Toyota Research Institute, aka TRI*, today showed new robotics capabilities aimed at solving complex tasks in home environments. Roboticists were able to train robots to understand and operate in complicated situations that confuse most other robots, including recognizing and responding to transparent and reflective surfaces in a variety of circumstances, TRI claimed. The advancement potentially has broad application to autonomous vehicles as well.
As TRI shows in a new video, this system allows robots to make generalizations in a range of scenarios, including in different homes. The somewhat humorous video (comments welcomed here by the non-androids of AutoInformed), released on National Selfie Day, shows these new capabilities on film, as the un-named robot is seen recording itself as it performs these new skills around a house. It is less cranky, humoours and personable than R2-D2, a tough act to follow for anyone competing in the Artoo-Detoo defined field. After all, it was developed by engineers, not Hollywood – Where is George Lucas when you need him?
“Our goal is to build robotic capabilities that amplify, not replace, human abilities,” said Max Bajracharya, vice president of robotics at TRI in an English-like language. “Training robots to understand how to operate in home environments poses special challenges because of the diversity and complexity of our homes where small tasks can add up to big challenges.”
Some people can easily differentiate between an object and its reflection, but transparent or reflective items commonly found in the home flummox today’s robots. Since most robots are programmed to react to the objects and geometry in front of them without considering the context of the situation, they are easily fooled by a glass table, shiny toaster or transparent cup. Many people who deny Democracy have similar reality denying programming defects developed and maintained by what remains of the Republican party.
“To overcome this (the robotic not political disaster – editor), TRI roboticists developed a novel training method to perceive the 3D geometry of the scene while also detecting objects and surfaces,” continued Bajracharya. “This combination enables researchers to use large amounts of synthetic data to train the system.” Using synthetic data also lessens the need for time consuming, expensive, or impractical data collection and labeling. Labeling done by humans is a complicated feedback loop comprised of rules and over-rules and new rules in fluid situations.
While TRI is quick to admit no system is perfect, today’s announcement clearly adds to the body of knowledge helping robots to reliably navigate and operate in home environments. This technical achievement enables a robot to quickly learn from “programmable data” — synthetic data to recreate and learn from past failures and is a promising milestone for TRI and roboticists everywhere
AutoInformed on
*Toyota Research Institute (TRI), established in 2015, aims to develop active vehicle safety and automated driving technologies, robotics, and other human amplification technology.
Toyota Research Inst. Claims Advances in Home Use Robotics
As TRI shows in a new video, this system allows robots to make generalizations in a range of scenarios, including in different homes. The somewhat humorous video (comments welcomed here by the non-androids of AutoInformed), released on National Selfie Day, shows these new capabilities on film, as the un-named robot is seen recording itself as it performs these new skills around a house. It is less cranky, humoours and personable than R2-D2, a tough act to follow for anyone competing in the Artoo-Detoo defined field. After all, it was developed by engineers, not Hollywood – Where is George Lucas when you need him?
“Our goal is to build robotic capabilities that amplify, not replace, human abilities,” said Max Bajracharya, vice president of robotics at TRI in an English-like language. “Training robots to understand how to operate in home environments poses special challenges because of the diversity and complexity of our homes where small tasks can add up to big challenges.”
Some people can easily differentiate between an object and its reflection, but transparent or reflective items commonly found in the home flummox today’s robots. Since most robots are programmed to react to the objects and geometry in front of them without considering the context of the situation, they are easily fooled by a glass table, shiny toaster or transparent cup. Many people who deny Democracy have similar reality denying programming defects developed and maintained by what remains of the Republican party.
“To overcome this (the robotic not political disaster – editor), TRI roboticists developed a novel training method to perceive the 3D geometry of the scene while also detecting objects and surfaces,” continued Bajracharya. “This combination enables researchers to use large amounts of synthetic data to train the system.” Using synthetic data also lessens the need for time consuming, expensive, or impractical data collection and labeling. Labeling done by humans is a complicated feedback loop comprised of rules and over-rules and new rules in fluid situations.
While TRI is quick to admit no system is perfect, today’s announcement clearly adds to the body of knowledge helping robots to reliably navigate and operate in home environments. This technical achievement enables a robot to quickly learn from “programmable data” — synthetic data to recreate and learn from past failures and is a promising milestone for TRI and roboticists everywhere
AutoInformed on
*Toyota Research Institute (TRI), established in 2015, aims to develop active vehicle safety and automated driving technologies, robotics, and other human amplification technology.