SciVestor took a tour of the Robotics Pavilion at National Instruments’ NI Week 2008. Anu Saha, NI marketing manager discusses academic and corporate partnerships that feature LabView and CompactRIO technologies.
DARPA Urban Challenge
SciVestor Executive Director Jonas Lamis narrates the Autonomous Vehicle Roadmap that was presented at RoboBusiness 2008. This presentation is based in part on Robot Central’s observations, research, and opinions of emergent technologies from the DARPA Grand Challenge series of competitions. It highlights progress and challenges in the technologies necessary to facilitate civilian autonomous vehicles. Mr. Lamis discusses a plausible technology-driven autonomous vehicle roadmap from 2010 – 2020. The presentation highlights several emerging technology vendors including Velodyne, ibeo, Grey Matter, and TORC Technologies.
—
Jonas Lamis contributes to Robot Central, focusing on the business aspects of the robot economy. He also authors the weblog Singularity University and is an advisor to the Singularity Institute on Artificial Intelligence. Mr. Lamis is also the editor of Architecture and Governance Magazine, and writes and speaks frequently on enterprise software technologies.
New free research presentation available from SciVestor. You can download it here.
This presentation is being presented at RoboBusiness 2008. It highlights progress and challenges in the technologies necessary to facilitate civilian autonomous vehicles. We discuss a plausible technology driven autonomous vehicle roadmap from 2010 – 2030. The presentation highlights several emerging technology vendors including Velodyne, ibeo, Grey Matter, and TORC Technologies.
We present Renteria’s Hierarchy of Autonomy Needs – from Sensory Enablement to Basic Navigation to Business Logic. We discuss the fulfillment of these needs over the course of the three Grand Challenges. We lay out an autonomous vehicle roadmap and discuss key inflection points including: 1) The Cambrian technology explosion. 2) Adoption Hill. 3) The Plateau of Tenacity. SciVestor predicts adoption rates, reduction of fuel consumption, and vehicle deaths in 2020.
Authors: Ray Renteria and Jonas Lamis
Date: April 2008
Length: 32 pages
Research ID: 08R-002
Concepts Discussed: Grand Challenge, Urban Challenge, Autonomous vehicles, Prometheus Project, Stanley, Boss, Velodyne, ibeo, Grey Matter, TORC Technologies, roadmap
In what seems to be a recurring theme among DARPA Urban Challengers, these guys have greater ambitions than winning the race. “The goal was to be a strong performer, not necessarily win,” Chris Yakes, Director of the Advanced Products Group for Oshkosh, said.
Yakes explained that his team is developing an autonomous system in kit form similar to other kits the company provides to its military customers. Approximately 30% of Oshkosh’s business is in the military sector. The price of the kit will be comparable to the cost of their armored vehicle kit.
The kit still needs a little bit of fine-tuning. “We’re a couple of years from having a final product but we’re ready now to start doing demonstrations. By demonstrations I mean offering a vehicle (retrofitted with the kit) to a customer and letting them see first hand how it performs.” Yates went on to explain that variations of the autonomous system might be ready sooner. A semi-autonomous follower / leader system, for example, might be applied in a convoy of several vehicles in which only one contains a human driver or it is teleoperated.
Oshkosh has made some very overt technical design decisions based on the deep knowledge it has of its customer base. Their systems must be able to perform in very harsh environments and remain highly dependable for decades. “Our trucks live about 20 years. The system we provide must last at least that long.” Yates explained that they bias their technology selection to those without moving parts. Their computers are commercial off-the-shelf (“COTS”) systems that are cheap, easily replaced, and very durable. Oshkosh also depends more on computer vision than any other team that performed in the competition because cameras can be very rugged as they have no moving parts.
Computer vision is the method of identifying characteristics of a scene from digital images. Algorithms vary substantially depending on the desired data. Streoscopic vision, for example, requires two side-by-side cameras each generating an image of the same scene each from a slightly different perspective. The software behind this configuration finds objects of one image in the other. If the software finds the object in the same position on both images, the element is deemed to be far away. If the software finds that the object’s position has “shifted,” the object can be characterized as being closer to the cameras. The greater the shift, the closer the object is. From such information a 3D representation of the scene is constructed. Oshkosh is working with the University of Parma in Italy to develop the software behind their computer vision system.
