Видео

Abstract: We pursue the goal of developing robots that can interact zero-shot with generic unseen objects via a diverse repertoire of manipulation skills and show how passive human videos can serve as a rich source of data for learning such generalist robots. Unlike typical robot learning approaches which directly learn how a robot should act from interaction data, we adopt a factorized approac...

Some results showing the trained roboagent being deployed in a new setup 3000 miles away! For more results visit robopen.github.io

Explainer Video accompanying the paper Visual Affordance Prediction for Guiding Robot Exploration, presented in ICRA 2023 Abstract: Motivated by the intuitive understanding humans have about the space of possible interactions, and the ease with which they can generalize this understanding to previously unseen scenes, we develop an approach for learning `visual affordances'. Given an input image...

Video explaining the paper Zero-Shot Robot Manipulation from Passive Human Videos

Abstract: Model-based reinforcement learning (RL) algorithms designed for handling complex visual observations typically learn some sort of latent state representation, either explicitly or implicitly. Standard methods of this sort do not distinguish between functionally relevant aspects of the state and irrelevant distractors, instead aiming to represent all available information equally. We p...

Abstract: Self-supervised goal proposal and reaching is a key component for exploration and efficient policy learning algorithms. Such a self-supervised approach without access to any oracle goal sampling distribution requires deep exploration and commitment so that long horizon plans can be efficiently discovered. In this paper, we propose an exploration framework, which learns a dynamics-awar...

Homanga and Kevin's long presentation on the ICLR 2021 paper SKILL TRANSFER VIA PARTIALLY AMORTIZED HIERARCHICAL PLANNING (arxiv.org/pdf/2011.13897.pdf)

Fourier operators and Multipole Graph Neural Operator for solving PDEs arxiv.org/abs/2010.08895 arxiv.org/abs/2006.09535

Short summary video for the paper Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos arxiv.org/pdf/2101.07241.pdf

A short video explaining the paper Conservative Safety Critics for Exploration

Recurrent Independent Mechanisms arxiv.org/abs/1909.10893

Analytic Manifold Learning arxiv.org/abs/2006.08718

Offline Meta Reinforcement Learning arxiv.org/abs/2008.02598

Motion Planning Networks and follow-up papers qureshiahmed.github.io/ arxiv.org/abs/1907.06013

Yana Hasson's (INRIA) talk

Presentation by Yunzhu Li (MIT)