Skip to content
View original post on X: 👩‍💻 Paige Bailey
Published
18/100

UT Austin releases DamageSim to benchmark robots that avoid breaking objects

AIUT Austin's Robin lab releases OopsieVerse and DamageSim, open-source tools built on MuJoCo via RoboCasa. DamageSim tracks object-centric "health" from physics signals such as contact forces, so robots can be trained and benchmarked on avoiding damage while completing household tasks.
👩‍💻 Paige BaileyVerified on X
@DynamicWebPaige
View on X

Obsessed with both the name and the mission of OopsieVerse and OopsieData! ✨🤖 #CoRL2026

Built on MuJoCo (via RoboCasa), DamageSim tracks object-centric "health" from physics signals like contact forces -- so we can train and benchmark robots not just on completing household tasks, but doing them without breaking stuff.

Awesome open-source work from @UTAustin:

🔗 https://robin-lab.cs.utexas.edu/oopsieverse/

Source details

👩‍💻 Paige Bailey · x.comPublished · added here

Original title: Obsessed with both the name and the mission of OopsieVerse and OopsieData! ✨🤖 #CoRL2026

Topics

Embodied AIOpen-source ecosystemPapers & research