Katia Gao

Experienced Connector Expert | Ethernet, Sensor $ RF Connectors #connector #RJ45 #M8 #M12 #RF

[Tony Zhao @tonyzzhao]

Looking back, it’s wild to see how much has changed. The work, the thinking, the pace. Grateful to work alongside you @chichengcc

[Mustafa. @oprydai]

engineering is beautiful

[Jeremy KD8TUO 🇺🇸⏦⎓⎎⎍⏚ @ElectronicsbyJH]

Finally opened the box 😭😍
@RIGOL_Tech MHO98

[RWB_American @RWB_American]

This guy has all the tools.
Check out his tool box!

[Science girl @sciencegirl]

Laser art on mirrors

[ＤＡＮ_ＡＮＴＯＮＥＬＬＩ @__el__toro__]

"It's just metal."

"Then why does it speak to me?"

[RossRadio @cqcqcqdx]

Cake of the day:🏆 This neat electronic technician cake is all edible! (but watch for the solder lead)

[TITANS of CNC MACHINING @titangilroy]

INSANE Swiss Machining Toolpaths Compilation

[Mechanical Knowledge @mechanical_4u]

Origami-inspired engineering for next-gen space structures.

[Naoto Yoshida @movingsloth]

諸々勉強のために久しぶりに研究室でちゃんとロボットを作ったら、思ったよりかわいいものができた。
@tanichulab

[Kento Kawaharazuka / 河原塚 健人 @KKawaharazuka]

Our Paper "Exceeding the Maximum Speed Limit of the Joint Angle for the Redundant Tendon-driven Structures of Musculoskeletal Humanoids"
presented at IROS2020 is now on arXiv and YouTube!

arXiv: https://t.co/nvoKSQ6vJx
YouTube: https://t.co/X5K6JIDgil

[Amirhosein Hasanpur @RFAmirhosein]

Thinking of illegally boosting your #ISM band #transmitter range?
Don’t sweat it just hit me up.
Range extension is what we do best.😜

#RF #Microwave #hamradio

[村山龍太郎 | Muso Action 株式会社 CEO @03nova]

吉田さんの自作Open Duck Mini！

[obfuscated_D @obfuscated_D]

Gettin real tired of making up aviation connectors…

[Vishakh Ranotra @VishakhRanotra]

Japanese engineers are such geniuses especially when it comes to designing complex and precise machines.

This is not an easy machine to design and build.

Industrial automation and engineering at its finest.

[Matt Brown @nmatt0]

Ever step back and marvel at how cool it is to get paid for having this much fun?

[Ilir Aliu @IlirAliu_]

Robots are getting smarter, but most still fail the same way. They don’t learn from their own mistakes.

A new paper proposes something different: a way for robots to self-improve directly from their failures in the real world.

It’s called PLD (Probe, Learn, Distill).

The idea: instead of collecting endless human demos, let the robot figure out where it fails, learn how to recover, and then distill that knowledge back into its main model.

Key takeaways from the research:
✅ Uses residual reinforcement learning to recover from policy failures
✅ Achieves 99% success on LIBERO and 100% on real Franka and YAM arms
✅ Runs hour-long manipulation tasks without human resets
✅ Builds a feedback loop between real-world data and model adaptation

Unlike supervised fine-tuning, which relies on humans, PLD learns from the robot’s own experience.

By training on its own failure distribution, the model becomes both more efficient and more aligned with the real world.

It’s not just a technical shift, it’s a step toward robots that improve themselves through real-world practice.

Thanks for sharing, @_wenlixiao !!

Paper and demos: https://t.co/V1TKWVZGA1

—-

Weekly robotics and AI insights.
Subscribe free: https://t.co/dsa6wcvq6n

[John Gedmark @Gedmark]

When you ramp up manufacturing, you find weird bottlenecks.

For example: bending tubes.

Astranis is now one of California’s best tube benders, apparently.

[RossRadio @cqcqcqdx]

CHIPSmas Wreath - Upcycled Computer Parts🤓