Legged robots have enormous potential in their range of capabilities, from navigating unstructured terrains to high-speed running. However, designing robust controllers for highly agile dynamic motions remains a substantial challenge for roboticists. Reinforcement learning (RL) offers a promising data-driven approach for automatically training such controllers. However, exploration in these high-dimensional, underactuated systems remains a significant hurdle for enabling legged robots to learn performant, naturalistic, and versatile agility skills. We propose a framework for training complex robotic skills by transferring experience from existing controllers to jumpstart learning new tasks. To leverage controllers we can acquire in practice, we design this framework to be flexible in terms of their source -- that is, the controllers may have been optimized for a different objective under different dynamics, or may require different knowledge of the surroundings -- and thus may be highly suboptimal for the target task. We show that our method enables learning complex agile jumping behaviors, navigating to goal locations while walking on hind legs, and adapting to new environments. We also demonstrate that the agile behaviors learned in this way are graceful and safe enough to deploy in the real world.

The 41-year-old host and TV personality recently told Fox News, she's ready for a new challenge and the ABC reality competition series was the perfect fit. EXCLUSIVE: Jeannie Mai is ready to twirl across the ballroom floor on the upcoming season of "Dancing with the Stars." The 41-year-old host and TV personality recently told Fox News she's ready for a new challenge and the ABC reality competition series was the perfect fit. "I'm being thrown across the dance floor, which was my request, by the way," she joked. "And I also want to twirl underneath legs!" Mai said joining the cast for Season 29 was like crossing something off her wish list but, more importantly: "I want to just reconnect with people," she said.

Robots can (usually) walk or roll around just fine, but hand control has often proven elusive: it's hard to give them the same kind of finger dexterity as a human. However, University of Washington researchers just got much closer to fulfilling that dream. They've built a robot hand that is not only dextrous enough to spin objects (such as the tube of coffee beans you see above), but learns how to do this on its own. Its algorithm gradually discovers what works and what doesn't -- give it enough time and it'll go from clumsy to reasonably skilled.

Watching 3D films is already an immersive experience but a new projector promises to make it more of a physical activity too. XGIMI's Z4 Aurora projector features sensors that detect movement, allowing users to turn up the volume with a twirl of a finger or skip forward or backwards with the wave of a hand. The device features built-in Harman Kardon speakers to produce stereo quality sound and can stream movies sent to it from your phone or laptop using AirPlay and Miracast. The Z4 Aurora (pictured) claims to be the world's first gesture-controlled projector with a built in stereo. China-based XGIMI has designed the projector so it looks more like a turntable, meaning it can blend in more easily in the average living room.