Originally Published: Monday, 15 October 2001 Author: S.A. Hayes, Linux.com
Published to: develop_articles/Development Articles Page: 1/1 - [Std View]

Linux.com Interview: Mark Micire of the Center for Robotic Assisted Search and Rescue at the University of South Florida.

Mark Micire helps build and deploy the robots used to speed the search for survivors in the rubble of the World Trade Center. The CRASAR Lab that create these remarkable robots use Linux for most of their computing needs. Linux, and the geeks, researchers and professors who use it are speeding the development of critical technologies like USAR Robotics, technologies that help save lives. Linux.com got in touch with this lab in South Florida to get a closer look at who they are, what they do, and what they do it with.


Credit for all photo media in this article goes to the Center for Robot-Assisted Search and Rescue. Contact Mark Micire at http://www.csee.usf.edu/robotics/crasar/ if you have further needs.

Mark Micire is a graduate student at the University of South Florida CRASAR lab -- The Center for Robotic Assisted Search and Rescue. He's one of a team of four people led by Dr Robin Murphy who responded with 24 hours to the dramatic search and rescue presented to the nation on September 11th. The team has research interests in unstructured environments and victim detection. In addition, each member of the team is themselves formally trained in Urban Search and Rescue. Imagine for a second when this team of rescue academics from florida show up with a mass of robots, most packable by a human being, but as it turns out it is the smallest marsupial machines that really perform. Small, sturdy robots (about the size of a big loaf of bread) are the critters that can go down drains and squeeze through cracks, where no human can go, no matter how determined. It's possible these designs still proved the most adept at finding victims in the rubble.

The robotocist teams are still at work on the rubble even today, though the mission has long been changed to analysis and inspection duties. Neverthless, for the days following September 11th, this first use of robots to help target victims is considered a dramatic success, as you may have already seen in the media.

Incidentally, most of the robots that have a brain at all run Linux for their primitive nervous systems, so we were also interested in why so many critters might share the same operating system. (As a side note we should mention here that the marsupial robots have, as yet, no processor.)

Anyway, turns out it's much more than just price that puts Linux into all these exciting robots. Mike Micire told us "Linux and robotics are very closely tied... You only have to go to a single robotics competition and see how many people are using Linux to understand."

OK, so don't tell us twice, we know a Linux success story when we see one!

Today Linux.com caught up with Mike Micire, now that he is 'back in the office' and asked him about the experience and about the robots he works with every day.

Click through to read the interview and see the pictures of the team in action (with robots descending drains) and thanks for visiting Linux.com.

USAR

Linux.com: Can you tell us, for those who don't know, what USAR is and how your lab is involved?

Mark Micire: USAR stands for Urban Search and Rescue. In 1995, our professor, Dr. Robin Murphy, had a graduate student that was certified for search and rescue and went to aid in the rescue after the Oklahoma bombing. The student was then Lt. Col John Blitch with the Army (now retired). He was amazed by the lack of technology and the numerous places that robotic technology could have been utilized. This then became one of the focuses of the laboratory (then at the Colorado School of Mines). When Dr. Murphy came to University of South Florida, she continued her work here while John Blitch went on to become a DARPA funding manager. Through DARPA funding and our close ties to the local county fire rescue personnel, myself and another grad student have been working to become certified in Search and Rescue. This certification allows us to work in the field with the professionals that have been doing search and rescue for years.

Today we belong to a group called the Center for Robotic Assisted Search and Rescue (CRASAR). If you'd like more details, visit http://www.crasar.org.

Linux.com: Can you tell us about your position in the group?

Mark Micire: I am one of two "hardware support" guys. We are all students at the university, so our time is split (theoretically) between classes and supporting the other programmers in the lab. Just keeping the robots running and modifying them for projects is a full time job. We have five other full time programmers.

Linux.com: Your group is using Linux to help save lives - not just the lives of those who may be trapped in disaster situations, but also the lives of the people who are searching for them. How does that make you feel?

