Biologically inspired robots are being realized by engineers and scientists all over the world. While much emphasis is placed on developing physical characteristics for robots such as human-like faces or artificial muscles, engineers in the Telerobotics Research and Applications Group at NASA’s Jet Propulsion Laboratory in Pasadena, CA, are among those working to program robots with forms of artificial intelligence similar to human thinking processes.
“The way robots function now, if something goes wrong, humans modify their programming code and reload everything, then hope it eventually works,” said JPL robotics engineer Barry Werger. “What we hope to do eventually is get robots to be more independent and learn to adjust their own programming.”
Scientists and engineers take several approaches to control robots. The two extreme ends of the spectrum are called “deliberative control” and “reactive control.” The former is the traditional, dominant way in which robots function, by painstakingly constructing maps and other types of models that they use to plan sequences of action with mathematical precision. The robot performs these sequences like reading a treasure map: from point A, move 36 paces north, then 12 paces east, then 4 paces northeast to point X.
The downside to this is that if anything interrupts the robot’s progress (for example, if the map is wrong or lacks detail), the robot must stop and make a new map and a new plan of action. This re-planning process can become costly if repeated over time. Also, to ensure the robot’s safety, back-up programs must be in place to abort the plan if the robot encounters an unforeseen rock or hole that may hinder its journey.
“Reactive” approaches, on the other hand, get rid of maps and planning altogether and focus on live observation of the environment: slow down if there’s a rock ahead, dig if you see a big X on the ground.
The JPL Telerobotics Research and Applications Group, led by technical group supervisor Dr. Homayoun Seraji, focuses on “behavior-based control,” which lies toward the “reactive” end of the spectrum. Behavior-based control allows robots to follow a plan while staying aware of the unexpected, changing features of their environment: turn right when you see a red rock, go all the way down the hill, and dig right next to the palm tree.
Behavior-based control allows the robot a great deal of flexibility to adapt the plan to its environment as it goes, much as a human does. This presents a number of advantages in space exploration, including alleviating the communication delay that results from operating distant rovers from Earth.
In space, extending the human touch — be it in low Earth orbit or to the Moon, Mars, and asteroids — is bolstered by a fusion of astronaut and robot skills.
“We’re working on human robotic systems — not either or, but robots that make a crew more effective,” said Bill Bluethmann at NASA’s Johnson Space Center (JSC) in Houston, TX. Ap p roaching 25 years of robotics work, Bluethmann is the Human Robotic Systems Project Manag er at JSC.
NASA’s Office of the Chief Technologist is cultivating new sets of human robotics systems under its Space Technology Program. As Bluethmann pointed out, “A big part of that is doing in-space work,” such as designing lengthy robot arms that can stretch out and grapple an asteroid.
“Giving astronauts a ‘finesse factor’ to safely work around a space object demands different approaches, given an asteroid’s microgravity condition,” Bluethmann said. “Making use of a robotic arm to anchor a piloted excursion vehicle to an asteroid is under study, as is positioning an astronaut over the asteroid to enable up-close-and-personal study.”
Leading-edge custom motors and motion control technology are enabling factors in tightly packaging robotic arms. “We’re able to embed a lot of smarts in the joints,” Bluethmann ex plain ed, “rather than running long and heavy wires back to some central spot.”
Shoulder to Shoulder
Designing integrated human robotic systems relies upon three main disciplines: mechanical, electrical, and software engineering. “We work shoulder-to-shoulder. The tools have gotten better and we have put together great teams,” Bluethmann said.
Another task of human robotic systems is to alleviate the things that astronauts don’t necessarily want to do. “We call those the dull, dangerous, and dirty duties,” Bluethmann added. Setting up or tearing down a worksite, even checking a spacecraft’s airflow, he said, is checklist labor that’s perfect for a robot.
An added robot responsibility would be to predict what the next tool is that an astronaut will require. Once again, robots would work with humans in a complementary way to reduce the burden, take over repetitive toil, or help mitigate risk.
“We’re not building robots to compete with the crew, but to really make them more productive,” Bluethmann said. The International Space Station (ISS) has become an ideal place to testbed human robotic systems, such Robonaut 2 (R2), fulfilling a 15-year dream to put a humanoid robot into space.
