The events organized at the 2011 Virtual Manufacturing and Automation Challenge (VMAC) are designed to focus attention on the problems of mixed-palletizing and intra-factory package delivery/logistics.
MIXED PALLETIZING CHALLENGE
This challenge contains two independent events. In the first event, teams will be provided with order files that correspond to an XML schema (link provided below). The teams will need to create XML formatted packing plans that will then be evaluated by metrics included with the Pallet Viewer application (link provided below) as shown in the figure below. In the second event, teams will be presented with completed packing plans that they must construct using the USARSim simulation framework. Sample code and detailed directions may be found at the link provided below. Since this is a simulated challenge, ground truth will be available for such items as package locations and package types. It is desired that teams utilize as little of this information as possible, however, the organizers realize that most teams will require some help from ground truth. Teams must disclose their ground truth needs in their Team Description Paper (described below).
Figure 1: Sample output of pallet evaluation software.
The mobility challenge will utilize the USARSim simulation framework to represent a large warehouse. In this challenge, teams will use robotic forklift platforms to deliver completed pallets throughout the warehouse. Since this is a simulated event, perfect ground truth is available on items such as vehicle locations and pallet destinations. It is desired that teams utilize as little of this information as possible, however, the organizers realize that most teams will require some help from ground truth. Teams must disclose their ground truth needs in their Team Description Paper (described below).
Figure 2: Sample of mobility challenge run from ICRA 2010
Potential participants should submit a team description paper (TDP) of their intended entry to roboSim@nist.gov. The TDP should contain which challenge events your team will participate in, a high-level description of the algorithms that you will employ, requirements that you will place on the simulation system (i.e. what robots, sensors, and infrastructure you expect to need), and references to the team’s relevant work in the area.
------------------------------------------------------------------------------- *** Team Description Papers due February 1, 2011 *** -------------------------------------------------------------------------------
Recent advances in the design and fabrication of microelectromechanical systems (MEMS) have enabled the development of mobile microrobots that can autonomously navigate and manipulate in controlled environments. It is expected that this technology will be critical in applications as varied as intelligent sensor networks, in vivo medical diagnosis and treatment, and adaptive microelectronics.
However, many challenges remain, particularly with respect to locomotion, power storage, embedded intelligence, and motion measurement. As a result, NIST has organized performance-based competitions for mobile microrobots that are designed to: 1) motivate researchers to accelerate microrobot development, 2) reveal the most pressing technical challenges, and 3) evaluate the most successful methods for locomotion and manipulation at the microscale (e.g., actuation techniques for crawling).
Microrobots from past competitions: a) hard magnet (Carnegie Mellon), b) polymer-based electrostatic (Simon Fraser), c) resonant electromagnetic (ETH Zurich), and d) electrostatic (US Naval Academy)
This challenge aims, step by step, to remove the main bottleneck to agile robotics: reliable perception. It seeks an answer to the question, “of the myriad of perception scenarios, which problems have known and dependable solutions?”
This year’s Challenge addresses the issue of object recognition and accurate 6DOF position estimation for robot applications. Seeking the development and documentation of solutions to pragmatic robotic sensing problems, the goal is to correctly identify objects and determine their pose on a work surface, since both are required for robotic manipulation. Entries will attempt to accurately locate and identify specified objects in a variety of situations using off-the-shelf consumer sensors and open-source APIs. Participants must also demonstrate the ability to learn new parts on-the-fly given object training and validation sets. Representative object identification data will be available on the Challenge’s home server, and will be of sufficient amount for full training/recognition of the task.
Can you build and program a robot fast enough to save an astronaut’s life? If you were stuck on the moon, what would be the best robotic tools?
This event simulates an unexpected problem occurring at a planetary habitat. A robotic solution must be quickly developed and deployed, using only what you can fit in a suitcase. The intent of this event is to develop versatile robotic systems and software that can be adapted quickly to address unexpected events.
Unlike the previous years of this competition where CKBot hardware are supplied by the conference, this year, we expect teams to bring their own robotic modules, tools, and software. The robotics modules or components will be like "Lego" building blocks that you can quickly build necessary robots to solve the problems given at the site. Please visit the websites for previous competitions to get some ideas for what are expected. There will be a constraint on the space and weight for all your equipments. These constraints serve two purposes: one is to simulate the resource limitation you might have in real situations, the other is to limit the scope of your preparation and transportation for this event and make it more portable.