Sometimes it takes a village to teach a robot.
University of Washington computer scientists have shown that crowdsourcing can be a quick and effective way to teach a robot how to complete tasks. Instead of learning from just one human, robots could one day query the larger online community, asking for instructions or input on the best way to set the table or water the garden.
The research team presented its results at the 2014 Institute of Electrical and Electronics Engineers International Conference on Robotics and Automation in Hong Kong in early June.
“We’re trying to create a method for a robot to seek help from the whole world when it’s puzzled by something,” said Rajesh Rao, an associate professor of computer science and engineering and director of the Center for Sensorimotor Neural Engineering at the UW. “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.”
Learning by imitating a human is a proven approach to teach a robot to perform tasks, but it can take a lot of time. Imagine having to teach a robot how to load the dishwasher – it might take many repetitious lessons for the robot to learn how to hold different types of cookware and cutlery and how to most efficiently fill the machine.
But if the robot could learn a task’s basic steps, then ask the online community for additional input, it could collect more data on how to complete this task efficiently and correctly.
“Because our robots use machine-learning techniques, they require a lot of data to build accurate models of the task. The more data they have, the better model they can build. Our solution is to get that data from crowdsourcing,” said Maya Cakmak, a UW assistant professor of computer science and engineering.
The research team, led by professors Rao and Cakmak, also includes UW computer science and engineering graduate student Michael Jae-Yoon Chung and undergraduate Maxwell Forbes. 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.
“The end result is still a turtle, but it’s something that is manageable for the robot and similar enough to the original model, so it achieves the same goal,” Cakmak explained.
Study participants generally preferred crowdsourced versions that looked the most like their original designs. In general, the robot’s final models were simpler than the starting designs – and it was able to successfully build these models, which wasn’t always the case when starting with the study participants’ initial designs.
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. This work will be presented at the Conference on Human Computation and Crowdsourcing in November.
Other research teams at Brown University, Worcester Polytechnic Institute and Cornell University are working on similar ideas for developing robots that have the ability to learn new capabilities through crowdsourcing.
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 our personal robots will engage increasingly with humans online, learning new skills and tasks to better assist us in everyday life.
This research was funded by the U.S. Office of Naval Research and the National Science Foundation.
Michelle Ma | Eurek Alert!
Discovery about new battery overturns decades of false assumptions
07.10.2015 | Oregon State University
New polymer creates safer fuels
02.10.2015 | California Institute of Technology
Nondestructive material testing (NDT) is a fast and effective way to analyze the quality of a product during the manufacturing process. Because defective materials can lead to malfunctioning finished products, NDT is an essential quality assurance measure, especially in the manufacture of safety-critical components such as automotive B-pillars. NDT examines the quality without damaging the component or modifying the surface of the material. At this year's Blechexpo trade fair in Stuttgart, Fraunhofer IZFP will have an exhibit that demonstrates the nondestructive testing of high-strength automotive body parts using 3MA. The measurement results are available in a matter of seconds.
To minimize vehicle weight and fuel consumption while providing the highest level of crash safety, automotive bodies are reinforced with elements made from...
The MICADO camera, a first light instrument for the European Extremely Large Telescope (E-ELT), has entered a new phase in the project: by agreeing to a Memorandum of Understanding, the partners in Germany, France, the Netherlands, Austria, and Italy, have all confirmed their participation. Following this milestone, the project's transition into its preliminary design phase was approved at a kick-off meeting held in Vienna. Two weeks earlier, on September 18, the consortium and the European Southern Observatory (ESO), which is building the telescope, have signed the corresponding collaboration agreement.
As the first dedicated camera for the E-ELT, MICADO will equip the giant telescope with a capability for diffraction-limited imaging at near-infrared...
Self-driving cars will be on our streets in the foreseeable future. In Graz, research is currently dedicated to an innovative driver assistance system that takes over control if there is a danger of collision. It was nature that inspired Dr Manfred Hartbauer from the Institute of Zoology at the University of Graz: in dangerous traffic situations, migratory locusts react around ten times faster than humans. Working together with an interdisciplinary team, Hartbauer is investigating an affordable collision detector that is equipped with artificial locust eyes and can recognise potential crashes in time, during both day and night.
Inspired by insects
An interdisciplinary team of researchers has built the first prototype of a miniature particle accelerator that uses terahertz radiation instead of radio...
At present, tiny magnetic whirls – so called skyrmions – are discussed as promising candidates for bits in future robust and compact data storage devices. At...
01.10.2015 | Event News
30.09.2015 | Event News
17.09.2015 | Event News
09.10.2015 | Earth Sciences
09.10.2015 | Life Sciences
09.10.2015 | Life Sciences