jimbooonooo

I have to dig around, I think I still have one of the original wiring boards from around 2006 (maybe)?

I'm curious about materials safety, some platinum/tin 2 part hardners are pretty nasty...

Tons of questions, this is incredibly cool! Can you discuss:

1.) How you compensate for anode consumption/geometry changes over the lifetime of the anode. For instance, does the center get worn away or do you try to uniformly use each "pixel".

2.) More details on anode "pixel" geometry and minimum feature size.

3.) Can you talk about the development process? Did you have in situ measurement, or post build analysis of the part and anode.

4.) Typical surface finish?

Relevant patent here:

https://patents.google.com/patent/US10724146B1/en

Edit: I wonder what compensation for anode consumption looks like. Model based? I assume in-situ measurement/process control is hard.

Yah, please post it! Can you speak to the minimum resolution and wear rate/lifetime with single electrode approaches?

Rejection of neighboring HDD vibe disturbances is already an issue, so fascinating to see what their control approach is. In my limited experience, mechanical HDD control is near top of the game for electromechanical positioning.

Agreed re: mechanical HDDs being engineering marvels. The positioning performance at the price/manf volumes is really incredible.

As the poster below mentions, neighboring actuator coupling/disturbance rejection is very much a performance consideration (even between neighboring HDDs) and then to package all that additional complexity into the same form factor is really something.

It'll be interesting to see if this sticks around, or the added complexity makes it short lived.

Currently reading this and thought the same. Lots of scenarios I hadn't considered, and fun to see IRL work in the same vein.

None of the other video appeared to be live, is that intentional?

I like Boston Dynamics' Stretch as a general solution, but given the sheer volume of standard loading docks/trailers, optimizing loading speed and density with a specialized solution feels (ooof) right.

Customer feedback is useful. Understanding product issue frequency and severity is useful. Should they have emailed him to ask about what issues he was aware of before sending their feedback? Should they have asked you? :)

Cool, is this available as a PDF?

Thanks for the kind words, and agreed, I enjoy the enthusiasm and detailed craftsmanship you see in the boutique shops. Makes me think of watchmakers or similar...

After leaving my old job, I realized that I loved the device design work I had been doing, I just didn't like the work environment... So I started my own company and designed my own fine pointing device, sensors, controller and software.

The company didn't go anywhere because it turns out that business is hard when you don't like to self promote, but I am incredibly proud of the end result. It has high bandwidth, <100nm RMS jitter, a nice network interface, and incorporates reinforcement learning-based controller tuning

Check it out here if you'd like: https://www.rockymountainservo.com

Howdy all,

Recently, a friend and I were joking about ways to ignore unpleasant voices at a family BBQ. A quick look at current speech detection methods led down a rabbit-hole (of course), and resulted in this fun proof of concept.

I was surprised at how well speaker embedding performed (and also acknowledge the sparse, subjective nature of my results).

It was a fun weekend project, and I hope you enjoy the write up!

Rocky Mountain Servo builds fine pointing devices for free space optical comms and space science applications. Our devices are highly reconfigurable, low cost, and easy to integrate. Check out more here:

https://www.rockymountainservo.com