Toyota Research Institute researchers today released a video summarizing the latest research around the problems of robot manipulation, and its challenges towards making human-assisting robots more reliable and robust. In the video, you can see how a robot arm is able to identify objects in a bin and place them correctly into a dishwasher.
Russ Tedrake, Ph.D., the vice president of Robotics Research at TRI, presented at the Robotics: Science and Systems conference this week, discussing how the company is working on getting closer on developing a robot that can help the elderly live a better life by helping them with tasks in the home.
Russ Tedrake, Toyota Research Institute
“Decades of prognostications about the future – largely driven by science-fiction novels and popular entertainment – have encouraged public expectations that someday home robots will happen,” said Tedrake in a contributed blog post. “Companies have been trying for years to deliver on such forecasts and figure out how to safely introduce ever more capable robots into the unstructured home environment.
“Despite this age of tremendous technological process, the robots we see in homes to date are primarily vacuum cleaners and toys. Most people don’t realize how far today’s best robots are from being able to do basic household tasks. When they see heavy use of robot arms in factories or impressive videos on YouTube showing what a robot can do, they might reasonably expect these robots could be used in the home now.”
Tedrake explained that a major barrier for researchers is unsolved problems in manipulation that prevent reliability. “Unlike the sterile, controlled and programmable environment of the factory, the home is a ‘wild west’ – unstructured and diverse,” Tedrake said. “Despite recent strides in artificial intelligence and machine learning, it is still very hard to engineer a system that can deal with the complexity of a home environment and guarantee that it will (almost) work correctly.”
With the dishwashing video, Tedrake said it was created to not design a robot that loads a dishwasher, but rather use the task as a means to develop the tools and algorithms that can then be applied for different applications. “Our focus is not on hardware, which is why we are using a factory robot arm in this demonstration rather than designing one that would be more appropriate for the home kitchen.”
He also said the company is utilizing simulation, which gives the company a way to engineer and test systems of this complexity with diversity, machine learning, and AI components. “An exciting achievement is that we have made great strides in making simulation robust enough to handle the visual and mechanical complexity of this dishwasher loading task and closing the ‘sim to real’ gap,” Tedrake said. “At long last, we have reached a point where we do nearly all of our development in simulation, which has traditionally not been the case for robotic manipulation research.”
More details on the development of the video and TRI’s research is available here.
