Meet CoBot—short for "Collaborative Robot." You might call it "help on wheels." With support from the National Science Foundation (NSF), computer scientist Manuela Veloso and her team at Carnegie Mellon University (CMU) are developing CoBots, autonomous indoor service robots to interact with people and provide help "on the go."
Getting on a CoBot's dance card is simple: log on to a website, select a task, book a time slot—and CoBot is on the job. If one CoBot is too busy, then another will carry out the request. CoBots can transport objects, deliver messages, escort people and go to places, continuously executing these tasks over multiple weeks in a multi-floor building. The robustness of the mobile robot's localization and navigation has permitted it to travel non-accompanied for hundreds of kilometers in a building.
CoBots are able to plan their paths and smoothly navigate autonomously. They monitor the walls, calculate planar surfaces, and plot window and door locations—all while avoiding dynamic obstacles and even making notes about things like where the carpet and hardwood floor meet. Aware of their limitations, CoBots also proactively ask for help from the web or from humans for locations and for assistance with tasks that they cannot do, such as pressing elevator buttons and picking up objects to be carried.
Explore further: New 'deep learning' technique enables robot mastery of skills via trial and error