The latest episode of the Robots podcast focusses on using robots to model biology. The first guest is Barbara Webb, who is director of the Insect Robotics Group at the University of Edinburgh and has published several seminal papers on the subject (her 2008 paper on 'Using robots to understand animal behavior' is a good place to start). Following an earlier interview on her work, Webb now addresses more complex questions: What is the importance of distributed control and embodiment in biological systems? and How do we find equally powerful solutions for robots? This episode's second guest is Steffen Wischmann, who is a Postdoctoral researcher at the Laboratory of Intelligent Systems at the EPFL and at the Department of Ecology and Evolution at the University of Lausanne, Switzerland. Wischmann has a long-standing, deep interest in robotic models and his work has covered both embodied and cognitive aspects of robot models. He outlines the value of robotic models for biology, describes their strengths and limitations, and explains their increasingly important role in research fields that cannot rely on a fossil record to understand the evolution of traits, such as animal communication. Read on or directly tune in!
�I N ' S B X"
Robots: Modeling Biology: "Barbara Webb from the University of Edinburgh discusses insect inspired robotics as a control system design approach. Steffen Wischman from the EPFL/UNIL then gives his view on when robots should be used to model biology and his interest in using artificial evolution."
Scoop: KUKA's youBot Mobile Manipulator Unveiled: "With a 5-DOF manipulation arm sitting on omnidirectional wheels, KUKA's youBot has open interfaces that roboticists can use to experiment with the machine"
Following the Mobile Manipulation Challenge at ICRA 2010, Willow Garage has compiled an entertaining video. It shows some robots having fun, and at the same time showcases some of the world's most advanced service robot arms.
In order of appearance, the video features Willow Garage's own PR2 shaking hands with a Kuka Lightweight and a Meka arm, the Fraunhofer IPA's Care-O-Bot which uses a Schunk arm, an unknown mobile robot, the PR2 shaking hands with the Barrett arm, Aldebaran's Nao, the homer@UniKoblenz Team's manipulation challenge robot based on a Pioneer 3AT and a Katana arm, the University of Bonn's Dynamaid, another brief glimpse of the Barrett arm and finally an impressive demo of the PR2 and Care-O-Bot dancing in the robotic equivalent of a tight embrace.
Robots big and small showcase their skills: "Two robotics events were designed to prove the viability of advanced technologies for robotic automation of manufacturing and microrobotics."
Make room, Bender, Rosie and R2D2! Your newest mechanical colleagues are a few steps closer to reality, thanks to lessons learned during two robotics events hosted by the National Institute of Standards and Technology (NIST) at the recent IEEE International Conference on Robotics and Automation (ICRA) in Anchorage, Alaska. The events -- the Virtual Manufacturing Automation Competition (VMAC) and the Mobile Microrobotics Challenge (MMC) -- were designed to prove the viability of advanced technologies for robotic automation of manufacturing and microrobotics.
n the first of two VMAC matches, contestants used off-the-shelf computer gaming engines to run simulations of a robot picking up boxes of various sizes and weights from a conveyor belt and arranging them on a pallet for shipping. The two teams in the competition -- both from Georgia Tech University -- showed that their systems were capable of solving mixed palletizing challenges. To do this, the system had to receive a previously unseen order list, create a logical plan for stacking and arranging boxes on a pallet to fulfill that order, and then computer simulate the process to show that the plan worked. Getting all of the boxes onto the pallet is relatively straightforward; however, creating a stable, dense pallet is a difficult challenge for a robot.
The second manufacturing contest "road tested" a robot's mobility in a one-third scale factory environment. The lone participating team, the University of Zagreb (Croatia), demonstrated that it could successfully deliver packages simultaneously to different locations in the mock factory by controlling three robotic Automated Guided Vehicles (AGVs) at once.
In the microrobotics match-up, six teams from Canada, Europe and the United States pitted their miniature mechanisms -- whose dimensions are measured in micrometers (millionths of a meter) -- against each other in three tests: a two-millimeter dash in which microbots sprinted across a distance equal to the diameter of a pin head; a microassembly task inserting pegs into designated holes; and a freestyle competition showcasing a robot's ability to perform a specialized activity emphasizing one or more of the following: system reliability, level of autonomy, power management and task complexity.
In the two-millimeter dash, the microbot from Carnegie Mellon University broke the world record held by Switzerland's ETH Zurich (the event also was part of earlier NIST-hosted "nanosoccer" competitions) with an average time of 78 milliseconds. However, the achievement was short-lived. Less than an hour later, the French team (representing two French research agencies: the FEMTO-ST Institute and the Institut des Systèmes Intelligents et de Robotique, or ISIR) shattered the mark with an average time of 32 milliseconds.
