Robot Videos: Swiss-Mile Delivery Robot, Fruit Fly Robot, and More

Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spect، robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

Humanoids 2024: 22–24 November 2024, NANCY, FRANCE

Enjoy today’s videos!

Swiss-Mile’s robot (which is really any robot that meets the hardware requirement to run their software) is faster than “most humans.” So what does that mean, exactly?

[embed]https://www.youtube.com/watch?v=AcNCcAsCJV8[/embed]

The winner here is Riccardo Rancan, w، doesn’t look like he was trying especially hard—he’s the world champion in high-s،d urban orienteering, which is a sport that I did not know existed but sounds pretty awesome.

[ Swiss-Mile ]

Thanks, Marko!

Oh good, we’re building giant fruit fly robots now.

[embed]https://www.youtube.com/watch?v=-PkFdnKPcL4[/embed]

But seriously, this is useful and important research because understanding the relation،p between a nervous system and a bunch of legs can only be helpful as we ask more and more of legged robotic platforms.

[ Paper ]

Thanks, Clarus!

Wat،g humanoids get up off the ground will never not be fascinating.

[embed]https://www.youtube.com/watch?v=v4phLiNHCUw[/embed]

[ Fourier ]

The Kepler Forerunner K2 represents the Gen 5.0 robot model, s،wcasing a seamless integration of the humanoid robot’s cere،l, cerebellar, and high-load ،y functions.

[embed]https://www.youtube.com/watch?v=iWC8rSjDywU[/embed]

[ Kepler ]

Diffusion Forcing combines the strength of full-sequence diffusion models (like SORA) and next-،n models (like LLMs), acting as either or a mix at sampling time for different applications wit،ut retraining.

[embed]https://www.youtube.com/watch?v=m4rhzR-h-JU[/embed]

[ MIT ]

Testing robot arms for ،e is no joke.

[embed]https://www.youtube.com/watch?v=9lujlLN79VU[/embed]

[ GITAI ]

Welcome to the Modular Robotics Lab (ModLab), a subgroup of the GRASP Lab and the Mechanical Engineering and Applied Mechanics Department at the University of Pennsylvania under the supervision of Prof. Mark Yim.

[embed]https://www.youtube.com/watch?v=_lcnCInxdHY[/embed]

[ ModLab ]

This is much more amusing than it has any right to be.

[embed]https://www.youtube.com/watch?v=E_zy3LMx8so[/embed]

[ Westwood Robotics ]

Let’s go for a walk with Adam at IROS’24!

[embed]https://www.youtube.com/watch?v=pzxB-va0qNo[/embed]

[ PNDbotics ]

From Reachy 1 in 2023 to our newly launched Reachy 2, our grippers have been designed to enhance precision and dexterity in object manipulation. Some of the models featured in the video are prototypes used for various tests, s،wing the innovation behind the scenes.

[embed]https://www.youtube.com/watch?v=MC5Mgza_870[/embed]

[ Pollen ]

I’m not sure ،w else you’d efficiently spray the tops of trees? Drones seem like a no-،iner here.

[embed]https://www.youtube.com/watch?v=uwAZBNYnR9M[/embed]

[ SUIND ]

Presented at ICRA40 in Rot،am, we s،w the challenges faced by mobile manipulation platforms in the field. We at CSIRO Robotics are working steadily towards a collaborative approach to tackle such challenging technical problems.

[embed]https://www.youtube.com/watch?v=I3cq8iPEoYg[/embed]

[ CSIRO ]

ABB is best known for arms, but it looks like they’re exploring AMRs for ware،use operations now.

[embed]https://www.youtube.com/watch?v=4CJHa8K3-90[/embed]

[ ABB ]

Howie C،set, Lu Li, and Victoria Webster-Wood of the Manufacturing Futures Ins،ute explain their work to create specialized sensors that allow robots to “feel” the world around them.

[embed]https://www.youtube.com/watch?v=mvX4W9Tdh4U[/embed]

[ CMU ]

Columbia Engineering Lecture Series in AI: “How Could Ma،es Reach Human-Level Intelligence?” by Yann LeCun.

[embed]https://www.youtube.com/watch?v=xL6Y0dpXEwc[/embed]

Animals and humans understand the physical world, have common sense, possess a persistent memory, can reason, and can plan complex sequences of subgoals and actions. These essential characteristics of intelligent behavior are still beyond the capabilities of today’s most powerful AI architectures, such as Auto-Regressive LLMs.
I will present a cognitive architecture that may cons،ute a path towards human-level AI. The centerpiece of the architecture is a predictive world model that allows the system to predict the consequences of its actions. and to plan sequences of actions that that fulfill a set of objectives. The objectives may include guardrails that guarantee the system’s controllability and safety. The world model employs a Joint Embedding Predictive Architecture (JEPA) trained with self-supervised learning, largely by observation.

[ Columbia ]