Tony Z. Zhao Profile picture
CS PhD student @Stanford and student researcher @GoogleDeepMind. Aspiring full-stack roboticist. Prev Tesla, GoogleX.
Jan 3, 2024 β€’ 7 tweets β€’ 3 min read
Introducing πŒπ¨π›π’π₯𝐞 π€π‹πŽπ‡π€πŸ„ -- Hardware!
A low-cost, open-source, mobile manipulator.

One of the most high-effort projects in my past 5yrs! Not possible without co-lead @zipengfu and @chelseabfinn.

At the end, what's better than cooking yourself a meal with the πŸ€–πŸ§‘β€πŸ³ How does πŒπ¨π›π’π₯𝐞 π€π‹πŽπ‡π€ work? We seek to achieve a few more goals to augment the dexterity of the original π€π‹πŽπ‡π€:
Mar 27, 2023 β€’ 10 tweets β€’ 4 min read
How can robots acquire fine-grained manipulation skills?

Introducing ACT: Action Chunking with Transformers πŸ€–

Key idea: Imitation, but predict actions in chunks instead of one at a time.

Here are results with only ~15min of demonstrations, running on low-cost arms: In case you missed ALOHA πŸ–, the hardware we use for all these experiments, here is the thread!
Mar 27, 2023 β€’ 10 tweets β€’ 6 min read
Introducing ALOHA πŸ–: 𝐀 𝐋ow-cost 𝐎pen-source 𝐇𝐀rdware System for Bimanual Teleoperation

After 8 months iterating @stanford and 2 months working with beta users, we are finally ready to release it!

Here is what ALOHA is capable of: @Stanford We built ALOHA to be maximally user-friendly for researchers: it is simple, dependable and performant.

The whole system costs <$20k, yet it is more capable than setups with 5-10x the price.