In the future robots may be dispatched as last-mile delivery vehicles if only they could find the front door. Autonomous vehicles and robots could share sensor data to get better navigation of the world around them.

MIT engineers have approaches for robotics using algorithms to guide a robot toward a specific goal or GPS coordinate on the map. Now engineers of MIT have developed a separate navigation method that doesn’t require mapping an area in advance. For example, if the robot is instructed to deliver a package to someone’s front door, it will start on the road and see a driveway, as trained to recognize the lead toward a sidewalk, which in turn is likely to lead to the front door.

“We wouldn’t want to have to make a map of every building that we’d need to visit,” says Michael Everett, a graduate student in MIT’s Department of Mechanical Engineering.

The MIT researchers used an algorithm to build up a map of the environment as the robot moved around, using the semantic labels of each object and a depth image. This algorithm is called semantic SLAM.

Though such a task can be difficult to scale to an entire city, particularly as the exteriors of houses often change with the seasons the researchers are optimist enough that with this technique they would be able to find the front door.