Biasing towards cameras does not necessarily make them the only sensor in the kit. Oshkosh has also chosen to use ibeo LIDAR scanning technology to supplement their computer vision system. Yates was very reserved when asked details about other systems they evaluated and why they chose ibeo; however, he did explain the role of the ibeo. There are three units on the vehicle–two forward units and one rear. The units are used to identify obstacles.
During a conversation with 3rd-Place winner Virginia Tech Team Leader Charles Reinholtz about their own implementation of the ibeo sensors, Robot Central learned that there were occasions that the ibeo would be blinded and the system would require a reboot. There was at least one time when their robot, Odin, paused itself for approximately 90 seconds while it rebooted its ibeo systems. Team Oshkosh was eliminated when their robot threatened to bring down a building after it ran off the course and met a load-bearing pillar. As of the writing of this article, it was unclear if any contact was made nor was it clear if the failure was due to the ibeo issue described by Virginia Tech.
Nevertheless, Oshkosh is optimistic about its future role in saving the lives of American soldiers. And it should be. The sensor vendors will address their issues and Oshkosh will continue to mature its product. Oshkosh’s performance in the 2005 Grand Challenge and in this year’s 2007 Urban Challenge has very effectively demonstrated its technical and business prowess.
Tartan Racing’s “Boss” of Pittsburgh, Penn. turned in the top performance in the Defense Advanced Research Projects Agency (DARPA) Urban Challenge and won the $2 million cash prize as the competition’s first-place winner, DARPA announced today. Stanford Racing’s “Junior” of Stanford, Calif., won the $1 million second place prize, while Victor Tango’s “Odin” of Blacksburg, Va., received $500,000 for finishing third.
In a press briefing Dr. Tether explained that the teams each completed their missions approximately 20 minutes of each other. All performed well although he explained that he offered advice to Carnegie Mellon and Stanford during the National Qualifying event. “Carnegie Mellon was a little too aggressive in its driving. We told Stanford that they were too conservative. I don’t think we offered any advice to Victor Tango.” Virginia Tech team leader Charles Reinholtz chimed in, smiling, “We didn’t need any advice. We were just right.”
The competition is not quite over; however, three of the final six teams have met their mission objectives already. Who ranks 1st, 2nd, and 3rd is still to be determined as judges calculate each of the robot’s penalties and running times. Considering the substantial margin and relatively low number of penalties for Stanford’s Junior, Carnegie Mellon’s Boss, and Virginia Tech’s Odin, chances are very good that the top three positions will be filled by these three teams.
DARPA will announce the final scores Sunday.
I doubt the insurance company is going to cover this collision.
At 12:35 PM local time Cornell’s robot, Skynet, stopped itself in front of MIT’s robot. Skynet stayed there long enough that MIT’s robot made an executive decision to pass. It successfully passed Skynet’s DARPA chase vehicle. As MIT approached Skynet, it made another executive decision to pass. MIT began the procedure very elegantly. It went around Skynet and as it proceeded to reenter the lane in front of Skynet, Skynet began to drive forward.
Stanford’s robot, Junior, was paused because it was on its way to the wreck. The vehicles were separated and both are proceeding. Stanford was resumed. At risk is the performance of the impacted sensors. It appears that all systems are behaving well and all vehicles are still in the race.
I’ve been talking to a lot of people about all sorts of technologies and programming algorithms. I took a minute to break out of that mode to absorb the ambiance here today. It’s unlike anything I’ve ever experienced including the 2005 Grand Challenge tent. The ’05 tent was mostly occupied by engineers and media. The feed was very structured and the updates looked more like a giant video game than a feed.
This year, the feed is nicely produced and augmented with very professional commentary. I thought I’d take a break from the technology to describe this experience.
Outside this massive tent you can hear helicopters. Inside you hear the murmur of hundreds, maybe thousands of people. On occasion, the murmur erupts into a loud cheer of appreciation for the intelligence required to drive the course as the robots show off on the three massive projection screens at the front of the tent.
What is striking about this year’s event is the number of families and kids present. In this tent, there are armed guards, brilliant scientists, demonstrations of history-making robots, and families of all sorts of backgrounds. This is Americana at its best.
DARPA sure knows how to throw a party.
The teams definitely have a substantial cheering section with future scientists enjoying the shiny cars and all the great stuff around them.
At the same time, there are those who are working feverishly to keep the outside world up-to-date on today’s happenings. The media table is crowded and there are cables everywhere.
And now I’m smelling food.
