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

  • How Greener Grids Can Stay Lit
  • Rapid growth of solar power a challenge for utilities
  • Canada should ease foreign ownership rules for uranium, says Sask premier
  • Irving Shipbuilding wins $2.3 billion icebreaker contract with navy
  • Alberta to allow increased production of 25,000 barrels of oil per day in April; eases mandatory production cuts
  • Tesla is now the number one valued carmaker in America, jumping ahead of GM
  • Oil drags capital spending down, though some bright spots remain: Statistics Canada
  • 3D printed hempcrete could revolutionize construction industry
  • Giant wind-solar development announces SMA Canada for O&M
  • Cascade Aerospace named a Hercules heavy maintenance centre
  • Artificial pancreas would reduce need for self-care by diabetics, improve insulin delivery
  • High speed rail finally coming to Toronto-Windsor corridor? What will Ontario high speed look like?
  • Wave energy farm in Scotland to use Oysters
  • Electricity-conducting cement could make runways, roads ice proof
  • Strong auto exports highlight industry's importance, vulnerability to TPP
  • Breakthrough wearable Virtual Reality body suits and gloves allow you to feel objects in virtual Reality — Applications in industry, medicine, safety
  • Armoured vehicles an important niche in Ontario's auto industry
  • Canada's oil sands dispute with EU flares
  • Elon Musk's Hyperloop vision racing ahead of naysayers and regulators — Boring Company receives permission to tunnel 10 miles; early tests of tube successful
  • Bombardier to build 170 high-speed rail cars for Siemens
Scroll to Top