Teams of researchers are hoping to give life to a six-foot, 330-pound humanoid robot at the the Robotics Challenge in Homestead, Florida on December 20 and 21.
The teams are expected to enable the robot—and others—to autonomously walk, use human tools, and drive a car.
The event is sponsored by DARPA, or the Defense Advanced Research Projects Agency, an arm of the U.S. Department of Defense that focuses on advanced research.
DARPA said the program at the Homestead Miami Speedway, is aimed at developing robots capable of working hand-in-hand with humans during natural or man-made disasters.
”Think of the nuclear plants that were damaged during the tsunami in Japan,” said David Conner, a senior research scientist with TORC Robotics, whose team is includes with roboticists from Virginia Polytechnic Institute, better known as Virginia Tech. “If they could have gone in and opened some valves to vent some of the hydrogen, they could have avoided an explosion. If we could have sent a robot in to do that task, it wouldn’t have put humans in danger. That’s the motivating goal in this project.
”We’re working to raise the realm of what’s possible,” he added.
The test is part of a multi-year competition that’s divided into three phases. The Florida event is the second phase. The final phase is set for late in 2014. The winner will receive a $2 million prize.
”Robots right now, for the most part, are either on stationary bases working on repetitive tasks or working in a lab,” said Gill Pratt, a DARPA program manager. “We’re trying to move to task-level autonomy. Instead of saying, ‘Move ahead a tenth of an inch,’ we’d say, ‘Move forward and open that door.’ During a disaster, communications could be very poor. The robot needs more smarts to be able to do things on its own.”
Robots have yet to reach that level of development. In fact, to date they are far from it.
However, Peter Neuhaus, a research scientist and member of the Florida Institute for Human and Machine Cognition team, said that at the close of the current challenge next year, the vision of having a robot work in a disaster area will be much closer.
The event includes teams from NASA’s Jet Propulsion Labs, MIT, Carnegie Mellon University, Drexel University, and Virginia Tech. They are charged with having their robot complete eight different tasks.
The robots will have 30 minutes to complete each task in the challenge. They include climbing a ladder, removing debris, opening and walking through doors, cutting a hole into a wall, turning valves and driving a car.
The tasks are geared to test the robot’s mobility, dexterity, perception, and operator control mechanisms.
”The robots are not at the level of task autonomy we would like to see,” said Pratt. “We expect their human operators will play a big role. Ultimately, the robot will need to recognize its environment and plan its moves to accomplish its tasks.”
The point of the challenge is to push robotics technology to become more autonomous, deciding themselves how best to move around obstacles and how to get to where they need to be.
”It’s a robot approximating human capabilities,” Connor said. “This is the most ambitious challenge to get all of the systems integrated into a robot acting outdoors. Each individual piece, such as the steering controller or obstacle avoidance, has been demonstrated. But taking that obstacle detection capability into a humanoid robot that is actually steering a car? That’s new.”
Human controllers will be involved at a higher level than in the past.
For instance, the robots are too complex to control every joint so a human may have to command it to turn a valve while the device figures which individual joints, like the elbow and the wrist, need to be engaged.
”The software is interpreting these high-level commands into low-level commands for how it will get that done,” noted Connor.
And R.J. Linton, a Ph.D. candidate and member of the team from the Worcester Polytechnic Institute, said it’s a much greater challenge to build the software for a humanoid robot, than for a four-legged or wheeled robot.
”The human form is bad in general,” he explained. “We have an unstable gate. The humanoid shape is inherently unstable. You’re always shifting weight to maintain balance. You have to teach a robot how to do that. Atlas has to always be kind of moving, just like a human.”
Neuhaus said humanoid robots are in their infancy and called the challenge a good starting point for needed research.
”There are some technical challenges—no one really felt it was possible,” he said. “It involves solving a lot of problems at the same time. You have to solve the [artificial intelligence] challenge, embedded computers, actuation, algorithms for walking and balancing and manipulation. You have to fit all of that into the same research project. Researchers might work on individual parts but not the entire thing.”
A big issue for a humanoid robot, for instance, is enabling it to have the hands do something while it’s walking. Those two simple sounding tasks might involve 30 or 40 joints working simultaneously and in unison.
”We spend a few years of our lives learning how to control our [joints] and our sense of balance and pushing that task down to a reflex,” said Neuhaus. “When a one-year-old is learning to walk, it’s at the forefront of their cognition. They’re really thinking hard about how to do it. When you’re older, you can walk and think about other things at the same time.”
Some teams are building their own robot and the software to run it, while others are developing software for the Boston Dynamics Atlas robot, a six-foot, two-legged, humanoid robot that, at this point, has the mobility and dexterity of a one-year-old child.
When the robotics challenge began, 100 teams registered and 26 qualified to compete. The number was thinned to 17 in June after the software was tested in simulation.
The 17 teams remaining are receiving financial backing from DARPA. The field will be narrowed to eight teams or less after the latest challenge.
According to Linton, a humanoid robot capable of assisting humans during a natural disaster is possible within the next ten years.
This story, "Robots compete to mimic common human tasks" was originally published by Computerworld.