A Comprehensive Software Framework for Complex Locomotion and Manipulation Tasks Applicable to Different Types of Humanoid Robots

Stefan Kohlbrecher,Alberto Romay,Philipp Schillinger,Alexander Stumpf,Oskar Von Stryk,David C Conner

doi:10.3389/frobt.2016.00031

Stefan Kohlbrecher, Alberto Romay + Show 4 more

Open Access

https://doi.org/10.3389/frobt.2016.00031

Copy DOI

Abstract

While recent advances in approaches for control of humanoid robot systems show highly promising results, consideration of fully integrated humanoid systems for solving complex tasks such as disaster response has only gained focus recently. In this work, a software framework for humanoid disaster response robots is introduced. It provides newcomers as well as experienced researchers in humanoid robotics a comprehensive system comprising open source packages for locomotion, manipulation, perception, world modeling, behavior control, and operator interaction. The system uses the Robot Operating System (ROS) as a middleware, which has emerged as a de-facto standard in robotics research in recent years. The described architecture and components allow for flexible interaction between operator(s) and robot from teleoperation to remotely supervised autonomous operation while considering bandwidth constraints. The components are self-contained and can be used either in combination with others or standalone. They have been developed and evaluated during participation in the DARPA Robotics Challenge and their use for different tasks and parts of this competition are described.

Highlights

The 2015 DARPA Robotics Challenge (DRC) Finals showed that robotic systems provide promising capabilities for providing assistance in disaster scenarios that necessitate complex locomotion and manipulation abilities
We provide a detailed discussion of different components for perception, locomotion, and manipulation contributing to achieve the overall task of flexible disaster response
As the only team at the DRC Trials, we demonstrated that our approach is able to generate suitable footstep plans over entire obstacles that had been executed without interruptions

Summary

Introduction

The 2015 DARPA Robotics Challenge (DRC) Finals showed that robotic systems provide promising capabilities for providing assistance in disaster scenarios that necessitate complex locomotion and manipulation abilities (see Figure 1). The competition showed that there are still numerous research challenges that have to be solved before robot systems are capable and robust enough for use in real disasters. Toward this goal, we present our ROS-based framework for solving complex locomotion and manipulation tasks. We present our ROS-based framework for solving complex locomotion and manipulation tasks To our knowledge, it is the first fully open-sourced framework featuring documentation that allows other researchers to replicate the provided functionality and results in simulation or, after necessary interfacing, on their own robot systems. Our framework is based on ROS (Quigley et al, 2009), which has evolved to be the de facto standard robotics middleware within the robotics research community and parts of the robotics industry.

Objectives

Methods

Results

Discussion

Conclusion