Mark Micire: It is good to finally see that all of this research and training has not been in vain. We have many projects that our lab does outside of USAR to help bring in funding, but USAR has always been the main focus of some of the people in our lab. To bring together technologies like robotics, networking, Linux, and field research is very fulfilling.

Credit for all photo media in this article goes to the Center for Robot-Assisted Search and Rescue.

The Bombing

Linux.com: How many robots were involved with searching the disaster site of the recent terrorist bombings?

Mark Micire: I'm assuming you are referring to NY. In that case, our group deployed 8 robots total over 11 days.

Linux.com: Is this the most robots used at one time in one location?

Mark Micire: No, but this is the first use of robots in a real disaster to our knowledge. That is a big step for the robotics community, and we're glad to have been here when it happened.

Linux.com: What has been your most remarkable experience being involved with this massive rescue effort?

Mark Micire: Related to robotics: Hearing that the task force we were involved with ordered four of the robots when they got back. We have been patiently waiting for a team to step up to the plate and give these robots a try. For them to order them immediately is very validating.

Related to the disaster: The size and expansiveness of the disaster is probably the most remarkable thing that will stay with me. I know everyone has read and heard this a thousand times, but you really can't get an idea of the size of the disaster without being there and seeing the 360-degrees worth of devastation. I have yet to see a picture or film in the media that captures the gravity of the situation fully.

Credit for all photo media in this article goes to the Center for Robot-Assisted Search and Rescue.

The Robots

Linux.com: How many kinds of USAR robots are there?

Mark Micire: Many. I wouldn't even try to innumerate the different "kinds" and capabilities. The USF team has three primary ones as described earlier. We were one of four robotics teams in NY, and there were at least five other kinds of robots associated with those teams.

Credit for all photo media in this article goes to the Center for Robot-Assisted Search and Rescue.

Linux.com: Do they all run Linux?

Mark Micire: No. Some don't run anything at all, as in the case if the Inuktuns. Of the ones with processors, I can pretty safely say yes; Linux in some form.

Linux.com: What are the robots capable of, physically and "intellectually"?

Mark Micire: Part 1: Physical

The physical capabilities depend on the robot. We have many. I'll try to summarize the USAR ones:

Inuktun Microtracs: These were our New York work force. Rugged and strong little beasts, but relatively stupid. They have a Motorola HC11 for motor and logistic control. Originally designed for chemical inspection, they are no larger than a shoe box and have a tether to provide power and feedback to the teleoperator. Because of their size and "packability" they were able to crawl into very small spaces. Some of them have the ability to change shape which is very useful in tight spaces. Sensing includes visible-light cameras, two-way audio, and twin halogens.

iRobot Urbans: Although not used in NY, these are used a lot in our training. These have Pentium II class processor boards and are able to perform more complex tasks like image processing and control assistance. They have the ability to climb stairs and are fairly rugged. They can be equipped with a wide range of sensing capabilities including sonar range finding, laser range finding, visible-light cameras, infrared-thermal imaging cameras, and halogen lighting.

iRobot ATRV2: Again, went to NY, but not used. This is the "mother ship" for our three Urbans. It has off road knobby wheels and is very powerful. With four deep-cycle marine batteries and a geared motor for each wheel, it can run for hours. It has the capability to carry three of the Urbans into a hazardous site and deploy them with a large docking arm. Again, Pentium II class processors allow this machine to perform higher level tasks. Because of its large size, just about any sensor can be mounted on this platform. All of the above mentioned sensors have been on this system at one time or another.

Part 2: Intellectual As for "intellectual" abilities, we have worked on many projects. Our main focus in USAR has been in victim detection and sensor fusion. Through our training we found that one of the hardest tasks is interpreting all of the data coming from the sensors. The AI in our system is used for fusing the various sensors in such a way that the user is alerted to victims that might otherwise have been missed if viewed by a single sensor. Another goal of this fusion is the intelligent selection of sensors given different environmental characteristics or sensor failure.

I will let a simple example illustrate. Let's take one of our Urban platforms and put a color camera and a thermal imaging camera on it. Now, rather than make the operator view two video streams, we fuse the two together. The image processing on the thermal camera attempts to look for something in the image around 98 degrees. The color camera is looking for something flesh colored.

