Vivek Gopal Ramaswamy
Notes on teaching a low-cost robot arm to stack paper cups.
I am learning robot manipulation by building things and writing down what happens. This site collects my experiment notes: what I tried, the real numbers, the mistakes, and what I learned.
The current series follows one task from the first model that would not move to a camera-guided skill that stacks reliably, with the videos and the open questions.
Latest posts
SummaryEvery run in one table, and the lessons
What was tried, what each run cost, and what I would tell myself before starting.
3 min read
Oct 24, nightACT on the same data: the same story
The small ACT model stacks cups from the usual positions and fails when I shift them, just like SmolVLA.
2 min read
Oct 24, eveningDoes the model look for cup B?
With cup B moved far away, SmolVLA carried cup A to where cup B used to be. Why, and what data would fix it.
3 min read