Team NimbRo at MBZIRC 2017: Autonomous Valve Stem Turning using a Wrench

TL;DR

This paper presents the design and deployment of an autonomous mobile robot, Mario, capable of detecting, grasping, and turning a valve stem using deep learning and motion primitives, winning the MBZIRC 2017 Challenge 2.

Contribution

It introduces a novel integrated system combining 3D laser detection, neural network-based tool recognition, and adaptive motion primitives for autonomous valve manipulation.

Findings

Mario successfully completed the valve turning task at MBZIRC 2017

The system achieved high detection accuracy for tools and panels

Adaptive motion primitives improved manipulation success rate

Abstract

The Mohamed Bin Zayed International Robotics Challenge (MBZIRC) 2017 has defined ambitious new benchmarks to advance the state-of-the-art in autonomous operation of ground-based and flying robots. In this article, we describe our winning entry to MBZIRC Challenge 2: the mobile manipulation robot Mario. It is capable of autonomously solving a valve manipulation task using a wrench tool detected, grasped, and finally employed to turn a valve stem. Mario's omnidirectional base allows both fast locomotion and precise close approach to the manipulation panel. We describe an efficient detector for medium-sized objects in 3D laser scans and apply it to detect the manipulation panel. An object detection architecture based on deep neural networks is used to find and select the correct tool from grayscale images. Parametrized motion primitives are adapted online to percepts of the tool and valve stem in order to turn the stem. We report in detail on our winning performance at the challenge and discuss lessons learned.