Hacker News Reader

Comment by dimitry12 | Hacker News Reader

SO-ARM101 has a leader-arm, which is the arm with same exact dimensions and same servos - but used to read/record the trajectory. You move it with your own hand and teleoperate the follower-arm in real-time. Follower-arm is visible in the demo videos.

If you fully control the environment: exact positions of arm-base and all objects which it interacts with - you can just replay the trajectory on the follower-arm. No ML necessary.

You can use LLM to decide which trajectories to replay and in which order based on long-horizon instruction.

View on HN

Yes. You are exactly right. If you want the model to have some adaptability, you will need to train a policy like ACT or GR00T.

Just a quick difference I need to point out as it's critical product spec: leader arms are using 7.4v version of ST3215 (various gear ratios) while follower arms are using 12v version of ST3215. (12v version have higher peak torque at close to 3 Nm)

Thank you for confirming! Love how simple yet magical your demos look, the elegance of bridging LLM-driven long-horizon planning with the arm.

> various gear ratios

for anyone following along at home: THIS IS NOT A SMALL DETAIL!

there are 12 servos total and 4 different types of 7.4 volt ones in the box. make sure you use the right one, or else you'll waste precious time to reassemble the arm.

Wait so the arm isn't doing any learning or moving on its own? I don't understand why you need a leader arm?

It sounds like you use the leader arm to show the robot how the task should be done. If you just used your own arm for the task the robot would have to translate human movements to its own mechanics (hard) but this way it does only need to replicate the movement you showed (easier). After you teach it how to do the movement it can then do it by itself. You show once and it can repeat a million times.

Ok I was under the impression (due to the cameras) that it's doing something with machine learning or can do a novel movement. This is just recording movements and playing them back.

If you bridge recorded trajectories with LVLM, then cameras are necessary visual input for LLM to decide which sub-tasks need to be performed to accomplish long-horizon task, and sub-tasks correspond to pre-recorded ("blind") trajectories which are replayed.

If you go beyond pre-recorded "blind" trajectories into more robust task-policies (which you would have to train from many demonstrations) then cameras become necessary to execute the sub-task.

Reply on news.ycombinator.com