Google Research AI Robot
The Google research team is using artificial intelligence to teach robots how to move with the agility of real-life animals, like dogs. Accomplishing this feat involved reinforcement learning (RL), where the researchers began by sourcing reference motion clips recorded from an animal and using RL to get the robot to copy those motions. Read more for a video and additional information.



One issue was accounting for the randomness that occurs in real-life, thus they had to introduce this by using physical parameters in the simulation – i.e. changing physical quantities (robot’s mass / friction, etc.). This resulted in a machine learning model that could account small variances and the resulting complications.

Sale
eufy by Anker,BoostIQ RoboVac 11S (Slim), Robot Vacuum Cleaner, Super-Thin, 1300Pa Strong Suction, Quiet, Self-Charging Robotic Vacuum Cleaner, Cleans Hard Floors to Medium-Pile Carpets
  • Included in the “Best robot vacuums of 2019” by Tom’s Guide.
  • All-New RoboVac: Re-engineered to be the slimmest* RoboVac (2.85”) but with quiet operation and increased suction at 1300Pa for up to 100 minutes** of constant, powerful suction.
  • BoostIQ Technology: Automatically increases suction power within 1.5 seconds when extra vacuuming strength is needed to get the best clean.
  • A Quiet Clean: Vacuums for up to 100 minutes** on hardwood floors with consistant, powerful suction at a volume no louder than an operating microwave. Premium Features: Anti-scratch tempered glass-top cover for protection, infrared-sensor for evading obstacles, and drop-sensing tech to avoid falls. Automatically recharges so it's always ready to clean.
  • What You Get: RoboVac 11S, remote control (2 AAA batteries included), charging base, AC power adapter, cleaning tool, extra set of high-performance filters, 4 side brushes, 5 cable ties, welcome guide and our worry-free 12-month warranty.

We show that by leveraging reference motion data, a single learning-based approach is able to automatically synthesize controllers for a diverse repertoire behaviors for legged robots. By incorporating sample efficient domain adaptation techniques into the training process, our system is able to learn adaptive policies in simulation that can then be quickly adapted for real-world deployment,” said the researchers.