Researchers at the Massachusetts Institute of Technology (MIT) have developed a robotic navigation method that does not require mapping an area in advance. The approach enables a robot to use clues in its environment to plan out a route to its destination, which can be described in general semantic terms.
The technique can greatly reduce the time a robot spends exploring a property before identifying its target, and it does not rely on maps of specific residences. The team used an algorithm—called Simultaneous Localization and Mapping (SLAM)—to build up a map of the environment as the robot moved around, using the semantic labels of each object and a depth image.
The researchers also developed a "cost-to-go estimator," an algorithm that converts the semantic map into a second map representing the likelihood of any given location being close to the goal.
From MIT News
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA