A Billion Dollars in Funding: Figure’s Humanoid Robots

Friday video is your weekly selection of impressive robotics videos, collected by your friends in Spectrum ieee robotics. We also publish a weekly calendar for the next robotics events for the coming months. Please Send us your events for inclusion.

News 2025: 23-24 September 2025, San Francisco

Corl 2025: September 27-30 2025, Seoul

IEEE HUMANOIDIDS: September 30 to October 2, 2025, Seoul

World Robots Summit: October 10-12, 2025, Osaka, Japan

IROS 2025: 19-25 October 2025, Hangzhou, China

Take advantage of today’s videos!

A billion dollars is a lot of money. And it’s real money, not just an assessment. But the figure already had a lot of money. So what will they be able to do now that they did not already do, I wonder?

https://www.youtube.com/watch?v=c-nmhem7iya

[ Figure ]

Robots often succeed in simulation but actually fail. With rhythm, we introduce a systematic approach to the Sim-à-Rél transfer.

https://www.youtube.com/watch?v=KNF-UQB9K50

[ Paper ]

Anthropomorphic robotic hands are essential for robots to learn humans and operate in human environments. While most conceptions vaguely imitate the kinematics and the structure of human hands, the realization of dexterity and the emerging behaviors present in human hands, the anthropomorphic design must also extend to also correspond to passive compliant properties while simultaneously having a kinematic appearance. We present Adapt-Teleop, a system combining a robotic hand with kinematics, skin and a passive dynamic matching by man, as well as a robotic arm for intuitive teleoperation.

https://www.youtube.com/watch?v=gvnkmsfaq3q

[ Paper ]

This robot can walk without any electronic component in its body, because the power is transmitted through wires from concentrated motors outside its body. In addition, the front and rear legs of this robot are coupled optimally and can walk with only four wires.

https://www.youtube.com/watch?v=7YyNEVEY4W8

[ JSK Lab ]

Thank you, Takahiro!

Five teams of engineers from LOS Alamos have contributed to build the ultimate-hole robot dog in a recent engineering sprint. In a few days, the teams programmed their robot dogs to dig, designing personalized “legs” from materials such as sheet metal, foam and 3D -printed polymers. The legs imitated the excavation behavior of animals – paddles and snowshoes with dew claws – and helped the robots to avoid sink into a bucket of 30 gallons. Teams have run to see whose dog could dig the largest hole and dig under the fastest fence.

https://www.youtube.com/watch?v=akdagvctgck

[ Los Alamos ]

This work presents Unipilot, a payload of compact material-loqueur compact autonomy which can be integrated in various modes of realization of robots to allow autonomous operating resilient in GS environments. The system incorporates a multimodal detection series, including LIDAR, radar, inertial vision and detection for robust operation in conditions where unimodal approaches can fail. A large number of experiences are carried out in various environments and on a variety of robot platforms to validate the capacities of mapping, planning and safe navigation activated by the useful load.

https://www.youtube.com/watch?v=6pwi4-YCV8M

[ NTNU ]

Thank you, Kostas!

KAIST HUMANOID V0.5. Developed at the DRCD, KAIST laboratory, with a control policy formed via strengthening learning.

https://www.youtube.com/watch?v=ytwo7lldn4c

[ KAIST ]

I just like the little jumps determined.

https://www.youtube.com/watch?v=f1aaxaskcso

[ AgileX ]

I am always a little suspicious of the robotic laboratories which are exceptionally clean and organized.

https://www.youtube.com/watch?v=ovigdxft4le

[ PNDbotics ]

Uh, has Pal Robotics already saw a kangaroo …?

https://www.youtube.com/watch?v=g7rid4YB1TG

[ PAL ]

See the spots grow. Push, spots, push.

https://www.youtube.com/watch?v=ug-5bn-5nja

[ Tufts ]

The formation of humanoid robots to hiking could accelerate the development of an embodied AI for tasks such as autonomous research and rescue, ecological surveillance in unexplored places, and even more, for example, researchers from the University of Michigan who have developed an AI model that gives humanoids to browse the paths.

https://www.youtube.com/watch?v=-kusnexvj2g

[ Michigan ]

I am dangerously close to being impressed by the humanoid robots of Breakdance.

https://www.youtube.com/watch?v=B94_W7JIR-8

[ Fourier ]

This, however, would impress me.

https://www.youtube.com/watch?v=7htev2udsae

[ Inria ]

In this interview, the co-founder and CEO of Clone, Dhanush Radhakrishnan, discusses the business path to create synthetic humans straight out of science fiction.

(If youtube tries brilliantly for you automatically, go the audio track to the original [which YouTube thinks is Polish] And the video will always be in English.)

https://www.youtube.com/watch?v=2Sya8elzmes

[ Clone ]

This documentary takes you behind the scenes of the Alpha HMND 01 output: the breakthroughs, the late failures and the nights of the construction of the first industrial humanoid robot in the United Kingdom.

https://www.youtube.com/watch?v=JYFLDZULU4

[ Humanoid ]

What is the role of ethical considerations in the development and deployment of robotic and automation technologies, and what are the responsibilities of researchers to ensure that these technologies are progressing transparent, equitable and aligned with the broader well-being of society?

https://www.youtube.com/watch?v=PGBZETZX424

[ ICRA@40 ]

https://www.youtube.com/watch?v=SRPX2HKAP988

Humanoids represent the most versatile robotic platform, capable of walking, manipulating and collaborating with people in humans centered on humans. However, despite recent advances, the construction of humanoids which can work reliably in the real world remains a fundamental challenge. The progress has been hampered by difficulties of control of the whole body, a robust insightful reasoning and filling it with the Sim-à-Rél gap. In this presentation, I will discuss how evolving simulation and learning can systematically overcome these obstacles.

[ UPenn ]