Robots don’t do well in crowds. Their ability to sense and avoid objects is fairly well developed. Even a Roomba can slow down as it approaches a wall or a couch. What robots can’t do—yet—is navigate a busy space like a confident pedestrian. A robot can’t consistently and accurately gauge an approaching pedestrian’s likely next move, or the social etiquette of who should pass first. In other words, robots are really awkward. A Stanford University team of computer scientists is working to overcome artificial intelligence’s lack of social intelligence. They’ve created the Jackrabbot, a one-meter-high robot that can travel up to five miles per hour and, incidentally, looks adorable in a hat and tie. Equipped with motion sensors and software that utilizes an algorithm based on hours of aerial video footage of busy sidewalks, Jackrabbot goes on regular expeditions through Stanford’s busy campus making on-the-fly judgments about right-of-way and personal space. Since its March 2015 debut, the robot has made several dozen outings to test its software. “It’s one thing to detect pedestrians, but it’s another thing to understand how you should cooperate with them [and] negotiate social interaction,” says Alexandre Alahi, a research associate in Stanford’s Computational Vision and Geometry Lab. “It’s being able to develop systems that can make decisions with respect to human behavior, and be able to read human behavior in the same way that we humans do.” Alahi and his colleagues see applications for Jackrabbot’s software in everything from self-driving cars to robot caregivers. When computer-driven cars are sharing the road with people-piloted ones, they’ll need to understand the informal etiquette that human drivers follow, and the cultural differences that make driving in Rome a different experience from driving in Boston. With enough data, robots could tweak their movements to respond to local customs and social norms. Robots may eventually take your job, but at least they’ll respect your personal space when they do it.