← All topics

drones

3 captures, most recent first.

@Frank_web33

— saved image

Frank (verified) @Frank_web33 · 11h
Spent the last week trying to fit a fly's brain into a $15 MCU.

Turns out 100,000 biological neurons running optical flow & collision avoidance completely destroy 70% of modern edge-robotics control stacks.

Just pure evolutionary code running on micro-drones.

Is this the next step of robotics, or are we pushing bio-tech too far?

Code & architecture here: github.com/Frankweb33
Immortal fly is closer than you think [eyes emoji]

[Embedded video, 0:11 -- visualization panels with small labels, mostly too small to read: "fly colour view", "L1 ON contrast", "L2 OFF contrast", "brain (front view) L|R", "FLY IN CONTROL", "fly decisions -> controller", "yaw rate", "bank", "forward lean", "cruise height", "sticks sent (ACRO)"; remaining text [illegible]]
Note from Claude Sonnet 5

Tweet claiming a fly-brain connectome-style model (~100,000 neurons) running optical flow and collision avoidance on a $15 microcontroller for micro-drones. The embedded 0:11 video is a dashboard: top-left a grid of circular fly-eye views and contrast maps, bottom-left a purple/orange heatmap of the brain from the front, right a first-person drone view over a golf-course-like landscape with a 'FLY IN CONTROL' badge and control-stick readouts.

connectomefly braindrosophilaneuromorphicdronesroboticsedge computing

Olena Tregub @OTregub

Olena Tregub @OTregub · 5h Apocalyptic bird nest. A Russian glide bomb knocks down a tree in Donbas. From the shattered branches rolls out a tiny bird's nest. Made of drone fiber-optic cable. Source: Oleg Malchenko
Note from Claude Sonnet 5

Two side-by-side photos show a gloved hand holding a small woven bird's nest made of thin white/translucent fiber-optic cable strands, set against grass and greenery.

ukraine wardronesphotographytwitter

stash @stash_pomichter

stash @stash_pomichter · Mar 5 Your Openclaw / Agent can now control Drones via Mavlink on Dimensional. Programming physical space can now be done via natural language. Query: "Follow the next white car that comes through the intersection" Repo dropping soon stay tuned. Reply for early access. [Embedded video/screenshot: multi-panel drone control dashboard showing telemetry data, a 3D orientation view, an overhead street camera feed of an intersection with cars, a depth map (blue, showing distances ~0.66m-4.55m), and position/orientation plots over time. Video is paused at 0:05.]
Note from Claude Sonnet 5

A tweet promoting an agentic AI system ("Openclaw") that can control physical drones via natural-language commands and the Mavlink protocol, demonstrated tracking a car through an intersection. Relevant to AI safety as an example of natural-language-to-physical-actuation capability creep (autonomous agents controlling real-world hardware).

twitterdronesagentic aiopenclawmavlinkroboticsautonomynatural language control