[robotics-worldwide] Call for Participation: Virtual Manufacturing Automation Competition

Raj Madhavan raj.madhavan at nist.gov
Tue Feb 17 12:33:17 PST 2009

NIST/IEEE Virtual Manufacturing Automation Competition (VMAC)

Teams are solicited for participation in the 
upcoming NIST/IEEE Virtual Manufacturing 
Automation Competition (VMAC). This includes both 
a national competition that will be held in late 
March'09 (NIST in Gaithersburg, MD, USA) and an 
international competition that will be held in 
May'09 at ICRA'09 (Kobe, Japan). Relevant details 
on the competition and how to participate follow. 
Additional information is available from the VMAC 
website at 
<http://vmac.hood.edu/>http://vmac.hood.edu/ and 
from the ICRA 2009 competitions website at 
If interested, send an email to robosim at nist.gov.


Automated Guided Vehicles (AGVs) and forklifts 
represent integral components of today’s 
manufacturing processes. They are widely used on 
factory floors for intra-factory transport of 
goods between conveyors and assembly sections, 
parts and frame movements, and truck-trailer 
loading/unloading. Automating these systems to 
operate in unstructured environments presents an 
exciting area of current research in robotics and 
automation. Unfortunately, the traditional entry 
barrier into this research area is quite high. 
Researchers need an extensive physical 
environment, robotic hardware, and knowledge in 
research areas ranging from mobility and mapping 
to behavior generation and scheduling. An 
accepted approach to lowering this entry barrier 
is through the use of simulation systems and open 
source software. It is our belief that 
competitions are an effective means of 
stimulating interest and participation among 
students by providing exciting technological problems to tackle.


The long-term goal of this competition is to 
present a full factory buffer-zone problem. This 
problem will involve a heterogeneous team of 
forklifts, unit loaders, and Automated Guided 
Vehicles (AGVs) that will cooperatively clear 
pallets from a temporary storage location and 
deliver needed supplies throughout the factory.

The scenario begins with a truck unloading 
pallets into the buffer zone. A team of 
autonomous forklifts must move the pallets from 
the buffer zone to sorted storage shelves located 
a short distance away. Once loaded on the 
shelves, the pallet’s contents become available 
for distribution to users in the factory. The 
scenario continues with a parts request coming 
from a factory user. A robotic arm must take a 
package from the shelves and load it onto a 
conveyor where an AGV will be able to load the 
package for delivery. The AGV must then navigate 
through a dynamic factory environment to deliver 
the goods. Anticipated challenges include, 
traffic management, fine driving skills (for 
docking with pallets and conveyor stations), route planning, 

This year’s competition will present a more 
modest scenario. A team of unit loaders will be 
tasked with transporting packages from a loading 
station to several different unloading stations. 
The unit loaders will be required to dock with 
the loading/unloading stations and interact with 
a conveyor system to load packages. The vehicle 
will then need to determine the package’s 
destination (through an RFID tag), and transport 
the package to the correct unloading station. 
Challenges will include fine autonomous vehicle 
control, path planning, and traffic management. 
Multiple paths will exist from the loading 
station to the unloading station. There will be a 
trade-off between path length and path traversal difficulty.

A sample simulated world for this scenario exists 
on the sourceforge USARSim website. It may be 
accessed through this link 
The map package is called DM-VMAC1-3.31 and both 
.exe and .zip versions are available. A complete 
interface to the conveyor system of the factory 
is not yet complete. Until then, directions for 
command-line based interactions are included with the map distribution.

Requirements include the following:

• This is a virtual competition; the competition 
will involve multiple simulated robots
• The simulation engine that is used is Epic 
Game’s UnReal 2004 w/ Karma physics
• The socket level interface to the game engine is USARSim Control
• Teams will be fully autonomous
• Teams will accept high-level commands (e.g. 
init, mission start) over a Neutral Messaging 
Language (NML) connection (See 
www.sourceforge.net/projects/moast for communications definitions)
• Teams have the option of controlling robots via 
USARSim ASCII socket or using simWare middleware (an NML based middleware)
• Teams have the option of using as much of the 
MOAST control system (last year’s winning code base) as they desire

• Remote participation will be allowed
– Details are still being worked out
– We are looking for volunteers to help in this effort

• All code used in the competition becomes open source after the competition
– You cannot participate until you deliver your source code

• Teams are expected to publish their contributions at a scientific conference
– Last year, special session held at the 
Performance Metrics for Intelligent Systems 
(PerMIS) Workshop: http://www.isd.mel.nist.gov/PerMIS_2008/

If you are interested in participating, submit a 
succinct statement to 
<mailto:robosim at nist.gov>robosim at nist.gov 
describing 1) how you expect to benefit from your 
participation, and 2) why you should be selected 
(emphasize skills and experience with respect to 
the requirements of the competition). Please be 
sure to also include the following information:
    * Team Name
    * Affiliation
    * Team Leader
    * Email
    * Phone
    * Team size (number of individuals)

Using a metrics-driven competition model, 
advancements in the various technologies 
comprising the AGV control system are quantified, 
helping the community gauge as well as target 
progress. It is our belief that these 
competitions will serve as a model for 
establishing a university-community focused on a real-world practical problem.

More information on USASim and MOAST are 
available from 

Raj Madhavan, Ph.D.
Intelligent Systems Division
National Institute of Standards and Technology
100 Bureau Drive, Mail Stop 8230
Gaithersburg, MD 20899-8230.

Tel: (301) 975-2865 Fax: (301) 990-9688
URL: http://aser.ornl.gov/madhavan/

More information about the robotics-worldwide mailing list