Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Diffusion-based Virtual Fixtures

Cem Bilaloglu, Tobias Löw, Sylvain Calinon

TL;DR

This extended abstract introduces a novel virtual fixture formulation for tactile robotics tasks that constrains the behavior based on the position on the surface and generalizes it over the surface by considering the distance (metric) on the surface.

Abstract

Virtual fixtures assist human operators in teleoperation settings by constraining their actions. This extended abstract introduces a novel virtual fixture formulation \emph{on surfaces} for tactile robotics tasks. Unlike existing methods, our approach constrains the behavior based on the position on the surface and generalizes it over the surface by considering the distance (metric) on the surface. Our method works directly on possibly noisy and partial point clouds collected via a camera. Given a set of regions on the surface together with their desired behaviors, our method diffuses the behaviors across the entire surface by taking into account the surface geometry. We demonstrate our method's ability in two simulated experiments (i) to regulate contact force magnitude or tangential speed based on surface position and (ii) to guide the robot to targets while avoiding restricted regions defined on the surface. All source codes, experimental data, and videos are available as open access at https://sites.google.com/view/diffusion-virtual-fixtures

Diffusion-based Virtual Fixtures

TL;DR

This extended abstract introduces a novel virtual fixture formulation for tactile robotics tasks that constrains the behavior based on the position on the surface and generalizes it over the surface by considering the distance (metric) on the surface.

Abstract

Virtual fixtures assist human operators in teleoperation settings by constraining their actions. This extended abstract introduces a novel virtual fixture formulation \emph{on surfaces} for tactile robotics tasks. Unlike existing methods, our approach constrains the behavior based on the position on the surface and generalizes it over the surface by considering the distance (metric) on the surface. Our method works directly on possibly noisy and partial point clouds collected via a camera. Given a set of regions on the surface together with their desired behaviors, our method diffuses the behaviors across the entire surface by taking into account the surface geometry. We demonstrate our method's ability in two simulated experiments (i) to regulate contact force magnitude or tangential speed based on surface position and (ii) to guide the robot to targets while avoiding restricted regions defined on the surface. All source codes, experimental data, and videos are available as open access at https://sites.google.com/view/diffusion-virtual-fixtures

Paper Structure

This paper contains 4 sections, 4 equations, 1 figure.

Table of Contents

  1. INTRODUCTION
  2. METHOD
  3. EXPERIMENTS
  4. CONCLUSION & FUTURE WORK

Figures (1)

  • Figure 1: Input and example use-cases of our method. Left, the input to our method -- a partial point cloud with segmented regions $\Omega_1$, $\Omega_2$ and the free region $\Omega_0$ with their estimated boundaries $\partial\Omega_1$, $\partial\Omega_2$ and $\partial\Omega_0$. Center, the first experiment showing the virtual fixture constraining the contact force magnitude based on diffusing the contact forces designated on $\Omega_1$ and $\Omega_2$. Right, the second experiment showing the flow field guiding the agents towards target $\Omega_2$ by avoiding restricted regions $\Omega_1$ where the black paths show trajectories with different initial positions.