Author: Adam Conner-Simons | Rachel Gordon | CSAIL<\/p>\n
For many people, household chores are a dreaded, inescapable part of life that we often put off or do with little care. But what if a robot assistant could help lighten the load?<\/p>\n
Recently, computer scientists have been working on teaching machines to do a wider range of tasks around the house<\/a>. In a new paper spearheaded by MIT\u2019s Computer Science and Artificial Intelligence Laboratory (CSAIL) and the University of Toronto, researchers demonstrate \u201cVirtualHome,\u201d a system that can simulate detailed household tasks and then have artificial \u201cagents\u201d execute them, opening up the possibility of one day teaching robots to do such tasks.<\/p>\n The team trained the system using nearly 3,000 programs of various activities, which are further broken down into subtasks for the computer to understand. A simple task like \u201cmaking coffee,\u201d for example, would also include the step \u201cgrabbing a cup.\u201d The researchers demonstrated VirtualHome in a 3-D world inspired by the Sims video game.<\/p>\n The team\u2019s artificial agent can execute 1,000 of these interactions in the Sims-style world, with eight different scenes including a living room, kitchen, dining room, bedroom, and home office.<\/p>\n \u201cDescribing actions as computer programs has the advantage of providing clear and unambiguous descriptions of all the steps needed to complete a task,\u201d says MIT PhD student Xavier Puig, who was lead author on the paper. \u201cThese programs can instruct a robot or a virtual character, and can also be used as a representation for complex tasks with simpler actions.\u201d<\/p>\n The project was co-developed by CSAIL and the University of Toronto alongside researchers from McGill University and the University of Ljubljana. It will be presented at the Computer Vision and Pattern Recognition (CVPR) conference, which takes place this month in Salt Lake City.<\/p>\n Unlike humans, robots need more explicit instructions to complete easy tasks; they can\u2019t just infer and reason with ease.<\/p>\n For example, one might tell a human to \u201cswitch on the TV and watch it from the sofa.\u201d Here, actions like \u201cgrab the remote control\u201d and \u201csit\/lie on sofa\u201d have been omitted, since they\u2019re part of the commonsense knowledge that humans have.<\/p>\n To better demonstrate these kinds of tasks to robots, the descriptions for actions needed to be much more detailed. To do so, the team first collected verbal descriptions of household activities, and then translated them into simple code. A program like this might include steps like: walk to the television, switch on the television, walk to the sofa, sit on the sofa, and watch television.<\/p>\n Once the programs were created, the team fed them to the VirtualHome 3-D simulator to be turned into videos. Then, a virtual agent would execute the tasks defined by the programs, whether it was watching television, placing a pot on the stove, or turning a toaster on and off.<\/p>\n The end result is not just a system for training robots to do chores, but also a large database of household tasks described using natural language. <\/em>Companies like Amazon that are working to develop Alexa-like robotic systems at home could eventually use data like these to train their models to do more complex tasks.<\/p>\n The team\u2019s model successfully demonstrated that their agents could learn to reconstruct a program, and therefore perform a task, given either a description: \u201cpour milk into glass\u201d or a video demonstration of the activity.<\/p>\n \u201cThis line of work could facilitate true robotic personal assistants in the future,\u201d says Qiao Wang, a research assistant in arts, media, and engineering at Arizona State University. \u201cInstead of each task programmed by the manufacturer, the robot can learn tasks just by listening to or watching the specific person it accompanies. This allows the robot to do tasks in a personalized way, or even some day invoke an emotional connection as a result of this personalized learning process.\u201d<\/p>\n In the future, the team hopes to train the robots using actual videos instead of Sims-style simulation videos, which would enable a robot to learn simply by watching a YouTube video. The team is also working on implementing a reward-learning system in which the agent gets positive feedback when it does tasks correctly.<\/p>\n \u201cYou can imagine a setting where robots are assisting with chores at home and can eventually anticipate personalized wants and needs, or impending action,\u201d says Puig. \u201cThis could be especially helpful as an assistive technology for the elderly, or those who may have limited mobility.\u201d<\/p>\n<\/div>\n Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"