A spectator favorite, Team Oshkosh’s Terra Max literally almost took out a building. At this point, it’s unclear what went wrong. There was aerial video footage that showed Terra Max butted up against a brick pillar. I don’t know if there was contact.
Annie Way placed itself in pause mode and DARPA made a decision to pull her out.
Update: As of 10:38 AM local time, Team UCF is out of the race.
Update: As of 11:07 AM local time, CarOLO is out of the race.
This morning’s launch was relatively smooth. Intelligent Vehicle Systems had some trouble when it saw a k-rail and paused itself for too long. DARPA allowed the team to reset and reposition itself for a relaunch. Their relaunch was successful and they’re doing well now. As a matter of fact, as I type this, I witnessed IVS perform a fantastic maneuver while it avoided car # 26, Cornell.
Cornell was in the wrong lane. When IVS came upon it, face-to-face, it avoided a collision and made the decision to pick the least of the evils to go around it. It hopped a curb, slightly, to avoid Cornell’s robot.
Car #62, Team CarOLO threw itself into Pause mode after it lodged itself on a berm in the off-road portion of the course. We’re waiting for an update on that.
Team Annie Way is stopped for undetermined reasons at an off-road intersection.
You can keep up to date with the very dramatic real-time video feed with excellent commentary at http://www.grandchallenge.org/darpauc07/watchtherace/livevideo.html.
Just minutes ago, Dr. Tony Tether announced the pole positions of the robots as they are unleashed into a simulated urban environment at the Urban Challenge Final Event Saturday. The environment is simulated only in that human-driven vehicles will have roll cages and six point harnesses and all the drivers will be wearing protective head gear. Otherwise, there is nothing simulated about the environment in which the robots will be driving.
The pole positions are:
- Tartan
- Victor Tango
- Stanford
- Ben Franklin
- Team UCF
- MIT
- Team Cornell
- “Our Nightmare” Team Oshkosh
- Honeywell / Intelligent Vehicle Systems
- Team AnnieWay
- CarOLO
Robots will be released in order of pole position. Dr. Tether jokingly qualified Team Oshkosh as “our nightmare” because its robot, TerraMax, has tires that are bigger than some of the robots. The robots will all be operating concurrently, each following its own mission.
Robot Central will be there to watch the mahem, er, um, the competition.
I wrote about the Velodyne sensor a couple of weeks ago touting its commercial viability in the emerging mobile robotics market. I had a chance to talk to one of its inventors today. Velodyne President Bruce Hall made it clear that although his company doesn’t have a vehicular entrant, they are clearly and very visibly participating in the DARPA Urban Challenge.
“We went from being on 12 out of 35 teams at the beginning of the National Qualifying Event to being on 7 out of 11 at the finals. I hope that when vehicles 1, 2, and 3 come in, we’re on 3 out of 3 vehicles,” Hall said.
The Urban Challenge teams are comprised of some of the most brilliant engineers on the planet. Adoption of a technology that can give them a structured view of the world around their robot obviously seems too compelling to resist, considering the adoption rates of Velodyne’s LIDAR within the DARPA Urban Challenge ecosystem. The interpretation of the data is where the scientists shine. Mere mortal application developers, however, require a higher-level abstraction that interprets the data for them–recognizing a blob of points as a vehicle or a pedestrian, for example.
Every team that uses the Velodyne system has built what is likely to be a driver intended to solve the same problem. That seems to be the point. One of those implementations will be the best. “It’s a competition. These guys are trying to solve a common problem better than the rest,” Hall explained. That statement seems to be validated by several teams with whom I spoke. Teams that used a competing technology, ibeo, chose to employ their own object recognition algorithms instead of using the algorithms provided by ibeo, a technology I will cover in a subsequent post.
“Today, our customers require a certain level of sophistication that inherently limits our sales [to scientific programmers that can interpret the data]. We know that. Some customers are asking for (inerntial management) correction, object identification, and so on. Like any good business, we try to stay focused.”
Staying focused is not the same thing as ignoring customer feedback. “Customers wanted to be able to choose density over speed. We gave them the ability to spin the unit at 300 and at 900 RPM.” The slower-spinning mode provides higher density of data points while the higher speeds senses the world faster. Another feature due to customer feedback was the governing of the high data volume being broadcast by the device. The governor reduces the number of points sent by the device to something relatively consumable by most applications. The device is capable of informing the robot of over 2.3 million points every second but for the software that consumes it but it’s like drinking from a full-open fire hose. The device can be governed down to a slower 1 million points per second and the application can choose to ignore data it can’t consume.