ETH Zurich was the champion in the microassembly event with a perfect 12 for 12 score steering pegs approximately 500 micrometers long (about the size of a dust particle) into holes at the edge of a microchip. Runner-up was Carnegie Mellon whose microbot successfully placed 4 of 9 pegs.
ETH Zurich's robot also captured the freestyle event, amazing spectators with its unprecedented ability to maneuver in three dimensions within a water medium. In fact, in one demonstration, the Swiss device "flew" over the edge of the microassembly field, reversed direction and pushed out the pegs it had inserted earlier. Taking second place in the freestyle event was the team from Carnegie Mellon that demonstrated how three microbots could be combined into a single system and then disassembled again into separate units. Third place in the event went to the microbot from the Stevens Institute of Technology.
NIST conducted the VMAC in cooperation with IEEE and Georgia Tech, and collaborated on the MMC with the IEEE Robotics and Automation Society. More events of this kind with evolving challenges are planned for the future, as robotics technologies mature. NIST will work with university and industry partners on these events with the goal of advancing skills that future robots -- both full-size and micro-size -- will need to carry out their functions.
Soccer-playing robots get creative with physics-based planning: "Robot soccer players are warming up to compete in this month's RoboCup 2010 world championship in Singapore. A new algorithm will help newly created robots to predict the ball's behavior based on physics principles."
Robot soccer players from Carnegie Mellon University competing in this month's RoboCup 2010 world championship in Singapore should be able to out-dribble their opponents, thanks to a new algorithm that helps them to predict the ball's behavior based on physics principles.
That means that the CMDragons, the Carnegie Mellon team that competes in RoboCup's fast-paced Small-Size League, likely will be able to out-maneuver their opponents and find creative solutions to game situations that could even surprise their programmers. It's possible that the physics-based planning algorithm also might enable the players to invent some new kicks. "Over the years, we have developed many successful teams of robot soccer players, but we believe that the physics-based planning algorithm is a particularly noteworthy accomplishment," said Manuela Veloso, professor of computer science and leader of Carnegie Mellon's two robot soccer teams.
"Past teams have drawn from a repertoire of pre-programmed behaviors to play their matches, planning mostly to avoid obstacles and acting with reactive strategies. "To reach RoboCup's goal of creating robot teams that can compete with human teams, we need robots that can plan a strategy using models of their capabilities as well as the capabilities of others, and accurate predictions of the state of a constantly changing game," said Veloso, who is president of the International RoboCup Federation. In addition to the Small-Size League team, which uses wheeled robots less than six inches high, Carnegie Mellon fields a Standard Platform League team that uses 22-inch-tall humanoid robots as players. Both teams will join more than 500 other teams with about 3,000 participants when they converge on Singapore June 19-25 for RoboCup 2010, the world's largest robotics and artificial intelligence event.
RoboCup includes five different robot soccer leagues, as well as competitions for search-and-rescue robots, for assistive robots and for students up to age 19. The CMDragons have been strong competitors at RoboCup, winning in 2006 and 2007 and finishing second in 2008. Last year, the team lost in the quarterfinals because of a programming glitch, but had dominated teams up to that point with the help of a preliminary version of the physics-based planning algorithm. "Physics-based planning gives us an advantage when a robot is dribbling the ball and needs to make a tight turn, or any other instance that requires an awareness of the dynamics of the ball," said Stefan Zickler, a newly minted Ph.D. in computer science who developed the algorithm for his thesis. "Will the ball stick with me when I turn? How fast can I turn? These are questions that the robots previously could never answer."
The algorithm could enable the robots to concoct some new kicks, including bank shots, Zickler said. But the computational requirements for kick planning are greater than for dribbling, so limited computational power and time will keep this use to a minimum.
Each Small-Size League team consists of five robots. The CMDragon robots include two kicking mechanisms -- one for flat kicks and another for chip shots. They also are equipped with a dribble bar that exerts backspin on the ball. Each team builds their own players; Michael Licitra, an engineer at Carnegie Mellon's National Robotics Engineering Center, built the CMDragons' highly capable robots. Like many robots in the league, the CMDragons have omni-directional wheels for tight, quick turns. In addition to physics-based planning, the CMDragons are preparing to use a more aggressive strategy than in previous years.
"We've noticed that in our last few matches against strong teams, the ball has been on our side of the field way too much," Zickler said. "We need to be more opportunistic. When no better option is available, we may just take a shot at the goal even if we don't have a clear view of it." In addition to Veloso and Zickler, the CMDragons include Joydeep Biswas, a Robotics Institute master's degree graduate and now a first-year Ph.D. student in robotics, and computer science undergraduate Can Erdogan. "Figuring out how to get robots to coordinate with each other and to do so in environments with high uncertainty is one of the grand challenges facing artificial intelligence," Veloso said. "RoboCup is focusing the energies of many smart young minds on solving this problem, which ultimately will enable using distributed intelligence technology in the general physical world."
