Lucy Cai's banner

Lucy Cai

@lucyjcai • 2,336 subscribers

building @mostrobotic (YC S26) I like robots! @MIT_LISLab MIT

Shorts

1/ we trained a behavior cloning policy on 40 demos of picking and placing a plush toy. the result is so smooth that you would think it was teleoperated. it's also badly overfit. to explore how well it generalizes, we probed it along four axes to find where it suffers most.

1/ we trained a behavior cloning policy on 40 demos of picking and placing a plush toy. the result is so smooth that you would think it was teleoperated. it's also badly overfit. to explore how well it generalizes, we probed it along four axes to find where it suffers most.

26,529 görüntüleme

pov behind the scenes of collecting training data for a mini pick and place policy

pov behind the scenes of collecting training data for a mini pick and place policy

21,214 görüntüleme

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

$We’re excited to launch Instance – a success detector for robot rollouts! Describe your task and drop in a dataset, and it judges success/fail on each rollout with detailed subtask captions– it’s more accurate than Claude Opus 4.8, at a fraction of the latency. This is just the first step toward our larger goal: an autonomous evaluation rig for robot learning. Today, evaluating a robot policy means humans have to watch the robot roll out, mark success, and reset the scene– we're automating that, starting with the success judge.$

We’re excited to launch Instance – a success detector for robot rollouts! Describe your task and drop in a dataset, and it judges success/fail on each rollout with detailed subtask captions– it’s more accurate than Claude Opus 4.8, at a fraction of the latency. This is just the first step toward our larger goal: an autonomous evaluation rig for robot learning. Today, evaluating a robot policy means humans have to watch the robot roll out, mark success, and reset the scene– we're automating that, starting with the success judge.

74,890 görüntüleme • 3 ay önce

unboxed a new pair of robot arms today! and mounted it to our kitchen table

unboxed a new pair of robot arms today! and mounted it to our kitchen table

21,561 görüntüleme • 1 ay önce

first time teleoperating our new Anvil Robotics arm!

first time teleoperating our new Anvil Robotics arm!

28,298 görüntüleme • 3 ay önce

today we're launching automatic captioning at Instance. send us your robot data, and every episode is segmented into captioned subtasks, graded success/fail plus 1-5 on quality and speed. if this could be useful for you, reach out and we'll caption an episode for free!

today we're launching automatic captioning at Instance. send us your robot data, and every episode is segmented into captioned subtasks, graded success/fail plus 1-5 on quality and speed. if this could be useful for you, reach out and we'll caption an episode for free!

15,951 görüntüleme • 2 ay önce

we taught our robot arm to pack us a box of fruit snacks! (with retry behavior)

we taught our robot arm to pack us a box of fruit snacks! (with retry behavior)

10,757 görüntüleme • 1 ay önce

Imagine you told a robot to "find your car keys" in your apartment and it looked around, opened a drawer, and retrieved them for you. As a step towards that, I adapted TiPToP to run on the RBY1 humanoid in our lab! Here's an example instruction it follows: "Put the green block on the blue plate and the yellow block on the magazine." TiPToP helps plan over the right arm + single torso joint, but it's easy to unlock more joints -- even the base wheels -- for more expressive, real-world tasks. Humans find objects without thinking twice. One day, robots will too! 🤖

Imagine you told a robot to "find your car keys" in your apartment and it looked around, opened a drawer, and retrieved them for you. As a step towards that, I adapted TiPToP to run on the RBY1 humanoid in our lab! Here's an example instruction it follows: "Put the green block on the blue plate and the yellow block on the magazine." TiPToP helps plan over the right arm + single torso joint, but it's easy to unlock more joints -- even the base wheels -- for more expressive, real-world tasks. Humans find objects without thinking twice. One day, robots will too! 🤖

14,786 görüntüleme • 7 ay önce

Daha fazla içerik yok.