In all emerging technologies there are always issues that come up that allow their makers to refine and to strengthen the technology. Velodyne is not immune to this. There is a little bit of tension in the air with regards to a bug that has manifested in the context of the Urban Challenge. Close-proximity RF signals can potentially confuse the sensor. This problem has a simple fix that was offered to all teams. All but one chose to decline the fix. Hendrik Dahlkamp of Stanford Univeristy reflected a classic product development discipline. “We declined on putting in the fix because it’s too risky to make a change this late in the game. Plus, the cost of the bug isn’t that great to us.” For another team, however, it’s life and death. Team Annie Way was almost eliminated when the Velodyne sensor was “blinded” by the radio of a DARPA official. Actually, the team was in fact eliminated until the Team Leader contested the decision and explained the situation. Team Annie Way is now a finalist and Velodyne is working very closely with them.
Visit Scivestor.com or contact me at rrenteria@scivestor.com to learn more about the Velodyne and the Mobile Sensing market.
Team Gray may not have advanced to the finals but they’ve got their sights on bigger targets. With their latest autonomy in-a-box they may be positioned to become the Microsoft and IBM of autonomous vehicles.
Chief Engineer Paul Trepagnier explained that the Autonomous Vehicle System, or AVS for short, is a completely self-contained unit comprised of componentized navigational mobility that can be scripted.
The system effectively boils the entire autonomous navigation down into three major categories:
- Localization
- Obstacle Avoidance
- Actuation
It takes input from a GPS sensor to determine where it is in the world and the desired route to traverse. “The core AVS platform takes the GPS information and drives the vehicle. We’ve driven the car up to eighty miles per hour with less than 5 cm of error,” Trepagnier said. “Eighty two miles per hour,” President and Director of Gray Matter Eric Gray corrected.
The system is designed to accept input from sensors in order to identify obstacles. In the event an obstacle is in the way of the vehicle, the AVS performs the appropriate behavior to avoid the obstacle if possible.
As a testament to the modularity and flexibility of the system, Trepagnier explained that when they acquired the new vehicle for the National Qualifying Event, retiring “the white one,” they were able to integrate all sensors and actuators in less than fifteen minutes.
The modularity sheds a little light into the elegant architecture in the design. First, the system is comprised of two major layers: The Hardware Layer and The Software Layer. Both are proprietary.
Features of The Software Layer include the extensibility of the sensor array. It takes only three days or less to integrate a new sensor. The integration is comprised of a reusable driver that provides a common output that is consumable by the obstacle detection algorithms. Considering the available-now and relatively inexpensive cost of this device it behooves all major sensor manufacturers to develop AVS-compliant sensor drivers for their technologies.
Also within The Software Layer is a high-priority fail-safe system. There are two threads constantly running that monitor the software and the sensors: a Safety Monitor and a Failure Monitor, respectively. If one of the threads identifies something wrong, they have the authority to bring the vehicle to a stop.
The Hardware Layer also has some important responsibilities. “We didn’t like that (the monitor threads) could potentially go down. So we designed hardware to monitor the Safety Monitor and the Failure Monitor. The Hardware Layer can stop the vehicle if it detects that something went wrong with the monitors.” The Hardware Layer is connected directly into the vehicle’s drive-by-wire system. The system has no moving parts and can withstand “way above 10g’s. Most of what we’ve seen in our applications have incurred fewer than 2g’s.”
The team has several prospects with whom demonstrations and negotiations are underway. The base price of the unit is $125,000. This is a tremendously cost-efficient solution to an otherwise expensive problem.
“Our vision is to be a commonplace technology in all vehicular testing environments,” declared Eric Gray. “Universities are talking about using this as a basis for their work. It allows them to focus their efforts on areas of specialization such as computer vision.”
Trepagnier seemed to enjoy his next hypothetical scenario almost a little too much. “We have a computer that can drive within five centimeters of a planned course. We can run the car in record mode, drive the track, and then put the path through a post-processor that will run a genetic algorithm to find the optimal route, and feed it into AVS. ” He said of racing an autonomous vehicle at high speeds. “We would be unbeatable.”