Individually, finding something in this classification might not be a human. Seeing both of these characteristics in the same region is significant though. Now repeat this over three or four sensors and you quickly create a very efficient victim detection system that can alert the operator and let them know that there is possibly something here they should look at.

Linux.com: Wow! So, what's the complete sensor set?

Mark Micire: Things we have now: Color Cameras - good old fashioned color CCD cameras. Omnidirectional Cameras - cameras that can see in 360-degrees. Infrared Imaging Cameras - cameras that can see heat. Infrared Thermal Meters - probes that can give relatively accurate "point" temperatures. Laser Range finders - uses an infrared laser to give a 180-degree range plane that shows the robot's proximity to things in the environment. Sonar Range finders - uses ultrasonic pulses to give a point distance to objects in the environment. Two-way audio - speakers and microphones to communicate and listen for victims. GPS - Global positioning system. Tilt sensor - Gives pitch and roll characteristics. Thermometer - temperature inside the robot. Compass - magnetic compass.

Possibilities in the near future: Air quality meters - to detect flammables, oxygen levels, etc. Bio-stat sensors - to give victim health status. Penetrating microwave radar - to look through walls and floors for movement and even heartbeats.

Linux.com: For those who haven't seen them yet, how do the robots move, for the most part? Did you try any alternate movement designs that might be interesting to mention?

Mark Micire: All of our USAR robots are tracked vehicles with the exception of the ATRV2. All use tracked steering. Because we do not actually manufacture the robots here at US, we have tried to find what similar industries we might be able to exploit. As I said before, the Inuktuns were designed for chemical inspection such as power plant pipes and tanks. By taking that system and adapting it for our own needs, we have been able to take commercial robots and turn them into specialized USAR robots.

Linux.com: What are the robots best at in USAR at the moment?

Mark Micire: In NY, our niche was very small voids in the pile. Two things contributed to this. First, some of these holes were so deep that you could not see to the bottom but were too small for even a search dog to get into. Our little Inuktuns filled this need very quickly. Second, the heat in the bottom of some of these holes was very intense. Even if you could get a dog or person in the hole, you would not want to expose anyone to that kind of heat. In one case, one of the tracks was heated enough that it fell off the robot while in the hole.

Long term, sensing will be the big winner for robots. By adding AI into the sensing capabilities of the robots, we can make the victim sensing much more easy to use and accurate at the same time.

Linux.com: Do the robots move rubble and debris intelligently yet?

Mark Micire: Right now, our robots are primarily tele-operated in rubble. We have done some "guarded motion" work that uses the range sensing capabilities of the robot to help the operator keep from running into walls and debris.

Linux.com: What might these kinds of robots be able to do 5 or 10 years from now?

Mark Micire: All of the above with regards to sensing, and hopefully more. There is a lot needing to be done mechanically before the robots can navigate the rubble piles autonomously. Once that hurdle is cleared, the potential is mind boggling. In 10 years I hope to be reading about the first human rescued by a robot.

Intelligence

Linux.com: What kind of intelligence would you attribute to the robots at this time?

Mark Micire: When specifically talking about our USAR goals, they are intelligent in that they assist the rescuer. This is a situation where the robot has to be sufficiently complex enough that it appears simple to the user. That is a tough task given the complexity of the sensing and the unstructured nature of the environment.

Credit for all photo media in this article goes to the Center for Robot-Assisted Search and Rescue.

Linux.com: Your web page talks briefly about robot teams and competitions. Like many people I've seen the soccer playing robots on documentaries. These little teams of small robots cooperate with each other and adapt as a group. How is the CESAR team involved in that kind of activity?

Mark Micire: Yes. We competed in the very first rescue competition two years ago at the AAAI conference in Austin Texas. Since then we have found it more beneficial to help organize the competitions. We assisted greatly in the Robocup/AAAI rescue competition this summer in Seattle and will be actively helping to organize future competitions.

