CycleIK: Neuro-inspired Inverse Kinematics

Link:
Autor/in:
Beteiligte Personen:
  • L., Iliadis
  • A., Papaleonidas
  • P., Angelov
  • C., Jayne
Verlag/Körperschaft:
Springer Science and Business Media Deutschland GmbH
Erscheinungsjahr:
2023
Medientyp:
Text
Schlagworte:
  • Generative Adversarial Networks
  • Genetic Algorithms
  • Humanoid Robots
  • Neuro-inspired Inverse Kinematics
Beschreibung:
  • The paper introduces CycleIK, a neuro-robotic approach that wraps two novel neuro-inspired methods for the inverse kinematics (IK) task—a Generative Adversarial Network (GAN), and a Multi-Layer Perceptron architecture. These methods can be used in a standalone fashion, but we also show how embedding these into a hybrid neuro-genetic IK pipeline allows for further optimization via sequential least-squares programming (SLSQP) or a genetic algorithm (GA). The models are trained and tested on dense datasets that were collected from random robot configurations of the new Neuro-Inspired COLlaborator (NICOL), a semi-humanoid robot with two redundant 8-DoF manipulators. We utilize the weighted multi-objective function from the state-of-the-art BioIK method to support the training process and our hybrid neuro-genetic architecture. We show that the neural models can compete with state-of-the-art IK approaches, which allows for deployment directly to robotic hardware. Additionally, it is shown that the incorporation of the genetic algorithm improves the precision while simultaneously reducing the overall runtime. © 2023, The Author(s).
Lizenz:
  • info:eu-repo/semantics/openAccess
Quellsystem:
Forschungsinformationssystem der UHH
Interne Metadaten
Quelldatensatz
oai:www.edit.fis.uni-hamburg.de:publications/0ef9dde1-bfca-422a-9b1d-7fa361458468