Manda

[Manda @Mandarobotics]

@chalo2000 @tv0ff Correct! The model actually produced a .usd asset and not a video.

[Manda @Mandarobotics]

GPT-6 Astra generates the best zero-shot Real2Sim assets tested against Opus 5.5 and Fable 5.1. It’s also the most expensive.

We gave frontier models ~20 iPhone captures of real-world objects and asked them to recreate them as realistic, functional NVIDIA Isaac Sim assets:

🧵

[Manda @Mandarobotics]

@MozarellaPesto Thanks!

[Manda @Mandarobotics]

Find the prompts and downloadable assets here: https://t.co/m6nRx6YsuD

We’re expanding our robotics evaluation work with a small number of partners. Tell us about your project: https://t.co/JPjd5dCkXN

[Manda @Mandarobotics]

All tests were zero-shot without human intervention. Inputs were 12-25 ordinary iPhone photos from different angles, plus 1-4 short videos of the objects and their mechanics.

We then placed, tested and rendered the resulting assets in our own Isaac Sim environment.

Even where zero-shot generation falls short, frontier models have become remarkably useful for asset generation. With a few days of iteration, we built a realistic, functional vacuum cleaner for use in our private evals.

[Manda @Mandarobotics]

@imankitgoyal working on it!

[Manda @Mandarobotics]

Astra is dominating existing robot policies. But what can Astra do that existing policies could not?

We analyzed 10 tasks, 5 Episodes each on Astra, Pi0.5, Nvidia’s Cosmos3 Nano and Gr00t 1.7 on RoboLab.

1) Astra is by far the most reliable model in terms of object recognition:

[Max Zhaoshuo Li 李赵硕 @mli0603]

GPT-6 Astra is the most significant leap in robotics I’ve seen in the past few years. It cracked RoboLab with a near-perfect score. Solid infrastructure + scaling ultimately outperformed the heuristics explored in small-scale studies. We’re definitely on the brink of physical RSI.

Source: https://t.co/JvQcTZAy5i

[Akira Sasaki @gclue_akira]

GPT-6 Astra Directで、リアルタイムに動いているな。これはどうやってるんだろう....

[Manda @Mandarobotics]

@tonyzzhao Exaggerating results causes a bad equilibrium for the entire industry.

Everyone else also needs to make up improvements as well to not be perceived as falling behind.

[Manda @Mandarobotics]

We ran a large-scale comparison of different open-source policies on the full Robolab benchmark. Read the report here:

https://t.co/Sob9lY9Ykd

[Manda @Mandarobotics]

4) Simple pick & place tasks are saturated by all policies.