Robot Challenge

The second edition of the ICRA Robot Challenge will be held at ICRA 2009, in Kobe, Japan, May 12-17, 2009. The Challenge will consist of three specific events, just like last year. Our goal is to make the Challenge accessible to all members of the ICRA community, to integrate it tightly with the technical aspects of the conference, and to encourage as many participants as possible to bring their robots and participate. Please visit the following official site of Robot Challenge.

The ICRA Robot Challange is a new robotics event, introduced last year at ICRA 2008 in Pasadena, California. The overall theme of the Challenge last year was “space robotics”, and it consisted of three events, showcasing current　research in the field of robotics. Over fifty participants, from seven countries participated in 2008, and the event was a　great success. Building on our accomplishments from last　year, the second annual ICRA Robot Challenge will be held at ICRA 2009 in Kobe, Japan, in May of 2009. The Challenge will comprise three events, planetary exploration, human-robot interaction, and manufacturing automation, and　will be running throughout the conference venue.

The Events

The 2009 ICRA Robot Challenge will feature three events. Two of the events, the HRI Challenge and the Planetary　Exploration Challenge will be largely the same as in the 2008 Challenge. This supports the goal of demonstrating progress in the events from year to year. There will also be a new event this year, the Virtual Manufacturing Automation Challenge.

A. Planetary Exploration

Planetary exploration through intelligent mobile robots is a fascinating endeavor. The tremendous success of the Mars Exploration Rovers Spirit and Opportunity already shows the potential of this field where nevertheless many open problems remain. First of all, there are a large variety of different planetary environments and possible missions that are of scientific interest. Accordingly, various locomotion and manipulation challenges exist for planetary exploration robots. Second, communication delays or even dropouts make standard teleoperation very challenging. Intelligent autonomous functions are hence of tremendous interest to facilitate robot control.
The event consists of different mission components that reflect these open problems. A description of the challenges planned for this event can be found below. Teams interested in participation are welcome to make suggestions for the mission components. The event is intended as a demonstration of state of the art research relevant to planetary exploration, especially in form of robot designs and intelligent autonomous functions.

1) The Environment: The environment for this event is an outdoor area approximately 10m by 10m, covered in gravel to a depth of 10cm. Rocks of varying sizes and compositions will be placed on the surface. A simulated lander will be at one end, with one or more ramps extending down to the surface. Robots will ideally start and end all missions on the lander platform. The ramps will be clearly marked with brightly-colored tape, and at least one of them will be free of obstacles. The surface will be smoothed between runs, removing all traces of previous robots.
2) The Event Elements: This event simulates the exploration of a small area of a planetary surface. There are a number of sub-challenges in the event, and teams should feel free to attempt as many or as few of these as they want.

This event is intended to showcase autonomous systems that operate with a minimum of human intervention. We are more interested in demonstrating the state-of-the-art in robots that can explore natural terrain than in having a traditional competition.

1) Onto the surface. The robot must leave the lander platform, and make it onto the planetary surface. The robot must identify the ramps off of the platform, orient itself appropriately, and navigate down one of the ramps to the surface. The ramps might be obstructed by deflated “air bags”, or might not have deployed properly. The system should recognize and deal with these situations appropriately. The operation will be considered successful if the robot manages to get two meters (measured at the closest point) away from the
lander. The lander platform will be constructed to autonomously open (perhaps with some human intervention), and to include potential obstacles on the ramps. The event might also be set up to include obstacles at the bottom of the ramps that are either impassible, or must be navigated around.
2) Data collection. The robot must autonomously navigate to a remote science station, at the other side of the planetary surface to collect a set of recorded science data, and then return to the lander. The science station and robot are only equipped with short range (simulated) communications, so the robot must be physically close to the science station or lander in order to transfer data. The robot will be given the location of the science station, in some coordinate frame, but will not be given a map of the environment. The goal is to retrieve the data and bring it back to the lander as quickly as possible.
3) Map the Environment. The robot should build an accurate metric map of the environment in a fixed time period. The time period starts when the robot leaves the lander ramp, and the map must be built by the end of the time period. Building a map in the sandbox will be particularly difficult, since there will be a lot of wheel slip, and the surface is not planar. We will purposefully put rises and dips into the surface to make mapping challenging.
4) Extreme navigation. Part of the planetary surface will contain a number of extremely challenging physical obstacles, and a near-vertical cliff-face. Robots must traverse these obstacles to reach the bottom of the cliff, climb the cliff to the top (if possible), and then return to the lander.
5) Find the robot. A previous mission has gone wrong, and one of our robots is missing. The goal is to find this robot, possibly following it’s tracks in the surface material, and to bring it back to the lander. For robots that are incapable of picking up another robot, finding the other robot and touching it will be enough. To add difficulty to this problem, the lost robot can be made small, so that the finding robot cannot just follow the tracks (through narrow spaces), but must plan paths around obstacles, and find the trail again.
6) Bring back shiny things. The robot must go out and find interesting objects, and bring them back to the lander. These objects could be unusual rocks, differently colored sand or gravel, alien plants, or manmade artifacts. We could even have the robot look for liquid water or buried treasure. Back on the lander. At the end of the mission, the robot must return to the lander platform.