Melding the human brain with its ability to advise, with smart robots — but also have robots smart enough to ask for help — “is a very powerful approach,” Bluethmann observed.
Since arriving aboard the ISS, Robonaut 2, designed by NASA and General Motors, has been put through a series of increasingly complex tasks to test the feasibility of a humanoid robot taking over routine and mundane chores, or even assisting a spacewalker outside the station.
How Do They Do It?
Seraji’s group at JPL focuses on two of the many approaches to implementing behavior-based control: fuzzy logic and neural networks. The main difference between the two systems is that robots using fuzzy logic perform with a set knowledge that doesn’t improve, whereas robots with neural networks start out with no knowledge and learn over time.
“Fuzzy logic rules are a way of expressing actions as a human would, with linguistic instead of mathematical commands. For example, when one person says to another person, ‘It’s hot in here,’ the other person knows to either open the window or turn up the air conditioning. That person wasn’t told to open the window, but he or she knew a rule such as ‘when it is hot, do something to stay cool,’” said Seraji.
By incorporating fuzzy logic into their engineering technology, robots can function in a humanistic way and respond to visual or audible signals, or in the case of the above example, turn on the air conditioning when it thinks the room is hot.
Neural networks are tools that allow robots to learn from their experiences, associate perceptions with actions, and adapt to unforeseen situations or environments. “The concepts of ‘interesting’ and ‘rocky’ are ambiguous in nature, but can be learned using neural networks,” said JPL robotics research engineer Dr. Ayanna Howard, who specializes in artificial intelligence and creates intelligent technology for space applications. “We can train a robot to know that if it encounters rocky surfaces, then the terrain is hazardous. Or if the rocky surface has interesting features, then it may have great scientific value.”
Neural networks mimic the human brain in that they simulate a large network of simple elements similar to brain cells that learn through being presented with examples. A robot functioning with such a system learns somewhat like a baby or a child does, only at a slower rate.
“We can easily tell a robot that a square is an equilateral object with four sides, but how do we describe a cat?” Werger said. “With neural networks, we can show the robot many examples of cats, and it will later be able to recognize cats in general.”
Similarly, a neural network can “learn” to classify terrain if a geologist shows it images of many types of terrain and associates a label with each one. When the network later sees an image of terrain it hasn’t seen before, it can determine whether the terrain is hazardous or safe based on its lessons.
A big-picture view for human robotic systems is one that involves not only teleoperation (operating a machine from afar), but also telepresence. Telepresence makes use of technologies that allow a person to feel as if they were present, to give the appearance of being present, or to have an effect, via telerobotics, at a place other than their true location. A telepresence reality helmet, for example, would pipe in what a distant robot is viewing. “As technologists, that’s one direction we want to go in. The ability to look through a robot’s eyes is very potent,” Bluethmann added.
Human robotic systems for space can spur many applications on Earth. “The work we’re doing at NASA in robotics translates to our economy back home,” Bluethmann said. “As we saw with computers, they didn’t replace us — they made us more productive. I’m anticipating, as we go into the next decade and beyond, we’re going to have more and more robotic-type machines that can offload work.”
With continuous advances in robotic methods like behavior-based control, future space missions might be able to function without relying heavily on human commands. On the home front, similar technology is already used in many practical applications such as digital cameras, computer programs, dishwashers, washing machines, and some car engines.
“Does this mean robots in the near future will think like humans? No,” Werger said. “But by mimicking human techniques, they could become easier to communicate with, more independent, and ultimately more efficient.”
Bluethmann points out that NASA is partnered with the White House Office of Science and Technology Policy, and other aligned agencies, in undertaking a National Robotics Initiative. The goal of the NRI enterprise is to accelerate the development and use of robots in the United States that work beside or cooperatively with people.
“I see a new industry growing up around robots. I see it creating jobs and new opportunities, especially given the innovative nature of the U.S. population,” Bluethmann concluded. “For NASA, the idea is to look for inventive ideas for new robots that will make things better for what we’re doing in space, as well as back here on Earth.”