systemerror · 38 points · 8 comments · eergisteren · Open original
Comments
4 preview comments · loading full thread
Log in to use comments
Log in to h4cker, then connect Hacker News to publish comments.
MYMystery-Machine2 minuten geleden
Anyone tried using Jev for fast AI robot decisions? Would it make sense?
JVjvanderbot2 uur geleden
First law of calibration: Make sure you do an error analysis.
Finding the table surface is pretty useless using a top-down view, even with April tags, because the range error to an april tag is much more than the bearing (pixel) error to the april tag. You basically have trouble observing the thing you're trying to measure.
If you do this again, ask your agent to conduct this analysis and make sure your desired calibration variables are observable with small error. A second camera from a 45deg angle or even on the table would go a lot further, but then of course other things become unobservable.
Nice workaround using a proxy for force sensing to get touch info, however. And neat project overall!
PJpj_mukh2 uur geleden
Shoutout to people who don't overthink blog setups. "thisismypersonalblog.com" AND GO. It'll do the job.
On a technical note, your setup is not far from where professional setups are headed [1]. Astra is really doing an end-run around (for now) research Robotics setups.
[1]: https://x.com/ihorbeaver/status/2104646736652447854?s=20
AIainch1 uur geleden
Curious to see how they get on with VLAs. They sound great till you have to sit and record hundreds of teleop demos to teach them how to solve your task...
Comments
4 preview comments · loading full threadLog in to h4cker, then connect Hacker News to publish comments.
Anyone tried using Jev for fast AI robot decisions? Would it make sense?
First law of calibration: Make sure you do an error analysis. Finding the table surface is pretty useless using a top-down view, even with April tags, because the range error to an april tag is much more than the bearing (pixel) error to the april tag. You basically have trouble observing the thing you're trying to measure. If you do this again, ask your agent to conduct this analysis and make sure your desired calibration variables are observable with small error. A second camera from a 45deg angle or even on the table would go a lot further, but then of course other things become unobservable. Nice workaround using a proxy for force sensing to get touch info, however. And neat project overall!
Shoutout to people who don't overthink blog setups. "thisismypersonalblog.com" AND GO. It'll do the job. On a technical note, your setup is not far from where professional setups are headed [1]. Astra is really doing an end-run around (for now) research Robotics setups. [1]: https://x.com/ihorbeaver/status/2104646736652447854?s=20
Curious to see how they get on with VLAs. They sound great till you have to sit and record hundreds of teleop demos to teach them how to solve your task...