Video Friday is a weekly selection of great robotics videos curated by our friends at IEEE Spectrum Robotics. It also features a weekly calendar of robotics events for the coming months. Send us your event.
RoboCup 2024: July 17-22, 2024, Eindhoven, Netherlands
ICSR 2024: October 23-26, 2024, Odense, Denmark
CYBATHLON 2024: October 25-27, 2024, Zurich, Switzerland
Enjoy today's video!
NAVER 1784 is the world's largest robot testing ground. The Starbucks on the second floor of 1784 is the most unique Starbucks in the world, with over 100 service robots called “Rookies” that deliver Starbucks drinks to conference rooms and private rooms, as well as various experiments using dual-arm robots.
[ Naver ]
If you're going to take your robot dog hiking, you might as well have it carry your backpack.
[ Deep Robotics ]
Be aware that phrases such as “no remote control” can have different meanings without additional context.
[ Astribot ]
This video, presented at the ICRA 2024 conference, summarizes recent progress from the Learning AI for Dexterity Lab, showcasing how learning AI techniques have enabled a breakthrough in dexterity for the mobile humanoid robot DLR Agile Justin. While the core mechatronic hardware is almost 20 years old, it is only with the advent of learning AI techniques that we can achieve dexterity, flexibility, and autonomy approaching human capabilities.
[ TUM ]
Thank you, Berthold!
Blue hands? Not a good look.
[ Synaptic ]
With all the humanoid stuff coming, there should be more emphasis on intentional contact. Humans are always leaning on things for balance, and robots should do the same.
[ Inria ]
LimX Dynamics W1 is not just a quadruped robot with wheels, it has evolved into a bipedal robot that moves smoothly on two legs in various ways: 360 degree non-stop rotation, upright free gliding, smooth steering, random collision and self-recovery, step walking, and more.
[ LimX Dynamics ]
Animal brains consume less data and energy compared to current deep neural networks running on graphics processing units (GPUs). This makes it difficult to develop small, autonomous drones because they are too small and lightweight to carry heavy hardware or large batteries. Recently, the advent of neuromorphic processors that mimic the workings of the brain has enabled researchers at Delft University of Technology to develop drones that use neuromorphic vision and control for autonomous flight.
[ Science ]
The universe began in darkness, but the first organisms acquired vision, which led to an explosion of life, learning, and progress. AI pioneer Fei-Fei Li says we are approaching a similar moment for computers and robots. She shows how machines are gaining “spatial intelligence” — the ability to process visual data, make predictions, and act on those predictions — and how this will enable AI to interact with humans in the real world.
[ TED ]
