Conditional Visual Servoing for Multi-Step Tasks

TL;DR

This paper introduces a modular conditional visual servoing approach that enables robots to perform multi-step tasks by selecting demonstrations based on current observations, improving flexibility and applicability in complex scenarios.

Contribution

The paper presents a novel conditional servoing method that extends visual servoing to multi-step tasks by dynamically selecting demonstrations conditioned on robot observations.

Findings

Reprojection error-based selection performs best in simulation.

Conditional servoing successfully applied to real robot tasks.

Flexible combination of demonstrations enhances multi-step task execution.

Abstract

Visual Servoing has been effectively used to move a robot into specific target locations or to track a recorded demonstration. It does not require manual programming, but it is typically limited to settings where one demonstration maps to one environment state. We propose a modular approach to extend visual servoing to scenarios with multiple demonstration sequences. We call this conditional servoing, as we choose the next demonstration conditioned on the observation of the robot. This method presents an appealing strategy to tackle multi-step problems, as individual demonstrations can be combined flexibly into a control policy. We propose different selection functions and compare them on a shape-sorting task in simulation. With the reprojection error yielding the best overall results, we implement this selection function on a real robot and show the efficacy of the proposed conditional servoing. For videos of our experiments, please check out our project page: https://lmb.informatik.uni-freiburg.de/projects/conditional_servoing/