B. Human-Robot Interaction

This event is intended to showcase the latest research results in human-robot interaction. There is no particular theme for this event, but robots must either learn from their interactions with humans, or interact in some social context. We leave what the robots actually learn, and what the social context is, up to you.
1) Scope: In order to leave the floor open to any team working in HRI, there are no specific requirements neither on the shape and sensori-motor capabilities of the robot, nor on the experimental context. We will accept any robot: wheel-based platforms, as much as humanoids ones are welcome. We also accept Wizard-of-Oz type of experiments or video-based HRI experiments. And we leave it up to the teams to define the experimental context, i.e. the type of the interaction. Thus the sole requirements we set for taking part in the HRI Challenge concern the robot’s behavior. The robot should be at least endowed with either of the following two capabilities:
1) The ability to learn by interacting with a human (we say nothing about what the robot can learn; being more restrictive in the learning capabilities would constrain too much the hardware of the robot).

2) The ability to interact socially. This includes any of the following capabilities: detecting humans, detecting human activities, respond to humans; infer human intention, communicate verbally or in other manner, detect and respond to human emotion, . . . ...

3) Evaluation: The effectiveness of a robot engaging in HRI must be evaluated by human users who got the chance to interact with the robot for a sufficiently long period of time. This challenge thus requires that the robots be highly interactive and run constantly throughout ICRA.
The robots’ behavior will be evaluated formally by a team composed of 10 official evaluators (10 experts in robotics, but not necessarily in HRI) and lay people (all the people attending the conference will be given a questionnaire to fill in). The questionnaires will be prepared by experts in HRI evaluation methodologies. The exact scoring system is yet to be defined, but it will at least encompass a score according to the two requirements on the robot’s behavior listed above.

C. Manufacturing Automation

Automated Guided Vehicles (AGVs) and forklifts represent integral components of today’s manufacturing processes. They are widely used on factory floors for intrafactory 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.

1) Vision for the Future: 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 fork lifts must move the pallets from the buffer zone to sorted storage shelves located a short distance away. Once loaded on the shelves, the pallets 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, . . .

2) This Year’s Challenge: 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.

The 2009 ICRA Robot Challenge

The 2009 ICRA Robot Challenge will be held in conjunction with ICRA 2009 in Kobe, Japan, May 12–17, 2009. The events will be held during the three days of technical sessions, May 14–16, and will occur in various locations at the conference venue.

The 2010 ICRA Robot Challenge

We are planning to run another Robot Challenge, in conjunction with ICRA 2010, in Anchorage, Alaska, next year. Full details of the event will be available at the Challenge web site, https://icra.wustl.edu. More information about ICRA 2010 is available at the conference web site,
https://icra2010.grasp.upenn.edu.

Inquiry about Robot Challenge

If you have questions regarding the robot challenge, please contact the Exhibitions Chair (Robot Challenge).

Exhibitions Chair (Robot Challenge General Chair)

Bill Smart (Washington University in St.Louis)