DARPA tightened the scrutiny of the finalist selection process. DARPA originally planned on selecting the top 20 performers to participate in the final event. In a sudden change of plans, DARPA selected 11. The selected teams are:
- Ben Franklin Racing Team, Philadelphia, PA (Track B)
- CarOLO, Caroline, NY (Track B)
- Honeywell/Intelligent Vehicle Solutions, Troy, MI (Track A)
- MIT, Cambridge, MA (Track A)
- Stanford Racing Team, Stanford, CA (Track A)
- Tartan Racing, Pittsburgh, PA (Track A)
- Team Cornell, Ithaca, NY (Track A)
- Victor Tango, Blacksburg, VA (Track A)
- Team AnnieWay, Palo Alto, CA (Track B)
- Team Oshkosh Truck, Oshkosh, WI (Track A)
- Team UCF, Orlando, FL (Track B)
Track A designates a mode of participation that includes an award of up to $1M to cover development costs. Last year, all teams had the opportunity to apply for Track A participation. Ten were selected. These teams are eligible to win at most $1M on Saturday’s event.
Track B participation requires that the teams subsidize their own development costs. These teams are eligible for up to $2M in prizes on Saturday’s event.
Teams will be practicing today while DARPA refines its final mission plan.
Robot Central analyst Ray Renteria is blogging live from the Urban Challenge site in California this week. You can subscribe to his news feed to get a daily digest of all of the Urban Challenge news from Robot Central. Click here and enter your email address to subscribe.
DARPA has already decided that the following six Urban Challenge Teams demonstrated sufficient driving savvy to be invited to Saturday’s final event:
- Team Cornell
- Stanford Racing Team
- Tartan Racing (Carnegie Mellon)
- VictorTango (Virginia Tech)
- CarOLO (Track B)
- Ben Franklin Racing Team (Track B)
Of these teams, CarOLO and Ben Franklin Racing Team had not been awarded DARPA grants to develop their robots. All others had been eligible for up to $1M in development funds in the Track A program.
Conversely, DARPA has also decided that the following teams are not in contention for Saturday’s final event:
- The Golem Group (Track A)
- Mojavation
- Team Caltech (Track A)
- Team Jefferson
- Team Urbanator
- Gator Nation
- Team Juggernaut
- Georgia Tech / SAIC Sting Racing
- Ody-Era
- SciAutonics/Auburn Engineering
- Team Berlin
- University of Utah
- Princeton
- Axion Racing
Of the aforementioned teams, two are Track A teams. DARPA had awarded the Track A teams a grant of up to $1M in development funds while Track B teams funded their own development efforts.
This leaves the following 15 teams in contention for the remaining 14 finalist slots:
- OSU-ACT
- Team UCF
- Insight Racing
- Intelligent Vehicle Systems
- Team Oshkosh Truck
- Team CajunBot
- Team Case
- Team Gray
- Austin Robot Technology
- Team Autonomous Solutions
- Team-LUX
- Team Cybernet
- Team AnnieWay
- Avantguardium
- MIT
One of these teams might be dropped from the final lineup. In 2005, DARPA announced a last minute additional slot to the finalist roster. It’s possible that DARPA will do the same this year which would mean that all of the teams that have not been explicitly eliminated already will be in Saturday’s final run.
The Defense Advanced Research Projects Agency (DARPA) is hosting a robotics competition in Victorville, CA on November 3 called the DARPA Urban Challenge in which twenty autonomous vehicles are required to navigate traffic while respecting the rules of the road. An elimination phase called the National Qualifying Event has been underway this week in order to select the final twenty teams of thirty five that were invited to participate. Today marks the final day that the teams can impress the judges with their technical and navigational prowess to prove that they are worthy to compete in Saturday’s final competition.
According to a press release from Austin Robot Technology, a team still in contention, the following twelve teams have been eliminated:
- Mojavation
- Team Caltech
- Team Jefferson
- Team Urbanator
- Gator Nation
- Team Juggernaut
- Georgia Tech / SAIC Sting Racing
- Ody-Era
- SciAutonics/Auburn Engineering
- Team Berlin
- University of Utah
- Princeton
Four teams have already met the criteria for participating in the finals and are “sitting pretty,” according to the press release:
- Team Cornell
- Stanford Racing Team
- Tartan Racing (Carnegie Mellon)
- VictorTango (Virginia Tech)
This leaves the following 19 teams in contention for the remaining 16 positions:
- OSU-ACT
- Team UCF
- Insight Racing
- Intelligent Vehicle Systems
- The Golem Group
- Team Oshkosh Truck
- Axion Racing
- Team CajunBot
- Team Case
- Team Gray
- Austin Robot Technology
- Team Autonomous Solutions
- Team-LUX
- Team Cybernet
- Team AnnieWay
- CarOLD
- Avantguardium
- Ben Franklin Racing Team
- MIT
The eliminated teams undoubtedly spent hundreds, if not thousands, of man-hours in preparing for the qualifications and that effort does not go unnoticed, especially with DARPA officials. “DARPA congratulates these teams for making it to the semifinals, and salutes them for their contributions to developing autonomous robotic ground vehicle technology that will someday save lives on the battlefield,” said DARPA.
