Lerrel Pinto (@LerrelPinto) / X

Lerrel Pinto

725 posts

Lerrel Pinto

@LerrelPinto

Making robots more dexterous, robust and general. Co-founder of Assured Robot Intelligence (ARI)

NYC

Joined June 2019

Pinned
Lerrel Pinto
@LerrelPinto
Jun 16
Turns out you can train humanoid hands without any robot data. The idea in HUG is quite simple: (a) collect human data with smart glasses, (b) train a human manipulation model, (c) retarget to multi-fingered robot hands.
00:00
32K
Lerrel Pinto
@LerrelPinto
Jun 18, 2025
We have developed a new tactile sensor, called e-Flesh, with a simple working principle: measure deformations in 3D printable microstructures. Now all you need to make tactile sensors is a 3D printer, magnets, and magnetometers! 🧵
00:00
598K
Lerrel Pinto
@LerrelPinto
Sep 24, 2024
Why do we needs 100-1000s of demos to train even simple robot tasks? The answer: Supervised Learning wastes rich observational information. To fix this, we built DynaMo, a Self-Supervised method that operates on small in-domain data by exploiting the dynamics of temporal data.
151K
Lerrel Pinto
@LerrelPinto
Jun 3, 2025
Teaching robots to learn only from RGB human videos is hard! In Feel The Force (FTF), we teach robots to mimic the tactile feedback humans experience when handling objects. This allows for delicate, touch-sensitive tasks—like picking up a raw egg without breaking it. 🧵👇
00:00
70K
Lerrel Pinto
@LerrelPinto
Nov 28, 2023
Meet Dobb·E: a home robot system that needs just 5 minutes of human teaching to learn new tasks. Dobb·E has visited 10 homes, learned 100+ tasks, and we are just getting started! Dobb·E is fully open-sourced (including hardware, models, and software): dobb-e.com 🧵
00:00
212K
Lerrel Pinto
@LerrelPinto
Jan 23, 2024
Excited to release OK-Robot, an open-vocabulary mobile-manipulator for homes. Simply tell the robot what to pick and where to drop it in natural language, and it will do it. Like: Me: "OK Robot, move the Takis from the desk to the nightstand" Robot: ⬇️
00:00
152K
Lerrel Pinto
@LerrelPinto
Mar 6, 2023
While we are going gaga over large models and big data, there is still incredible value left to extract in small models and data, especially in robotics. All the skills shown below were each trained with <1 min of human data and <20 min of online RL fast-imitation.github.io 🧵👇
00:00
118K
Lerrel Pinto
@LerrelPinto
Jul 5, 2022
We just released ROT, a new imitation learning algorithm that can learn vision-based robotic policies with just 1 demonstration, 1 hour of interactive learning and without any pre-training! Project: rot-robot.github.io w/ @haldar_siddhant,@Vaibhavheretoo,@denisyarats (1/N)
00:00
Lerrel Pinto
@LerrelPinto
Oct 19, 2022
Almost ♾ unlabeled data is the “secret sauce” for today's ML, but how do we use uncurated datasets in robot learning? Conditional Behavior Transformer makes sense of "play" style robot demos w/ no labels and no RL to extract conditional policies! Play-to-policy.github.io 🧵
00:00
Lerrel Pinto
@LerrelPinto
Mar 22, 2023
Tactile feedback is one of the most important modalities in manipulation, but has been underutilized in dexterous hands. T-Dex is a framework for learning dexterous policies from tactile play data, beating vision and torque-based methods by 1.7x. tactile-dexterity.github.io 🧵👇
00:00
85K
Lerrel Pinto
@LerrelPinto
Mar 7, 2024
LLMs swept the world by predicting discrete tokens. But what’s the right tool to model continuous, multi-modal, and high dim behaviors? Meet Vector Quantized Behavior Transformer (VQ-BeT), beating or matching diffusion based models in speed, quality, and diversity. 🧵
00:00
49K
Lerrel Pinto
@LerrelPinto
May 27, 2025
Imagine robots learning new skills—without any robot data. Today, we're excited to release EgoZero: our first steps in training robot policies that operate in unseen environments, solely from data collected through humans wearing Aria smart glasses. 🧵👇
00:00
43K
Lerrel Pinto
@LerrelPinto
Sep 25, 2023
We just released TAVI -- a robotics framework that combines touch and vision to solve challenging dexterous tasks in under 1 hour. The key? Use human demonstrations to initialize a policy, followed by tactile-based online learning with vision-based rewards. Details in🧵(1/7)
00:00
139K
Lerrel Pinto
@LerrelPinto
Mar 28, 2025
When life gives you lemons, you pick them up.
00:00
66K