NVIDIA Researchers Attempt to Train Robot

A team of researchers with NVIDIA, led by Stan Birchfield and Jonathan Tremblay, have taken it upon themselves to teach a robot to complete tasks through machine learning. The experiment attempts to teach the robot by programming it to observe human interactions and movements to “learn” how to perform the same actions itself. The tactic was tested in real world circumstances that including having a Baxter robot stack colored cubes. The findings were published in a report titled Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations.

The experiment is intended to gauge how humans may work alongside robots, as well as how safely and efficiently they can do so. “In order for robots to perform useful tasks in real-world settings, it must be easy to communicate the task to the robot; this includes both the desired end result and any hints as to the best means to achieve that result,” said the team of six authors in their report.

To test their technique, a camera was set up to provide a live video feed of a simulated scene where objects’ positions and relationships were inferred in real time by a pair of neural networks. The camera recorded a person performing a series of actions and fed that information to another network. This second network then mapped out a plan for re-creating those relationships and movements. A final, execution network read the plan and generated actions for the robot. Amazingly, the robot was able to learn the task through a single demonstration.

“Industrial robots are typically all about repeating a well-defined task over and over again,” said Frederic Lardinois of TechCrunch. “Usually, that means performing those tasks a safe distance away from the fragile humans that programmed them. More and more, however, researchers are now thinking about how robots and humans can work in close proximity to humans and even learn from them.”

According to Birchfield, the researchers wanted to simplify robot training so that it could be accomplished by experts and novices alike. The researchers used mostly synthetic data from a simulated environment, which allowed them to quickly train the robots. “We think using simulation is a powerful paradigm going forward to train robots to do things that weren’t possible before,” he said.

According to NVIDIA’s Senior Director of Robotics Research, Dieter Fox, the goal of the team was to enable the next generation of robots to work in close proximity to humans while maintaining safety. This research and others will go a long way in teaching robots to aid and assist humans in any number of situations, whether at work or at home. The team will now work toward increasing the range of tasks which can be learned and performed by the robot, while also expanding the vocabulary necessary to describe those tasks.

 

Did you miss this?

Other Popular Stories

  • Mexican oil and gas re-opened to foreign companies after 76 years
  • Canadian high school student wins top prize at Intel International Science Fair
  • Silicon Valley North: Canada aims to rival Silicon Valley due to better access to highly skilled workers on expedited visas
  • Manufacturing sector continued to gain in November
  • Chinese market for water pumps expected to triple by 2017
  • Nanotechnology can help clean up oil spills with super-absorbant carbon nanotube sponges
  • Agreement between western provinces smooths way for pipelines
  • Moon Race 2: Nasa plans moon lander for 2024; Orion Spacecraft already complete
  • Bombardier CSeries finally flies the skies of Paris
  • TransCanada will use railroads if Keystone pipeline not approved
  • Stratasys unveils first multi-resin colour 3D printer
  • India interested in oil and gas as well as uranium from Canada
  • A startup to bring Wifi to the moon — the age of the new Lunar economy
  • Car Tech Trends from CES 2018
  • Hyundai Plans to Sell Millions of BEVs
  • Breakthrough wearable Virtual Reality body suits and gloves allow you to feel objects in virtual Reality — Applications in industry, medicine, safety
  • Canada should ease foreign ownership rules for uranium, says Sask premier
  • One sweet ride: a biodegradable auto made of sugar beets and flax — but what about mice?
  • Alberta to allow increased production of 25,000 barrels of oil per day in April; eases mandatory production cuts
  • Grid-scale electricity storage solution from New York startup
Scroll to Top