As a former finalist I’m sure that the remaining teams have not been getting much sleep or many showers. They’ve got hundreds of thousands of dollars, maxed-out credit cards, intangible debts like missed birthdays, anniversaries, and school days invested in their robots. Robot Central gratefully salutes their answering DARPA’s call to arms and wishes them the best in today’s trials.
The final 20 will be announced tomorrow. Robot Central will be there.
Team headed to California to compete among 35 semifinalist teams from across the country
ATLANTA (October 23, 2007) – The College of Computing at Georgia Tech today announced that the Sting Racing team, a collaboration between Georgia Tech and Science Applications International Corporation [NYSE: SAI], has left for Victorville, Calif. to compete in the Defense Advanced Research Projects Agency’s (DARPA) Urban Challenge semifinals and finals events with their fully autonomous vehicle entry, Sting 1. The semifinal National Qualifying Event (NQE) is scheduled to begin October 26, with the final event on November 3 on the site of the former George Air Force Base. Georgia Tech-SAIC Sting Racing, composed of researchers from Georgia Tech’s Colleges of Computing, Engineering, the Georgia Tech Research Institute, and SAIC, is one of only 35 semifinalist teams from across the country.
“We invite the public to join us in applauding the members of the Sting Racing team and their inspiring enthusiasm and commitment,” said Dr. Henrik Christensen, KUKA chair of Robotics for the College of Computing at Georgia Tech and principal investigator for Sting Racing. “With support from Georgia Tech, SAIC, and the local community, we are ready to compete among the world’s best robotics programs and drive our way into the Urban Challenge finals.”
For more than a year the members of the Sting Racing team have been working to prepare and program Sting 1, a Porsche Cayenne, to compete autonomously in this high-profile, national challenge. Combining the leadership and broad technological expertise in robotics at Georgia Tech and complemented by SAIC’s capabilities in robot vision and sensor fusion, the team has risen to the challenge of programming the vehicle to operate without a driver, stay on course, and deal with obstacles in its way, such as fellow cars, while maintaining realistic speeds.
“Sting 1 illustrates the seamless collaboration the Georgia Tech-SAIC team members have demonstrated in preparing for the Urban Challenge this past year,” said Karl Kluge, SAIC senior scientist – perception researcher. “With Georgia Tech as one of the nation’s foremost robotics research institutions and SAIC as a seasoned, two-time DARPA Grand Challenge contender, the Sting Racing entry is a strong contender in this Challenge.”
The Urban Challenge is the third in a series of DARPA-sponsored competitions to foster the development of robotic ground vehicle technology without a human operator, designed for use on the battlefield. The Urban Challenge will feature autonomous ground vehicles executing simulated military supply missions safely and effectively in a mock urban area. DARPA will award $2 million, $1 million and $500,000 awards to the top three finishers that complete the course within the six-hour time limit.
For more information, visit www.sting-racing.org.
About SAIC
SAIC is a leading provider of scientific, engineering, systems integration and technical services and solutions to all branches of the U.S. military, agencies of the Department of Defense, the intelligence community, the U.S. Department of Homeland Security and other U.S. Government civil agencies, as well as to customers in selected commercial markets. With more than 44,000 employees in over 150 cities worldwide, SAIC engineers and scientists solve complex technical challenges requiring innovative solutions for customers’ mission-critical functions. SAIC had annual revenues of $8.3 billion for its fiscal year ended January 31, 2007.
About the College of Computing at Georgia Tech
The College of Computing at Georgia Tech is a national leader in the creation of real-world computing breakthroughs that drive social and scientific progress. With its graduate program ranked 11th nationally by U.S. News and World Report, the College’s unconventional approach to education is defining the new face of computing by expanding the horizons of traditional computer science students through interdisciplinary collaboration and a focus on human centered solutions. For more information about the College of Computing at Georgia Tech, its academic divisions and research centers, please visit www.cc.gatech.edu.