Linux.com: Any major things your team learned, or are learning from this experience, about the use of the robots?

Mark Micire: We learned many many things. Enough that two of us have shifted our thesis over to just concepts learned at the WTC. (That's a lot of learning.)

Some of the ones directly related to the robots include ruggedization, heat tolerance, and deploy ability. We successfully managed to break just about every robot that we used. That isn't necessarily a bad thing though, because it showed us the weak points that we would have otherwise missed. The heat at the site was something we hadn't anticipated. Future robots will need to be extremely tolerant to heat above 200 degrees. When we left 11 days after the disaster, the core was still at over 1100 degrees. The general consensus around here is that we will need to be able to operate the robots in our home ovens at the very least. Finally, the ability to have the entire robot package be transportable and deployable by one person very quickly became very obvious. By the time we left, I was carrying a 80 pound pack with batteries, robot, cable, and control unit and could do a deployment in about 1 to 2 minutes. That number needs to be more around 40 pounds and a deployment of 30 seconds. It basically comes down to a wearable computing nightmare.

Linux.com: Your work is clearly important for everybody in the world. Who is funding your research?

Mark Micire: DARPA, ONR, NSF, and SAIC right now. Since Sept 11th we should be getting funding from more USAR related groups. This will be nice since until now it has been rare that one of those groups funded us specifically for USAR research. Normally we would have "work" research in other areas and would kind of slip the USAR research into our own time.

Linux

Linux.com: Mike, when did you first get into Linux?

Mark Micire: Picked up a silly little book (that I have now lost) that talked about this amazing new operating system. Two weeks later, my Infomagic CDs and Yggdrasil Linux Bible arrived and its been down hill from there. Before I got into robotics, I was diligently on the system/network admin track. 90% of my Linux experience is down that road.

Linux.com: So you're the Linux guru for these robots?

Mark Micire: All of us have to be a "jack of all trades". There are three of us that have been using Linux for over 5 years, so I won't take the "guru" credit for the lab. Each one of us has our own specialties and so we compliment each other very well. Overlap is nice, but it is very beneficial to have people with different backgrounds and experiences with Linux.

Linux.com: Good point. So, what's your favorite distribution and why?

Mark Micire: I'm a Redhat guy. As with any Linux group, our lab personal preferences are split between Redhat, Mandrake, Slackware, and Debian. Most of our robots are set up for Redhat out of the box, so most of our workstations are Redhat. I don't think I ever remember a debate. Since the robots come pre-installed with Redhat we've always defaulted to that.

Linux.com: Are there advantages to the use of Linux (beyond financial) in the supporting software for the more advanced robots?

Mark Micire: Source code availability and tool accessibility are probably the two primary ones. Robotics requires a very flexible programmer, since one might be programming HC11 assembly one day and looking at Java user interface code the next. To do this without being able to rip into source code is frustrating at best. Because the Linux community is typically open source from the start, this helps speed our development immensely. Having the full suite of GNU programming tools is an advantage that doesn't need explanation.

The stability of Linux also cannot be understated. Imagine turning your system on and carrying it around the room while shaking it. This is what the computers in our systems go through every time we use them. The last thing we want to be worrying about is the stability of the underlying OS.

Linux.com: Anything interesting to say about how you got Linux working with those input devices?

Mark Micire: Most of the vision systems work through vision daemons that either utilize the Video for Linux sub-system or talk directly to the card. Almost all of the other sensors are serial or have been adapted to work through serial communication. We are currently pursuing Firewire as another solution.

Linux.com: Can you tell us about any of your principle modifications to the OS or kernel?

Mark Micire: As anticlimactic as it may seem, we have not done a lot of kernel modifications. I think this is more of a testimony to the flexibility and usability of even a relatively "stock" Linux system. The use of the real-time scheduling modules may lie in our future.

Linux.com: Interesting. So what were some of the challenges to using Linux for the USAR robots?

Mark Micire: Driver support for one. Many of the vendors in the vision processing community have limited support for Linux. This is also true for the wireless ethernet community. Although nothing has yet to prove impossible in this area, "challenging" and more properly "frustrating" probably describe this best.

