Peter Chen (@peterxichen) / X

Peter Chen

156 posts

Peter Chen

@peterxichen

Building general purpose robotics at Amazon FAR. Previously Covariant CEO and Co-Founder, @OpenAI, @UCBerkeley PhD.

Joined December 2017

Peter Chen
@peterxichen
Mar 11, 2024
At Covariant, we have been deploying robots to the real world and thinking hard about how to build truly AI for general purpose robots that can go beyond demos. For a long time, we are building up large robotics datasets through our deployments without the right model that can
32K
Peter Chen
@peterxichen
Jan 15, 2018
Interesting paper from DeepMind: near SOTA density modeling performance on MNIST with only **single pass** through training data and online gradient descent arxiv.org/abs/1712.01897
Peter Chen
@peterxichen
May 6, 2020
Excited to announce our Series B and join forces with @mavolpi @IndexVentures and @JordanJacobs10 @radicalvcfund to push the boundary of AI Robotics in the real world!!
Covariant
@CovariantAI
May 6, 2020
We’ve raised $40m in Series B funding led by @IndexVentures w/ AI-focused @Radicalvcfund + existing investor @AmplifyPartners. Grateful for the support of our investors, customers + partners as we continue to bring AI Robotics to the real world! on.wsj.com/3fqWjiQ
Peter Chen
@peterxichen
Apr 5, 2024
What separates lab robot demos and robots in production? Extremely high reliability. This requires our model to robustly handle many long-tail scenarios like the one in attached picture, where one stray barcode label can tank the 99.95% sortation accuracy requirements. (1/n)
Pieter Abbeel
@pabbeel
Mar 28, 2024
resonates with my own experience: robot demo --> INSANE PAIN --> robot creating value in production luckily I am hopeful we have by now paid most of our dues at Covariant :)
19K
Peter Chen
@peterxichen
Mar 27, 2024
Text foundation models (LLMs) have an incredible ability to adapt to new problems through in-context learning. We show that it’s possible for robots to learn in context as well, in our latest scaling update of RFM-1, Covariant’s robotics foundation model. (1/n)
Covariant
@CovariantAI
Mar 27, 2024
RFM-1's latest scaling update enables robots with in-context learning of grasping improvements. The video shows the self-reflective reasoning capability — after a few tries and failing, the robot has an internal dialogue, hypothesizing that its current gripper is not suited for
00:00
7.5K
Peter Chen
@peterxichen
Apr 30, 2024
It was great to show @geoffreyhinton foundation models meeting robotics at Covariant HQ!
Covariant
@CovariantAI
Apr 30, 2024
Much of the groundbreaking advancements we've witnessed over the past decade, spanning from computer vision, speech recognition, protein folding prediction, and beyond, hinge on the deep learning work conducted by @geoffreyhinton, who has fundamentally changed the focus and
5K
Peter Chen
@peterxichen
Mar 20, 2024
What makes the training data for RFM-1 unique? A few properties that are distinctive from typical lab data: 1. real-world complexity: picking from extremely cluttered scenes where item occlusion presents a challenge for reliability. 2. high-speed handling: the dynamics of
Covariant
@CovariantAI
Mar 18, 2024
This is not a one-off cycle. This is performance over repeated cycles – the new benchmark for reliable AI Robotic systems. High pick rates, navigating cluttered environments, no double-picks, scoops, or errors – just consistent flawless execution, parcel after parcel.
00:00
9.5K
Peter Chen
@peterxichen
May 31, 2024
Very much agree with @alexgkendall - learning from the history of self driving is necessary for anyone that’s serious about ai and robotics. Demo is easy but real-world reliability is hard. Overfitting with elaborate hardware is easy but building generalized intelligence is
Alex Kendall
@alexgkendall
May 28, 2024
Interesting piece on Embodied AI. I wonder what we can learn from self-driving, which has been at the forefront of robotics for the last decade? Are we repeating the same mistakes with humanoids? High cost hardware and simple environments rather than focusing on intelligence
15K
Peter Chen
@peterxichen
Mar 13, 2024
Congrats @chelseabfinn @hausman_k @svlevine on starting a new company. We need more people to work on solving the physical world data challenge and bring foundation models to robotics!
Chelsea Finn
@chelseabfinn
Mar 12, 2024
I’m really excited to be starting a new adventure with multiple amazing friends & colleagues. Our company is called Physical Intelligence (Pi or π, like the policy). A short thread 🧵
6.1K
Peter Chen
@peterxichen
Jan 30, 2020
Had a lot of fun diving deep into how AI Robots learn with @CadeMetz & @satariano
Cade Metz
@CadeMetz
Jan 29, 2020
A robot in Germany shows that machines can learn to do the job of a human (*learn* being the key word): nytimes.com/2020/01/29/tec… (with the great @satariano)
Peter Chen
@peterxichen
Apr 5, 2024
Replying to @peterxichen
It turned out that going from 90% success rate to 99.95% required significantly more data to cover diverse failure modes. This is why a foundation model approach to robotics, instead of building task/embodiment specific policy, so powerful because one single model can leverage
1K
Peter Chen
@peterxichen
Jul 14, 2020
Generative models can drastically accelerate database systems! A new learning task was introduced: Range Density Estimation, for more details see thread 👇
Zongheng Yang
@zongheng_yang
Jul 14, 2020
Can self-supervised learning help computer systems? Our #ICML2020 paper equips autoregressive models to optimize databases. We introduce a new task, range density: estimate the prob. of variables in ranges. A super simple trick gives 10-100x gains. var-skip.github.io 👇 1/
Peter Chen
@peterxichen
Mar 11, 2024
Replying to @peterxichen
With RFM-1 and its multimodal setup, we have the ability to learn from a large amount of robots’ interaction with the world: learning robust manipulation policies by looking at robot actions+outcome across millions of distinct items, learning an intuitive physical world model by
00:00
1.8K
Peter Chen
@peterxichen
May 6, 2020
Thrilled to be working together!
Mike Volpi
@mavolpi
May 6, 2020
Robotics has been a challenging field for years, AI has changed the game and the time is now. Today, we are announcing our investment in @CovariantAI. Excited for our journey with @pabbeel and Peter Chen: indexventures.com/perspectives/r…