Semifinalist ”Cybervan” Perfecting New Life-Saving Technology in
San Antonio
ANN ARBOR, Mich.–(BUSINESS WIRE)–Oct. 17, 2007–A DARPA (Defense Advanced Research Projects Agency) Urban Challenge National Qualifier, Team Cybernet, is en route to Victorville, California, to compete in the final stages of the competition. The team is spending the remaining time before the main event perfecting the “Cybervan,” in San Antonio, Texas.
The 2007 DARPA Urban Challenge is the third in a series of competitions DARPA has held to foster the development of autonomous robotic ground vehicle technology simulated military supply missions in a mock urban area. Beginning on October 26th semifinalists will compete for a chance to reach the finals and contend for $3.5 million in prizes.
“We are very excited to have the opportunity to compete against the world’s leading innovators in this very important endeavor, and are grateful to DARPA for the opportunity to serve our men and women in uniform,” said Chuck Jacobus, Team Cybernet Leader. “At the heart of the countless hours and exceptional innovation dedicated to this effort by every member of Team Cybernet is a shared commitment to removing service personnel from harm’s way. The Cybervan is a practical solution to a very dangerous problem.”
Team Cybernet, from Ann Arbor, Michigan, is committed to delivering tomorrow’s military solutions today. By converting an 11-year old Chrysler minivan into a sophisticated autonomous “bot,” Team Cybernet’s solution can be applied to the similarly-aged fleet of military vehicles in the field today. Comprised almost entirely of professionals from Cybernet Systems Corporation, a woman-owned American research and development company, the self-funded Team Cybernet added $45,000 of mostly commercial off-the-shelf materials and countless hours of intellectual capital to develop the “Cybervan.”
To learn more about Team Cybernet or Cybernet Systems Corporation, please visit www.cybernet.com.
CONTACT: Cybernet
Lee Hudson, 202-715-1554
Lee.Hudson@dittus.com
or
Kevin Tang, 734-474-2612
media@cybernet.com
[This is a repost of Robot Central's first writeup. We will be counting down to the event where we will be on location providing you with real time updates. --Ray]
On November 3, thirty six of the worlds most advanced autonomous vehicles will be competing against each other to be declared the most advanced. Each will not only be required to demonstrate complex navigational and problem solving skills, but they will also be required to understand rules of the road.
Stanford University took home the prize with their Volkswagen Touareg “Stanley” at the 2005 DARPA Grand Challenge. Stanley was the first in history to successfully navigate through miles of desert terrain, avoiding pitfalls that killed all but five other competitors. As difficult as ’05 Grand Challenge was, it was could be boiled down to a basic obstacle avoidance problem. When a robot approached another robot to pass, the DARPA chase vehicle would send a command to the slowpoke and tell it to yield the road to the robot behind him. (You should have seen the observation tent where all the teams were watching their robots in action on scores of plasma screens when Stanford’s robot Stanley passed up Carnegie Mellon media sweetheart Sandstorm. They went nuts!) Anyway, the point is that back in my day, we were given a file of GPS coordinates to which the robots had to drive one at a time. Along the way, the ‘bots had to be smart enough to avoid obstacles and be built durably enough to withstand the kinds of things you’d expect in mountainous desert–a good transmission, puncture resistant tires, lots of gas, and so on. When something tricky came up like a robot wanting to pass, a human intervened and effectively made the forward vehicle an obstacle to the robot behind it. The robot behind it just avoided it.
This year at the 2007 DARPA Urban Challenge, there’ll be none of that. Navigation and obstacle avoidance is so 2005. Not only will the ‘bots be required to demonstrate robust navigational skills, they’ll have to be able to discover alternate routes because primary routes will be randomly blocked. Not only will robots be required to demonstrate their passing abilities, they will need to determine when it’s safe to pass. They’re even going to have to drive into oncoming traffic to pass the vehicle in front of it. At a four-way stop, the ‘bots will have to respect the rules of a stop-and-go intersection–a feat not usually performed well by many human drivers! You have to wonder how many of the teams had to Google the rules before they coded ‘em in.
This event is a big deal. It is bringing together some of the greatest minds and technologies in the world in order to force the advancement of autonomous transportation. We civilians have got better things to do with our time than to drive to and from work every day. My commute is an hour each way. That’s 10 hours that I could be doing something productive. Our soldiers have got better things to do than die driving a transport vehicle full of ammo down Mainstreet, Bagdad–like live.
