Video Friday: The Simplest Walking Robot
Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.
Enjoy today's videos!
We wrote about an earlier version of this absurdly simple walking robot a few years ago. That version had two motors, but this version walks fully controllably with just a single motor! We're told that the robot's name is Mugatu, because for a while, it wasn't an ambiturner.
This was just presented at the IEEE Humanoids Conference in Austin. And here's a second video with more technical detail on how the robot works:
[ CMU ]
Happy Holiday from Boston Dynamics!
Side note-has anyone built a robot that can flawlessly gift-wrap arbitrary objects yet?
[ Boston Dynamics ]
Is there a world where Digit can leverage a large language model (LLM) to expand its capabilities and better adapt to our world? We had the same question. Our innovation team developed this interactive demo to show how LLMs could make our robots more versatile and faster to deploy. The demo enables people to talk to Digit in natural language and ask it to do tasks, giving a glimpse at the future.
[ Agility Robotics ]
Thanks, Tim!
In 2028, ESA will launch its most ambitious exploration mission to search for past and present signs of life on Mars. ESA's Rosalind Franklin rover has unique scientific potential to search for evidence of past life on Mars thanks to its drill and scientific instruments. It will be the first rover to reach a depth of up to two metres deep below the surface, acquiring samples that have been protected from surface radiation and extreme temperatures. The drill will retrieve soils from ancient parts of Mars and analyse them in situ with its onboard laboratory.
[ ESA ]
With ChatGPT celebrating the anniversary of its launch a year ago, we thought this would be a good time to sit down with roboticist Hod Lipson and ask him what he thinks about all the changes with the rapid evolution of AI, how they've enabled the creation of ChatGPT, and what all this may mean for our future.
We propose a technique that simultaneously solves for optimal design and control parameters for a robotic character whose design is parameterized with configurable joints. At the technical core of our technique is an efficient solution strategy that uses dynamic programming to solve for optimal state, control, and design parameters, together with a strategy to remove redundant constraints that commonly exist in general robot assemblies with kinematic loops.
[ Disney Research ]
And now, this.
[ Baby Clappy ] via [ Kazumichi Moriyama ]
Humanoid robots that can autonomously operate in diverse environments have the potential to help address labor shortages in factories, assist elderly at homes, and colonize new planets. While classical controllers for humanoid robots have shown impressive results in a number of settings, they are challenging to generalize and adapt to new environments. Here, we present a fully learning-based approach for humanoid locomotion.
At the University of Michigan, graduate students in robotics all take ROB 550: Robotic Systems Laboratory. For the Fall 2023 class, the final project asked students to create a robot capable of lifting and stacking small pallets. Students designed and built the lift mechanisms from scratch, with a wide variety of solutions being implemented.
In-hand object reorientation is necessary for performing many dexterous manipulation tasks, such as tool use in less structured environments that remain beyond the reach of current robots. We present a general object reorientation controller that uses readings from a single commodity depth camera to dynamically reorient complex and new object shapes by any rotation in real-time, with the median reorientation time being close to seven seconds.
[ Visual Dexterity ]
If you weren't at IEEE Humanoids this week, you missed out on meeting me in person, so shame on you. But you can see all the lightning talks from the Can We Built Baymax workshop right here.
The U.S. National Science Foundation's Graduate Research Fellowship Program (GRFP) has helped ensure the quality, vitality and diversity of the scientific and engineering workforce by recognizing and supporting outstanding graduate students since 1952. Kyle Johnson, a doctoral student at the University of Washington, joins us to talk about his work with robotics, his GRFP experience and how he inspires the next generation.
[ NSF ]