Computer scientists from the University of Washington had a remarkable thing to share at the 2014 Institute of Electrical and Electronics Engineers International Conference on Robotics and Automation that was held in Hong Kong. They displayed how robots can quickly and efficiently learn from a large group of people via online community.

"We're trying to create a method for a robot to seek help from the whole world when it's puzzled by something .This is a way to go beyond just one-on-one interaction between a human and a robot by also learning from other humans around the world", said Rajesh Rao, an associate professor of computer science and engineering and director of the Center for Sensorimotor Neural Engineering at the UW.

Also this idea would prove to be a lot time-saving as a robot learning by imitating a human to perform tasks would take a lot of time. So this new crowdsourcing information from the online community concept states that the robot can learn a task's basic steps and then rely on online community for additional input. This additional input may include collection of more data on how to complete the task efficiently and correctly. This input will come from ideas from a large number of groups of people.

This research team was led by professors Rao and Cakmak, also includes UW computer science and engineering graduate student Michael Jae-Yoon Chung and undergraduate Maxwell Forbes. And, this type of learning system is called "goal-based imitation".

This "goal-based imitation" is believe to leverages the growing ability of robots to understand better as to what their human operators want and also, it would help humans rely on the robot to come up with the best possible way of achieving the desired goal considering factors such as time and difficulty.