Linux.com: Are there any other advantages of using Linux? Why Linux and not some other Unix?

Mark Micire: The cost is one good reason. When you are spending 10 to 40 thousand on a robot, it's nice to not have to add the OS, development tools, developers supplements, driver SDKs, and other necessary evils to the purchase order. With Linux, it's all there.

Also, most of us were Linux geeks before we came here. I've been using Linux since '94 and really couldn't see us feasibly pulling this off on any other platform as easily. This isn't saying that it couldn't be done under, let's say OpenBSD. It's just that most of the robotics community is already using Linux, we were already using Linux at home and school, and the robots have driver support for some of their eccentric hardware under Linux. In all honesty, there wasn't much of a debate.

Linux.com: Are there other groups working with other operating systems?

Mark Micire: QNX sometimes pokes its head up. The real-time capabilities of QNX are normally the motivator there. Cost is usually the demotivator for most groups.

MS-Windows is very popular with the vision processing community. Driver support for really weird and accelerated hardware is the motivator there. I don't think I need to explain the demotivators.

Linux.com: Why do they make it so hard on themselves?

Mark Micire: Need more than anything. In the case of the vision community, they are caught between a rock and a hard place with regards to the vendors. When you get a product and it only has a Windows SDK you kind of have to deal with it or send the product back. (As we have done several times.) This is especially tough if there is only one vendor and your research relies on this piece of hardware.

Final Thoughts

Linux.com: In purely economic terms how does the full training of a rescuer compare to the production of a robot?

Mark Micire: Unfortunately that isn't a fair comparison because we really aren't replacing the rescuer. The robot is a tool. Prior to Sept 11th, the comparable tool used for finding victims in confined spaces was a search cam. This is basically a 18 foot retractable pole with a camera at the end. In New York, we were able to extend this reach to over 45 feet in some cases and enter voids that were completely impossible otherwise.

In simple terms, robots do not save people right now. People save people. We are just trying to make it easier for the search crews to get into locations that would otherwise be impossible, extend their senses (cameras and microphones), and give them senses that they might not otherwise have (like thermal imaging).

Linux.com: What can be done to bring the price of these robots down so they can be used in far greater numbers?

Mark Micire: A commercial driver. Like anything else that comes out of R&D, the first thousand units are the most expensive. What mobile robotics is lacking right now is a big commercial use for them. Once the robots have come out of the laboratories into the hands of the masses and proven their usefulness, you will see a drastic drop in prices just like any other technology.

New York was a great existence-proof that if the robots can be put in the hands of the rescuers, they will want to purchase and use them. The FEMA task force that we worked with in New York ordered 4 of the robots we were using within 24 hours of arriving home. While being one hell of a compliment, it also proves that the usefulness and commercial feasibility is there. Hopefully with even more exposure we can help drive the prices down through use and purchases by more rescue teams.

Linux.com: OK, so how would a curious and ambitious Linux geek get ahold of a robot to play with?

Mark Micire: Well, I grew up on RC cars and PCs. Although these are much more advanced, the basics of what I do everyday still comes from those "good ol days". Without promoting any single company, there are a lot of outlets for robotics out there. For ones that run Linux, you might want to check with your local college or clubs and see if there are robotics groups around your area. Unfortunately the bigger robots with processing power will dig your pockets out pretty quickly if you try to do it alone.

Linux.com: How do you see the future of Linux and robots?

Mark Micire: Linux and robotics are very closely tied. All of the reasons I have described above are echoed for robotics teams around the world. You only have to go to a single robotics competition and see how many people are using Linux to understand. Most laboratory and field robots are reinstalled with Linux.

It is Linux's versatility that has allowed us to use it so successfully. This versatility will certainly bring it into all aspects of robotics.

Linux.com: That sounds great. We thank you very much for taking your precious free time to speak with us here at Linux.com.

Mark Micire: Thanks for giving me the opportunity.

Learn much more http://www.crasar.org an here http://www.csee.usf.edu/robotics, including more pictures to see.