Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Learning-Based Wiping Behavior of Low-Rigidity Robots Considering Various Surface Materials and Task Definitions

Kento Kawaharazuka, Naoaki Kanazawa, Kei Okada, Masayuki Inaba

TL;DR

A method of motion generation based on the learned prediction of contact force during the wiping motion of a low-rigidity robot is developed and it is shown that MyCobot, which is made of low- Rigidity resin, can appropriately perform wiping behaviors on a plane with multiple surface materials based on various task definitions.

Abstract

Wiping behavior is a task of tracing the surface of an object while feeling the force with the palm of the hand. It is necessary to adjust the force and posture appropriately considering the various contact conditions felt by the hand. Several studies have been conducted on the wiping motion, however, these studies have only dealt with a single surface material, and have only considered the application of the amount of appropriate force, lacking intelligent movements to ensure that the force is applied either evenly to the entire surface or to a certain area. Depending on the surface material, the hand posture and pressing force should be varied appropriately, and this is highly dependent on the definition of the task. Also, most of the movements are executed by high-rigidity robots that are easy to model, and few movements are executed by robots that are low-rigidity but therefore have a small risk of damage due to excessive contact. So, in this study, we develop a method of motion generation based on the learned prediction of contact force during the wiping motion of a low-rigidity robot. We show that MyCobot, which is made of low-rigidity resin, can appropriately perform wiping behaviors on a plane with multiple surface materials based on various task definitions.

Learning-Based Wiping Behavior of Low-Rigidity Robots Considering Various Surface Materials and Task Definitions

TL;DR

A method of motion generation based on the learned prediction of contact force during the wiping motion of a low-rigidity robot is developed and it is shown that MyCobot, which is made of low- Rigidity resin, can appropriately perform wiping behaviors on a plane with multiple surface materials based on various task definitions.

Abstract

Wiping behavior is a task of tracing the surface of an object while feeling the force with the palm of the hand. It is necessary to adjust the force and posture appropriately considering the various contact conditions felt by the hand. Several studies have been conducted on the wiping motion, however, these studies have only dealt with a single surface material, and have only considered the application of the amount of appropriate force, lacking intelligent movements to ensure that the force is applied either evenly to the entire surface or to a certain area. Depending on the surface material, the hand posture and pressing force should be varied appropriately, and this is highly dependent on the definition of the task. Also, most of the movements are executed by high-rigidity robots that are easy to model, and few movements are executed by robots that are low-rigidity but therefore have a small risk of damage due to excessive contact. So, in this study, we develop a method of motion generation based on the learned prediction of contact force during the wiping motion of a low-rigidity robot. We show that MyCobot, which is made of low-rigidity resin, can appropriately perform wiping behaviors on a plane with multiple surface materials based on various task definitions.
Paper Structure (13 sections, 6 equations, 6 figures)

This paper contains 13 sections, 6 equations, 6 figures.

Table of Contents

  1. INTRODUCTION
  2. Learning-Based Wiping Behavior of Low-Rigidity Robots Considering Various Surfaces and Task Definitions
  3. Network Structure
  4. Data Collection
  5. Training of TTNPB
  6. Online Recognition of Surface Being Wiped
  7. Contact Control with Various Task Definitions
  8. Experiments
  9. Experimental Setup
  10. Training of TTNPB and Online Learning of Parametric Bias
  11. Wiping Behavior Considering Various Surfaces and Task Definitions
  12. Discussion
  13. CONCLUSION

Figures (6)

  • Figure 1: The concept of this study: we handle wiping behaviors with (1) various surface materials, (2) various task definitions, and (3) low-rigidity robot.
  • Figure 2: The overview of the learning system of this study.
  • Figure 3: The experimental setup: the trajectory of wiping and various surface materials handled in this study.
  • Figure 4: The arrangement of the trained parametric bias.
  • Figure 5: The trajectory of parametric bias while updating it online.
  • ...and 1 more figures