Autonomous robots performing a joint task send each other continual updates: “I’ve passed through a door and am turning 90 degrees right.” “After advancing 2 feet I’ve encountered a wall. I’m turning 90 degrees right.” “After advancing 4 feet I’ve encountered a wall.”
Computers, of course, have no trouble filing this information away until they need it. But such a barrage of data would drive a human crazy.
Put that aside, because there is now a new way of modeling robot collaboration that reduces the need for communication by 60 percent. Researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) could make it easier to design systems that enable humans and robots to work together in things like emergency-response teams.
“We haven’t implemented it yet in human-robot teams,” said Julie Shah, an associate professor of aeronautics and astronautics and one of two authors of a paper on the subject. “But it’s very exciting, because you can imagine: You’ve just reduced the number of communications by 60 percent, and presumably those other communications weren’t really necessary toward the person achieving their part of the task in that team.”
The work could also have implications for multi-robot collaborations that don’t involve humans. Communication consumes some power, which is always a consideration in battery-powered devices, but in some circumstances, the cost of processing new information could be a much more severe resource drain.
In a multi-agent system each agent must maintain a model of the current state of the world, as well as a model of what each of the other agents takes to be the state of the world. These days, agents are also expected to factor in the probabilities their models are accurate. On the basis of those probabilities, they have to decide whether or not to modify their behaviors.
The Cost of Communications
In some scenarios, a robot’s decision to broadcast a new item of information could force its fellows to update their models and churn through all those probabilities again. If the information is not essential, broadcasting it could introduce serious delays, to no purpose. And the MIT researchers’ work suggests that 60 percent of communications in multi-agent systems may be inessential.
The state-of-the-art method for modeling multi-agent systems is decentralized partially observable Markov decision process, or Dec-POMDP.
A Dec-POMDP factors in several types of uncertainty; not only does it consider whether an agent’s view of the world is correct and whether its estimate of its fellows’ worldviews is correct, it also considers whether any action it takes will be successful. The robot may plan, for instance, to move forward 20 feet but find that crosswinds blow it off course.
Dec-POMDPs generally assume some prior knowledge about the environment in which the agents will be operating. Because Shah and Vaibhav Unhelkar, a graduate student in aeronautics and astronautics and first author on the new paper, were designing a system with emergency-response applications in mind, they couldn’t make that assumption. Emergency-response teams will usually be entering unfamiliar environments, and the very nature of the emergency could render the best prior information obsolete.
Adding the requirement of mapping the environment on the fly, however, makes the problem of computing a multi-agent plan prohibitively time consuming. So Shah and Unhelkar’s system ignores uncertainty about actions’ effectiveness and assumes that whatever an agent attempts to do, it will do.
Cost Benefit Analysis
When an agent acquires a new item of information it has three choices: It can ignore the information; it can use it but not broadcast it; or it can use it and broadcast it.
Each of these choices has benefits but imposes costs. In Shah and Unhelkar’s model, communication is a cost. But if an agent incorporates new information into its own model of the world and doesn’t broadcast it, it also incurs a cost, as its worldview becomes more difficult for its fellows to estimate correctly. For every new item of information an agent acquires, Shah and Unhelkar’s system performs that cost-benefit analysis, based on the agent’s model of the world, its expectations of its fellows’ actions, and the likelihood of accomplishing the joint goal more efficiently.
The researchers tested their system on more than 300 computer simulations of rescue tasks in unfamiliar environments. A version of their system that permitted extensive communication completed the tasks at a rate between 2 and 10 percent higher than the version that reduced communication by 60 percent.
In the experiments, however, all the agents were electronic.
“What I’d be willing to bet, although we have to wait until we do the human-subject experiments, is that the human-robot team will fail miserably if the system is just telling the person all sorts of spurious information all the time,” Shah said. “For human-robot teams, I think that this algorithm is going to make the difference between a team that can function effectively versus a team that just plain can’t.”