If a cleaning robot tries dirty tricks

GOOGLE can see a future where robots help us unload the dishwasher and sweep the floor.

The challenge is making sure they don’t knock over a vase — or worse — while doing so.

Researchers at Alphabet, a unit of Google, with collaborators at Stanford University, the University of California at Berkeley, and OpenAI — an artificial intelligence development company backed by Elon Musk — have ideas about how to design robot minds that won’t lead to undesirable consequences for the people they serve. They published a technical paper this week outlining their thinking.

The motivation for the research is the immense popularity of artificial intelligence, software that can learn about the world and act within it. Today’s AI systems let cars drive themselves, interpret speech spoken into phones, and devise trading strategies for the stock market. In the future, companies plan to use AI as personal assistants, first as softwarebased services like Apple’s Siri and the Google Assistant, and later as smart robots that can take actions for themselves.

But before giving smart machines the ability to make decisions, people need to make sure the goals of the robots are aligned with those of their human owners.

“While possible AI safety risks have received a lot of public attention, most previous discussion has been very hypothetical and speculative,” Google researcher Chris Olah wrote in a blog post accompanying the paper.

The report describes some of the problems robot designers may face, and lists techniques for building software the machines can’t subvert. The challenge is the open-ended nature of intelligence, and the puzzle is akin to one faced by regulators in other areas, like the financial system; how do you design rules to let entities achieve their goals in a system you regulate, without being able to subvert your rules, or be unnecessarily constricted by them?

For example, if you have a cleaning robot (and OpenAI aims to build such a machine), how do you make sure your rewards don’t give it an incentive to cheat, the researchers wonder. Reward it for cleaning a room and it might respond by sweeping dirt under the rug so it’s out of sight, or it might learn to turn off its cameras, preventing it from seeing any mess, and thereby giving it a reward. Counter these tactics by giving it an additional reward for using cleaning products and it might evolve into a system that uses bleach too liberally because it’s rewarded for doing so.

While cheating with housework may not seem to be a critical problem, the researchers are extrapolating to potential future uses where stakes are higher.

Some solutions the researchers propose include limiting how much control the AI system has over its environment, so as to contain the damage, and pairing a robot with a human buddy. Other ideas include programming “trip wires” in the AI machine to give humans a warning if it steps out of its routine.

The idea of smart machines going haywire is hardly new: Goethe wrote a poem in the 18th century in which a sorcerer’s apprentice creates a living broom to fetch water. The broom is so good at its job that it almost floods the house, so the sorcerer chops it up with an axe. New brooms emerge from the fragments and continue their tasks. — Bloomberg

Make sure the robots’ goals are aligned with those of their human owners