Video: Decentralized control of multiple robots under uncertainty

Feb 12, 2014 by Larry Hardesty

Writing a program to control a single autonomous robot navigating an uncertain environment with an erratic communication link is hard enough; write one for multiple robots that may or may not have to work in tandem, depending on the task, is even harder.

As a consequence, engineers designing control programs for "multiagent systems"—whether teams of robots or networks of devices with different functions—have generally restricted themselves to special cases, where reliable information about the environment can be assumed or a relatively simple collaborative task can be clearly specified in advance.

This May, at the International Conference on Autonomous Agents and Multiagent Systems, researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) will present a new system that stitches existing control programs together to allow multiagent systems to collaborate in much more complex ways. The system factors in uncertainty—the odds, for instance, that a communication link will drop, or that a particular algorithm will inadvertently steer a robot into a dead end—and automatically plans around it.

For small collaborative tasks, the system can guarantee that its combination of programs is optimal—that it will yield the best possible results, given the uncertainty of the environment and the limitations of the programs themselves.

Working together with Jon How, the Richard Cockburn Maclaurin Professor of Aeronautics and Astronautics, and his student Chris Maynor, the researchers are currently testing their system in a simulation of a warehousing application, where teams of robots would be required to retrieve arbitrary objects from indeterminate locations, collaborating as needed to transport heavy loads. The simulations involve small groups of iRobot Creates, programmable robots that have the same chassis as the Roomba vacuum cleaner.

This video is not supported by your browser at this time.
Planning for Decentralized Control of Multiple Robots Under Uncertainty

Reasonable doubt

"In [multiagent] systems, in general, in the real world, it's very hard for them to communicate effectively," says Christopher Amato, a postdoc in CSAIL and first author on the new paper. "If you have a camera, it's impossible for the camera to be constantly streaming all of its information to all the other cameras. Similarly, robots are on networks that are imperfect, so it takes some amount of time to get messages to other robots, and maybe they can't communicate in certain situations around obstacles."

An agent may not even have perfect information about its own location, Amato says—which aisle of the warehouse it's actually in, for instance. Moreover, "When you try to make a decision, there's some uncertainty about how that's going to unfold," he says. "Maybe you try to move in a certain direction, and there's wind or wheel slippage, or there's uncertainty across networks due to packet loss. So in these real-world domains with all this communication noise and about what's happening, it's hard to make decisions."

The new MIT system, which Amato developed with co-authors Leslie Kaelbling, the Panasonic Professor of Computer Science and Engineering, and George Konidaris, a fellow postdoc, takes three inputs. One is a set of low-level control algorithms—which the MIT researchers refer to as "macro-actions"—which may govern agents' behaviors collectively or individually. The second is a set of statistics about those programs' execution in a particular environment. And the third is a scheme for valuing different outcomes: Accomplishing a task accrues a high positive valuation, but consuming energy accrues a negative valuation.

School of hard knocks

Amato envisions that the statistics could be gathered automatically, by simply letting a multiagent system run for a while—whether in the or in simulations. In the warehousing application, for instance, the robots would be left to execute various macro-actions, and the system would collect data on results. Robots trying to move from point A to point B within the warehouse might end up down a blind alley some percentage of the time, and their communication bandwidth might drop some other percentage of the time; those percentages might vary for robots moving from point B to point C.

The MIT system takes these inputs and then decides how best to combine macro-actions to maximize the system's value function. It might use all the macro-actions; it might use only a tiny subset. And it might use them in ways that a human designer wouldn't have thought of.

Suppose, for instance, that each has a small bank of colored lights that it can use to communicate with its counterparts if their wireless links are down. "What typically happens is, the programmer decides that red light means go to this room and help somebody, green light means go to that room and help somebody," Amato says. "In our case, we can just say that there are three lights, and the algorithm spits out whether or not to use them and what each color means."

The MIT researchers' work frames the problem of multiagent control as something called a partially observable Markov decision process, or POMDP. "POMDPs, and especially Dec-POMDPs, which are the decentralized version, are basically intractable for real multirobot problems because they're so complex and computationally expensive to solve that they just explode when you increase the number of robots," says Nora Ayanian, an assistant professor of computer science at the University of Southern California who specializes in multirobot systems. "So they're not really very popular in the multirobot world."

"Normally, when you're using these Dec-POMDPs, you work at a very low level of granularity," she explains. "The interesting thing about this paper is that they take these very complex tools and kind of decrease the resolution."

"This will definitely get these POMDPs on the radar of multirobot-systems people," Ayanian adds. "It's something that really makes it way more capable to be applied to complex problems."

Explore further: Robots learn from each other on 'Wiki for robots'

More information: PAPER: "Planning with Macro-Actions in Decentralized POMDPs" people.csail.mit.edu/camato/publications/DecOptions-final.pdf

Related Stories

Robots learn from each other on 'Wiki for robots'

Jan 13, 2014

Now it's not just people – robots are also connected by internet thanks to RoboEarth. Next week, after four years of research, scientists at Eindhoven University of Technology (TU/e), Philips and four other ...

How computers can learn better

Jun 03, 2013

Reinforcement learning is a technique, common in computer science, in which a computer system learns how best to solve some problem through trial-and-error. Classic applications of reinforcement learning ...

Recommended for you

Simplicity is key to co-operative robots

Apr 16, 2014

A way of making hundreds—or even thousands—of tiny robots cluster to carry out tasks without using any memory or processing power has been developed by engineers at the University of Sheffield, UK.

Students turn $250 wheelchair into geo-positioning robot

Apr 16, 2014

Talk about your Craigslist finds! A team of student employees at The University of Alabama in Huntsville's Systems Management and Production Center (SMAP) combined inspiration with innovation to make a $250 ...

Using robots to study evolution

Apr 14, 2014

A new paper by OIST's Neural Computation Unit has demonstrated the usefulness of robots in studying evolution. Published in PLOS ONE, Stefan Elfwing, a researcher in Professor Kenji Doya's Unit, has succes ...

User comments : 0

More news stories

Venture investments jump to $9.5B in 1Q

Funding for U.S. startup companies soared 57 percent in the first quarter to a level not seen since 2001, as venture capitalists piled more money into an increasing number of deals, according to a report due out Friday.

Hackathon team's GoogolPlex gives Siri extra powers

(Phys.org) —Four freshmen at the University of Pennsylvania have taken Apple's personal assistant Siri to behave as a graduate-level executive assistant which, when asked, is capable of adjusting the temperature ...

White House updating online privacy policy

A new Obama administration privacy policy out Friday explains how the government will gather the user data of online visitors to WhiteHouse.gov, mobile apps and social media sites. It also clarifies that ...

Scientists tether lionfish to Cayman reefs

Research done by U.S. scientists in the Cayman Islands suggests that native predators can be trained to gobble up invasive lionfish that colonize regional reefs and voraciously prey on juvenile marine creatures.

Leeches help save woman's ear after pit bull mauling

(HealthDay)—A pit bull attack in July 2013 left a 19-year-old woman with her left ear ripped from her head, leaving an open wound. After preserving the ear, the surgical team started with a reconnection ...