Scientists: Robots can learn to learn from crowdsourcing – Daily Digest

University of Washington computer scientists have shown that crowdsourcing can be a quick and effective way to teach a robot how to complete tasks. The team designed a study that taps into the online crowdsourcing community to teach a robot a model-building task. To begin, study participants built a simple model – a car, tree, turtle and snake, among others – out of colored Lego blocks. Then, they asked the robot to build a similar object. But based on the few examples provided by the participants, the robot was unable to build complete models.

To gather more input about building the objects, the robots turned to the crowd. They hired people on Amazon Mechanical Turk, a crowdsourcing site, to build similar models of a car, tree, turtle, snake and others. From more than 100 crowd-generated models of each shape, the robot searched for the best models to build based on difficulty to construct, similarity to the original and the online community’s ratings of the models. The robot then built the best models of each participant’s shape.

This type of learning is called “goal-based imitation,” and it leverages the growing ability of robots to infer what their human operators want, relying on the robot to come up with the best possible way of achieving the goal when considering factors such as time and difficulty. For example, a robot might “watch” a human building a turtle model, infer the important qualities to carry over, then build a model that resembles the original, but is perhaps simpler so it’s easier for the robot to construct.

Goal-based imitation instilled in robots allows the machines to learn like a human child does, only better. By examining surroundings and equating actions with reactions, and as a constant panopticon to the world, a robot will be able to process, compute, and store thousands of learning scenarios within its database in a shorter time and higher retention rate than any human could.

The team applied the same idea to learning manipulation actions on a two-armed robot. This time, users physically demonstrated new actions to the robot. Then, the robot imagined new scenarios in which it did not know how to perform those actions. Using abstract, interactive visualizations of the action, it asked the crowd to provide new ways of performing actions in those new scenarios. The results are be presented at the Conference on Human Computation and Crowdsourcing in November.

The UW team is now looking at using crowdsourcing and community-sourcing to teach robots more complex tasks such as finding and fetching items in a multi-floor building. The researchers envision a future in which personal robots will engage increasingly with humans virtually, learning new skills and tasks to better assist humans in reality.

If implemented properly, robots utilizing goal-based imitation software could potentially learn and accrue vast quantities of knowledge and information on its database within hours or even minutes. As artificial intelligence surpasses the bounds of human capacity, robots can begin to learn at an exponential rate. In a short order, a robot could evolve from a rudimentary design imitator to an exquisite artist restricted only by the bounds of its imagination database.

Have something to say? Let us know in the comments section or send an email to the author. You can share ideas for stories by contacting us here.

Scientists: Robots can learn to learn from crowdsourcing – Daily Digest

Leave a Reply

Your email address will not be published. Required fields are marked *