Contact Point Localization for Articulated Manipulators with Proprioceptive Sensors and Machine Learning

Adrian Zwiener1, Christian Geckeler1, Andreas Zell2

  • 1University of Tuebingen
  • 2University of Tübingen

Details

Category

Interactive Session

Sessions

10:30 - 13:00 | Tue 22 May | podF | TuA@F

Control 1

Full Text

Abstract

A model-based Machine Learning (ML) approach is presented to detect and localize external contacts on a 6 degree of freedom (DoF) serial manipulator. This approach only requires the use of proprioceptive sensors (joint positions, velocities and one-dimensional (1D) joint torques already available in the robot arm). Good results are obtained with Random Forests (RFs) and Multi-Layer-Perceptrons (MLPs) leading to a precise localization of the contact link and its orientation. Apart from the link in contact and the orientation of the force, RFs and MLPs are also able to differentiate between contact points on the same link and orientation but with different distances to the joint axis. We experimentally verify this approach on simulated and real data obtained from the Kinova Jaco 2 manipulator and compare it against an optimization based approach.

Additional Information

No information added

Video

No videos found

Summary

Detected contact and true contact

  • Contact point localization as a classification problem solved with Random Forests and Multi-Layer-Perceptrons
  • Normal contact forces are applied onto the manipulator in an offline training phase
  • The sensor data is processed by an external torque observer and used as input features
  • The method is tested in simulations and experiments with the Kinova Jaco 2