[ExI] Figure Helix robot trained for housework

[BillK]

On Sat, 9 May 2026 at 12:18, John Clark <johnkclark at gmail.com> wrote:
> Forget Boston Dynamics and their gymnastics, this is by far the most
impressive demonstration of robot behavior that I have ever seen! Elon Musk
must be green with envy. China too.
>
> John K Clark
> -----------------------------------


The Figure website has a full explanation of just how difficult these robot
actions are.
<https://www.figure.ai/news/helix-02-bedroom-tidy>

I noticed that the two robots seemed to nod towards each other, and I asked
Gemini if this was to synchronise their actions. Gemini watched the video,
searched the Figure website and said Yes, that is what they were doing.
BillK


Gemini AI Thinking -

In the video, the robots (developed by *Figure AI*) are indeed
synchronizing their movements, and the head nodding is a critical part of
how they coordinate.

While it might look like a programmed "human-like" gesture for the sake of
the camera, it actually serves a functional purpose known as a *visual
handshake* or *visual signaling*.
Why they nod

According to the engineers at Figure, these robots operate using a
"Vision-Language-Action" (VLA) model called *Helix-02*. A unique feature of
this system is that the robots do *not* use an invisible wireless network
(like Wi-Fi or Bluetooth) to tell each other what to do. Instead, they
coordinate *entirely through visual perception*.

The "nod" is a deliberate signal one robot sends to the other.

   1.

   *Signaling Readiness:* When one robot has finished a sub-task (like
   grasping its corner of the sheet), it performs a head nod.
   2.

   *Visual Processing:* The second robot’s cameras detect this specific
   motion pattern.
   3.

   *Triggering Action:* Once the nod is "seen" and processed, it acts as a
   visual trigger for both robots to begin the next simultaneous movement,
   such as pulling the duvet upward in unison.

The Significance of the Nod

This approach is a major milestone in robotics because it moves away from
"centralized" control (where one brain controls both bodies) toward
*decentralized,
autonomous collaboration*.

   -

   *Mimicking Human Interaction:* It mimics how two people might make a bed
   by making eye contact or nodding to say "Ready? Go."
   -

   *Robustness:* Because they rely on sight rather than a network link,
   they can coordinate even if a wireless signal is blocked, provided they can
   see one another.
   -

   *Real-time Adaptation:* It allows the robots to work together on tasks
   that require perfect timing—like pulling a flexible, heavy sheet without it
   bunching up—by "reading" their partner's physical state rather than
   following a rigid timer.

The nod essentially acts as a *non-verbal token* in their communication,
proving that the robots can "read" social and behavioral cues to solve
physical problems as a team.

-----------------------------
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20260509/1fcbb666/attachment.htm>