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.

NVIDIA Robot 560

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.

Nvidia 560

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

  • 50,000 smaller Ontario manufacturers miss out on the 17 per-cent cut to electricity bills
  • Some industry support for new water heater regulations
  • Nexen Energy Expansion Announced
  • Demand for industrial real estate soaring in Canada: report
  • Entire airframe of this V-shaped flying wing houses passengers and cargo resulting in 20 percent fuel savings
  • Top seven pieces of exciting new tech that will soon become mainstream
  • Space X Falcon Heavy launch live! 'Great rocket launch or the best fireworks display,' says Elon Musk. Watch the launch at 3pm today live on EDI Weekly
  • Industrial chemicals producers report second-most profitable year
  • Record car sales reported in Canada, US for October
  • MRO continuing its rebound after Aveos collapse
  • Ontario to lose Toyota Corolla production but gain . . . ?
  • Solar power companies report growth
  • Deep Roads — researchers propose taking road expansion underground to reduce congestion and pollution
  • Manufacturing continues to grow but exports decline, increasing Canada's trade deficit in February
  • Hypersonic Jet Engine That Can Go 16 Times the Speed of Sound
  • Manufacturing sales up in December but down for the year on weak energy sector
  • Oil train disaster plays to the pro-pipeline position
  • Pilot project will use algae to recycle industrial CO2 emissions
  • First new Canadian refinery in 30 years now on track for 2017
  • Toyota celebrating 50 years in Canada with Special Edition Corolla S
Scroll to Top