(θ) is generally many to one. For nonredundant manipulators, this means that there are a finite num ber of configurations (joint angles) that will place the end-effector at a target location in the workspace. These correspond to pos tures of the manipulator, and each configuration lies on a specific solution branch. It is shown that for certain classes of revolute joint regional manipulators (those with no joint limits and having almost everywhere a constant number of… 
Canonical parameterization of excess motor degrees of freedom with self-organizing maps
TLDR
A method is presented for solving the nonlinear inverse kinematics problem for a redundant manipulator by learning a natural parameterization of the inverse solution manifolds with self-organizing maps.
A complete analytical solution to the inverse kinematics of the Pioneer 2 robotic arm
TLDR
A first complete analytical solution to the inverse kinematics of the P2Arm is presented, which makes it possible to control the arm to any reachable position in an unstructured environment.
A Hybrid Appproach to Inverse Kinematics Modeling and Control of Pioneer 2 Robotic Arms
TLDR
A first analytical solution to the inverse kinematics of a widely used robotic arm (Pioneer 2 robotic arm) is presented, which, combined with an optimal search method, provides an effective solution with respect to the modeling and control of the Pioneer 2 robotic arms.
Trajectory inverse kinematics by conditional density modes
TLDR
A machine learning approach for trajectory inverse kinematics to find a feasible trajectory in angle space, which can reconstruct the true angle trajectory even when the workspace trajectory contains singularities, and when the number of inverse branches depends on the workspace location.
Reconstruction of sequential data with density models
TLDR
This work proposes an algorithm based on two redundancy assumptions: vector redundancy (the data live in a low-dimensional manifold, so that the present variables constrain the missing ones; and sequence redundancy (e.g. continuity), so that consecutive vectors constrain each other.
Continuous latent variable models for dimensionality reduction and sequential data reconstruction
TLDR
A new method for missing data reconstruction of sequential data that includes as particular case the inversion of many-to-one mappings is proposed, based on multiple pointwise reconstruction and constraint optimisation.
Dimensionality Reduction 4.1 Introduction 4.1.1 Classes of Dimensionality Reduction Problems
  • Computer Science
TLDR
This chapter surveys non-probabilistic methods for dimen-sionality reduction, that is, methods that do not define a probabilistic model for the data, including linear methods, nonlinear autoassociators, kernel methods, local dimensionality Reduction, principal curves, vector quantisation methods and multidimensional scaling methods.
Experiments with real-world data: the acoustic-to-articulatory mapping problem
  • Computer Science
  • 2007
In this chapter, we apply our reconstruction algorithm to a version of the acoustic-to-articulatory mapping, a well-known mapping inversion problem of speech research. It is a complex,
Data-driven approaches to articulatory speech processing
TLDR
A successful solution to this long standing and unsolved problem can facilitate useful applications in vocal tract visualization, language learning, speech therapy, and improve state-of-art recognition, speech synthesis, speech coding.
Chapter 2 The continuous latent variable modelling formalism
  • Computer Science
TLDR
This chapter gives the theoretical basis for continuous latent variable models, and discusses other important topics, including parameter estimation, identifiability, interpretability and marginalisation in high dimensions.
...
1
2
...

References

SHOWING 1-10 OF 28 REFERENCES
Learning Global Topological Properties of Robot Kinematic Mappings for Neural Network-based Configuration Control
We examine the topology of the kinematics mapping and propose methods for resolving redundancy and the multiplicity of disjoint pre-image manifolds, resulting in a global regularization of the
Canonical parameterization of excess motor degrees of freedom with self-organizing maps
TLDR
A method is presented for solving the nonlinear inverse kinematics problem for a redundant manipulator by learning a natural parameterization of the inverse solution manifolds with self-organizing maps.
Learning Global Direct Inverse Kinematics
TLDR
A bootstrap method for construction of an inverse function for the robot kinematic mapping using only sample configuration--space/ workspace data is introduced and a global inverse kinematics solution for the wristless Puma manipulator is developed.
THE KINEMATICS OF MANIPULATORS UNDER COMPUTER CONTROL
TLDR
A set of heuristics is developed for moving a six degree-of-freedom manipulator from an initial position to a final position through a space containing obstacles, which results in a computer program shown to be able to direct a manipulator around obstacles.
Kinematic analysis of the 6R manipulator of general geometry
TLDR
This paper presents a new solution to the inverse kinematics problem for the 6R series manipulator of general geometry, which has 6 revolute (R) joints arranged in series.
Adaptive visual-motor coordination in multijoint robots using parallel architecture
  • M. Kuperstein
  • Computer Science
    Proceedings. 1987 IEEE International Conference on Robotics and Automation
  • 1987
This article derives and simulates a neural-like network architecture that adaptively controls a visually guided, two-jointed robot arm to reach spot targets in three dimensions. The architecture
Three-dimensional neural net for learning visuomotor coordination of a robot arm
An extension of T. Kohonen's (1982) self-organizing mapping algorithm together with an error-correction scheme based on the Widrow-Hoff learning rule is applied to develop a learning algorithm for
Some topological problems in robotics
This paper is intended to be an exposition for mathematicians on some problems in engineering, and, before introducing these problems, it seems worthwhile to first arm the reader with at least one
...
1
2
3
...