Acuitas Diary #83 (April 2025)

I'm eager to get started on trial-and-error learning, but in the spirit of also making progress on things that aren't as much fun, I rotated back to the Conversation engine for this month. The big new feature was getting what I'll call "purposeful conversations" implemented. Let me explain what I mean.

Euphonia, a "talking head" built by Joseph Faber in the 1800s.

A very old Acuitas feature is the ability to generate questions while idly "thinking," then save them in short-term memory and pose them to a conversation partner if he's unable to answer them himself. This was always something that came up randomly, though. A normal conversation with Acuitas wanders through whatever topics come up as a result of random selection or the partner's prompting. A "purposeful conversation" is a conversation that Acuitas initiates as a way of getting a specific problem addressed. The problem might be "I don't know <fact>," which prompts a question, or it might be another scenario in which Acuitas needs a more capable agent to do something for him. I've done work like this before, but the Executive and Conversation Engine have changed so much that it needed to be redone, unfortunately.

Implementing this in the new systems felt pretty nice, though. Since the Executive and the Conversation Engine each have a narrative scratchboard with problems and goals now, the Executive can just pass its current significant issue down to the Conversation Engine. The CE will then treat getting this issue resolved as the primary goal of the conversation, without losing any of its ability to handle other goals ... so greetings, introductions, tangents started by the human partner, etc. can all be handled as usual. Once the issue that forms the purpose of the conversation gets solved, Acuitas will say goodbye and go back to whatever he was doing.

I also worked on sprucing up some of the conversation features previously introduced this year, trying to make discussion of the partner's actions and states work a little better. Avoiding an infinite regress of either "why did you do that?" or "what happened next?" was a big part of this objective. Now if Acuitas can tie something you did back to one of your presumed goals, he'll just say "I suppose you enjoyed that" or the like. (Actually he says "I suppose you enjoyed a that," because the text generation still needs a little grammar work, ha ha ha oops.)

And I worked on a couple Narrative pain points: inability to register a previously known subgoal (as opposed to a fundamental goal) as the reason a character did something, and general brittleness of the moral reasoning features. I've got the first one taken care of; work on the second is still ongoing.

Until the next cycle,
Jenny

Pump and Hydraulics Progress

If you've been following for a while, you may know I've been working on pump designs for a miniature hydraulic system. The average commercially available water pump appears to be optimized for flow rate rather than pressure, and small-scale hobby hydraulics are barely a thing ... so that means I'm custom-making some of my own parts. Last year I got the peristaltic pump working and found it to be a generally better performer than my original syringe pump, but I always wanted to get a proper motor for it.

The original motor powering all the pumps was an unknown (possibly 12 V) unipolar stepper and gear assembly from my salvage bin. But the precision of a stepper motor truly wasn't necessary in this application, and was costing me some efficiency. For the upgrade, I wanted a plain gearmotor (DC motor + gear box assembly) with a relatively high torque and low RPM. I settled on this pair of motors, both of which are rated for 6 V input:

SOLARBOTICS GM3 GEAR MOTOR (4100 g-cm, 46 rpm)
Dagu HiTech Electronic RS003A DC Motors Gearhead (8800 g-cm, 133 rpm)

You can tell from the torque and speed ratings that the Dagu HiTech was always going to be the better performer. I included the Solarbotics motor in my order because its gearbox and housing are plastic, which may reduce durability but also means it weighs less. In practice, it also draws less current than the Dagu motor, which might mean the power source can weigh less ... these things are important when thinking about walking robot applications!

The next step was to reprint the pump. I left the main pump design essentially unchanged - all I did was correct the geometry errors from the previous iteration. So this time it worked after assembly without an extra shim, and I could put the lid on properly without needing zip ties to hold it closed. The motor housing and coupler were always separate pieces, so I designed two new versions of each, one for the Dagu motor and another for the Solarbotics motor. This is where the 3D printers reeeeaally show off their value. Compared with both the old stepper and each other, the new motors have completely different sizes, shapes, drive shaft designs, and mounting options, but I was able to produce custom parts that mated them to the pump in only a few hours of actual work.

And the test results were amazing. The Dagu is obviously more powerful and delivers a higher flow rate, but both motors have enough torque to drive the pump at the 6 V they're rated for.

Watch to the end for a surprise appearance by the Lab Assistant.

I pressure-test my pumps by dropping a piece of tubing from my second-story window to the back patio, and measuring how high the pump can lift water in the tube. From this it is possible to calculate PSI. I have published results from the previous pump designs. Well: Peristaltic Pump Version 3 can lift water all the way past the window with either motor. Given the water level etc. in this particular test, that's a total lift height of 170 inches. So the pump is producing at least 6 PSI, and I can't measure any higher than that. This makes it competitive with the syringe pump for pressure (at least as far as I can tell - the syringe pump also exceeded my maximum ability to measure), and MUCH better for flow rate.

When I was testing the syringe pumps last year, I used to go read a book for a little bit while I waited for the water to climb to its maximum height! I timed Peristaltic V3 with the Dagu motor, and it can get the water all the way up the tube (standard 1/4" aquarium tubing) in about 24 seconds. So this is a dramatic improvement on where I was when I started.

Hydraulics testing: it gets messy

One little problem remains: I've noticed that, with these more powerful motors, the friction between the latex pump tubing and the rollers gradually pulls the tube through the pump. It'll keep shortening on the intake side and eventually lift out of the water. So I need something to hold it in place without clamping it and blocking the flow. Piercing the tube seems like the only solution for this. I could do it below the water line, OR, the tube is thick-walled enough that I bet I could put a very thin thread or wire through the wall without creating a leak.

I've also started on new actuators, but that is mostly a story for another day. I did get a "knee" style of joint working to the point of a basic demo. Once I started trying to adapt my existing quadruped hinge joint for hydraulic power, I realized it would be less complicated to make an entirely new design that naturally incorporates the hydraulic bladder. Next I need better bladders ... I'm working on that!

Until the next cycle,
Jenny