
Video Friday: Drone vs. flying canoe
“Video Friday” is your weekly selection of great robotics videos collected by your friends at IEEE spectrum Robotics. We also publish a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.
RoboCup 2024: 17-22 July 2024, EINDHOVEN, NETHERLANDS
ICRA@40: 23-26 September 2024, ROTTERDAM, NETHERLANDS
IROS 2024: 14-18 October 2024, ABU DHABI, UAE
ICSR 2024: 23–26 October 2024, ODENSE, DENMARK
Cybathlon 2024: 25–27 October 2024, ZURICH
Enjoy today’s videos!
There’s a Canadian legend about a flying canoe, of course there is. The legend involves drunkenness, a party with some ladies, swearing, and a pact with the devil, of course there is. Luckily for the drone in this video, it doesn’t need any of that to successfully land on this (almost) flying canoe, just a pair of high-friction shock-absorbing legs and a judicious application of reverse thrust.
[ Createk ]
Thank you, Alexis!
This article summarizes a project on autonomous driving using musculoskeletal humanoids. The musculoskeletal humanoid, which mimics the human body in detail, has redundant sensors and a flexible body structure. We consider the developed hardware and software of the Musashi musculoskeletal humanoid in the context of autonomous driving. The respective components of autonomous driving are carried out using the advantages of the hardware and software. Finally, Musashi succeeded in operating pedals and steering wheel with recognition.
[ Paper ] above [ JSK Lab ]
Thank you, Kento!
Robust AI has been pretty quiet lately, but their Carter robot is getting better and better.
[ Robust AI ]
One of the main arguments for building robots that have a similar shape to humans is that we can leverage the enormous amounts of human data for training. In this paper, we present a full-stack system that enables humanoids to learn movements and autonomous skills using human data. We demonstrate the system on our custom-built, 180-centimeter tall humanoid with 33 degrees of freedom, which autonomously performs tasks such as putting on a shoe to stand up and walk, unloading objects from storage shelves, folding a sweatshirt, rearranging objects, typing, and greeting another robot with a success rate of 60 to 100 percent using up to 40 demonstrations.
[ HumanPlus ]
We present OmniH2O (Omni Human-to-Humanoid), a learning-based system for full-body teleoperation and autonomy of humanoid entities. Using kinematic pose as a universal control interface, OmniH2O enables a human to control a life-sized humanoid with dexterous hands in a variety of ways, including real-time teleoperation via a VR headset, verbal instructions, and an RGB camera. OmniH2O also enables full autonomy by learning from teleoperated demonstrations or integrating with pioneering models such as GPT-4.
[ OmniH2O ]
A collaboration between Boxbot, Agility Robotics and Robust.AI at Playground Global. Be sure to watch the video to the end to hear the reactions of the roboticists in the background as the demo works in a very robotic way.
::clap, clap, clap:: yeeeeeeeessssss….
[ Robust AI ]
The use of drones and robots poses a threat to civilian and military actors in conflict zones. We have started trials with robots to see how we can adapt our Hostile Environment Awareness Training (HEAT) courses to this new reality.
[ CSD ]
Thanks, Ebe!
How to make humanoids perform versatile parkour jumps, clap dances, cliff traverses, and box pick-and-moves using a unified RL framework? Introducing WoCoCo: Full-body humanoid control with sequential contacts
[ WoCoCo ]
A selection of excellent demos from the Learning Systems and Robotics Lab at TUM and the University of Toronto.
[ Learning Systems and Robotics Lab ]
Harvest Automation, one of the largest autonomous mobile robot companies, hasn’t updated its website since about 2016, but this week some videos appeared on YouTube.
[ Harvest Automation ]
Northrop Grumman has been a pioneer in underwater technology for more than 50 years. Now we are developing a new class of unmanned underwater vehicle (UUV) called Manta Ray. Named after the giant “winged” fish, Manta Ray will conduct long-duration, long-range missions in marine environments where humans cannot penetrate.
[ Northrop Grumman ]
Demo of Akara Robotics’ autonomous UV disinfection robots.
[ Akara Robotics ]
Scientists have mathematically predicted hundreds of thousands of novel materials that could hold promise for new technologies. But testing whether any of these materials can actually be made is a lengthy process. Now A-Lab comes into play, using robots controlled by artificial intelligence to speed up the process.
[ A-Lab ]
We wrote about this CMU research a while ago, but here’s a pretty nice video.
[ CMU RI ]
Oh, yes, pick-and-place robots.
[ Fanuc ]
Axel Moore describes his laboratory’s work in orthopedic biomechanics to relieve joint pain with robotic assistance.
[ CMU ]
The field of humanoid robots has grown in recent years as several companies and research labs develop new humanoid systems. However, the number of walking robots has not increased noticeably. Despite the need for fast locomotion to quickly complete certain tasks that require traversing complex terrain by running and jumping over obstacles. To provide an overview of the design of humanoid robots with bio-inspired mechanisms, this article introduces the basic features of the human walking style.
[ Paper ]