Govind Chada

founder @enact_labs (YC S26). prev rl/robotics research @StanfordAILab, bs/ms @stanford.

[James Stevens @jamesw_stevens]

We’ve started moving onto longer-horizon tasks.

Table bussing - π0.5 completed 48/50 rollouts on a consistent setup. Very much in distribution, but a useful baseline.

[Govind Chada @govindchada]

@vrajan @enact_labs thank you!

[Govind Chada @govindchada]

after years of babysitting robots in the gates basement at stanford, i’m proud to finally share what we’re building at @enact_labs

[James Stevens @jamesw_stevens]

Today we’re launching Enact: post-training infrastructure that makes robotics models work in the real world.

Robotics models fail when execution reaches states their training data never covered. A slip, an off-angle grasp, or an external disturbance can leave the policy without a learned recovery.

Enact finds those failures and generates the targeted recovery data teams use to make their models reliable in production.

@govindchada @enact_labs

[Govind Chada @govindchada]

@nrol_ling @enact_labs thanks bro, you too

[Govind Chada @govindchada]

@kwong47 @ayyeung42 @enact_labs thank you!

[Govind Chada @govindchada]

@0xsmallbrain @enact_labs thanks!!

[Govind Chada @govindchada]

@realnavida @Shiraz_AI amazing, love to see robots being deployed into production!

[Govind Chada @govindchada]

@LukeStiebel @enact_labs thank you!

[Annie Chen @_anniechen_]

How can robots autonomously handle ambiguous situations that require commonsense reasoning?

*VLM-PC* provides adaptive high-level planning, so robots can get unstuck by exploring multiple strategies.

Paper: https://t.co/UmR6raIPiW

[Annie Chen @_anniechen_]

Very excited to introduce ROAM, our new work that allows a robot to *adapt on-the-go* as it faces OOD situations during deployment, drawing on pre-trained behaviors.

See as ROAM enables our Go1 to roller skate zero-shot 🤖🐕🛼 (without any lessons!)

🧵(1/9)