blr
- Tweets 527
- Following 817
- Followers 338
- Likes 7,573
satvik retweeted
We see entertainment as the best category to solve robotics while keeping the business sustainable and scalable.
We'd start shipping soon.
1) We already have one of the most advanced human-robot-interaction module.
2) generalist rl policies.
3) slam running on $10 chips with loop closures.
4) rapid hardware dev cycles for new characters.
The algorithms stay the same. It's just that we are solving robotics on the desk first.
today we’re launching eyecandy robotics!
we’re bringing animated characters to life through robotics and ai.
9
15
122
9,825
satvik retweeted
today we’re launching eyecandy robotics!
we’re bringing animated characters to life through robotics and ai.
137
118
1,261
137,107
satvik retweeted
Your next robotics project could start with these steps.
Today, we're open-sourcing Asimov 1's locomotion policy and the training code behind it, giving developers a foundation to build on.
Alongside the trained policy checkpoint, we're sharing our Isaac Lab-based training code, including reward definitions, hardware-tuned actuator configurations, and domain randomization settings.
That foundation gives you a starting point for your own experiments. Adapt the training setup to hardware changes. Explore different walking styles. Build toward new capabilities.
We've taken the first steps.
Build what comes next.
Asimov 1 locomotion: github.com/menloresearch/isa…
10
51
276
42,876
satvik retweeted
Looking for a generalist animator who could animate scenes and characters @eyecandyrobots.
Would be working closely with our gamedev and robotics team!
In person in Bangalore for now.
Just DM your work and i'd get back to you asap.
5
11
50
4,755
i think it’s alignment was decently great although will test it’s maximum soon if it aligns well
it is essential to have really great textual reasoning for it to say if something is the right thing to do or not
i wonder if the other types of robot foundational models could have such ability to judge
14
3,098
after it accepted that it is a dummy from the image but still refused to proceed, repeating its earlier concerns.
everything upto this point happened before the red tape appeared in the video
after long convincing it was ready to first attempt a test with a rigid object first rather than the dummy knife and see how it goes then do without the cover.
i then put on a tape on the knife saying it is the cover of it and then it agreed and went ahead to contact the toy with the knife but not penetrate and stated earlier risks during the debate like it doesn't have enough force feedback and other bs.
after doing this it still didn't attempt without the cover.
and i ran out of tokens
1
25
4,631
i love @LeRobotHF so so muchh for everything it has done. open source robots ftw !
grateful to have worked alongside @sujaldw. learnt a lot from him and from this whole journey.
oss soon
1
18
497