This socially-aware robot knows the rules of pedestrian conduct

The 'rules of the road' are well known, but lesser known are the 'rules of the pavement'. Pedestrians also have a code of common behaviours that they tend to stick to, particularly when in crowded areas.

Those rules, which differ in different parts of the world, may include commandments like: Keep to the right, pass on the left, keep a respectable distance from other pedestrians, and be ready to change course to avoid oncoming obstacles.

For robots, these rules are mainly a mystery, but now engineers at MIT have taught a bot to observe them - allowing it to keep pace with foot traffic in crowded corridors while still avoiding collisions.

Frequent Interactions

“Socially aware navigation is a central capability for mobile robots operating in environments that require frequent interactions with pedestrians,” said Yu Fan “Steven” Chen, lead author of a paper describing the technology published on the pre-print arXiv server. 

“For instance, small robots could operate on sidewalks for package and food delivery. Similarly, personal mobility devices could transport people in large, crowded spaces, such as shopping malls, airports, and hospitals.”

Their robot, which looks like a knee-high kiosk on wheels, learnt to adapt to unpredictable human behaviour while still moving with the flow of traffic. In tests, it was able to successfully navigate MIT's busy Stata Center for periods of 20 minutes at a time without bumping into passers-by.

“We want it to be traveling naturally among people and not be intrusive,” said Michael Everett, who also worked on the project. “We want it to be following the same rules as everyone else."

Three's a crowd

The next step is to explore how a robot might handle crowds. “Crowds have a different dynamic than individual people, and you may have to learn something totally different if you see five people walking together,” Everett says. 

“There may be a social rule of, ‘Don’t move through people, don’t split people up, treat them as one mass.’ That’s something we’re looking at in the future.”