Summary of Team IHMC's virtual robotics challenge entry

This paper presents a high level overview of the work done by Team IHMC (Florida Institute for Human and Machine Cognition) to win the DARPA Virtual Robotics Challenge (VRC), held June 18–20 2013. The VRC consisted of a series of three tasks (driving a vehicle, walking over varied terrain, and manipulating a fire hose), to be completed in simulation using a model of the humanoid robot Atlas. Team IHMC was able to complete all of these challenges multiple times during the competition. The paper presents our approach, as well as a bird's-eye view of the major software components and their integration.

I. Introduction

The DARPA Robotics Challenge (DRC [1]) is a currently ongoing competition focused on developing disaster response robots that can operate in rough terrain and hazardous conditions. There are several possible routes to compete in the DRC, one of which is to first partake in the Virtual Robotics Challenge (VRC). During the VRC, which was held June 18–20 2013, teams attempted to complete three of the DRC tasks in a computer simulation using a simulated version of the robot ‘Atlas’, made by Boston Dynamics [2]. The three VRC tasks were to have the robot: 1)

climb into a Polaris Ranger vehicle, drive along a road with obstacles, exit the vehicle and walk across finish;

2)

walk across various rough terrain: a mud pit, rolling hills, and a debris field;

3)

attach a hose to a spigot and subsequently turn a valve to start fluid flow.