Videos

See AI2's full collection of videos on our YouTube channel.
Viewing 1-10 of 182 videos
  • Doing for our robots what nature did for us Thumbnail

    Doing for our robots what nature did for us

    April 29, 2022  |  Leslie Pack Kaelbling
    We, as robot engineers, have to think hard about our role in the design of robots and how it interacts with learning, both in "the factory" (that is, at engineering time) and in "the wild" (that is, when the robot is delivered to a customer). I will share some general thoughts about the strategies for robot…
  • Generalization for Robot Learning In The Wild Thumbnail

    Generalization for Robot Learning In The Wild

    April 15, 2022  |  Deepak Pathak
    How can we train a robot that can generalize to perform thousands of tasks in thousands of environments? This question underscores the holy grail of robot learning, more generally machine learning, research. Current AI systems are incredibly specific in that they only perform the tasks they are trained for and…
  • Robots Need To Reduce, Reuse, and Recycle Thumbnail

    Robots Need To Reduce, Reuse, and Recycle

    April 1, 2022  |  Chelsea Finn
    Despite numerous successes in deep robotic learning over the past decade, the generalization and versatility of robots across environments and tasks has remained a major challenge. This is because much of reinforcement and imitation learning research trains agents from scratch in a single or a few environments…
  • Synthetic Data for Language-Guided Agents Thumbnail

    Synthetic Data for Language-Guided Agents

    March 18, 2022  |  Peter Anderson
    Recent advances in vision and language modeling have been powered by truly massive datasets, often mined from the web. Instruction-following robots will also require large amounts of data to train and evaluate. However, images/videos/documents found on the web do not satisfy the needs of embodied agents, and data…
  • Soft Robotics and AI towards Embodied Intelligence Thumbnail

    Soft Robotics and AI towards Embodied Intelligence

    March 4, 2022  |  Fumiya Iida
    Soft robotics research has made considerable progress in many areas of robotics technologies based on deformable functional materials, including locomotion, manipulation, and other morphological adaptation such as self-healing, self-morph, and mechanical growth. While these technologies open up many new robotics…
  • Explaining Answers with Entailment Trees Thumbnail

    Explaining Answers with Entailment Trees

    November 12, 2021  |  Bhavana Dalvi
    Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by showing the line of reasoning from what is known to the answer, rather than simply showing a fragment of textual evidence (a "rationale'"). If this could be done, new opportunities for understanding and debugging the…
  • Adapting to Long Tail Domains: A Case Study in Clinical Information Thumbnail

    Adapting to Long Tail Domains: A Case Study in Clinical Information

    November 4, 2021  |  Aakanksha Naik
    Advances in deep learning, especially self-supervised representation learning, have produced models that reach human parity on many benchmark datasets, which cover a variety of natural language understanding tasks. However, benchmark datasets are constructed from naturally occurring texts, and are no exception to…
  • Beyond the Label: Robots that Reason about Object Semantics | Embodied AI Lecture Series Thumbnail

    Beyond the Label: Robots that Reason about Object Semantics | Embodied AI Lecture Series

    October 15, 2021  |  Sonia Chernova
    Reliable operation in everyday human environments – homes, offices, and businesses – remains elusive for today’s robotic systems. A key challenge is diversity, as no two homes or businesses are exactly alike. However, despite the innumerable unique aspects of any home, there are many commonalities as well…
  • GooAQ: Open Question Answering with Diverse Answer Types Thumbnail

    GooAQ: Open Question Answering with Diverse Answer Types

    October 12, 2021  |  Daniel Khashabi
    Based on the following paper: https://arxiv.org/abs/2104.08727
  • Open-Ended Learning Leads to Generally Capable Agents | Embodied AI Lecture Series Thumbnail

    Open-Ended Learning Leads to Generally Capable Agents | Embodied AI Lecture Series

    October 1, 2021  |  Max Jaderberg
    In this talk I will cover our recent publication "Open-Ended Learning Leads to Generally Capable Agents" (https://deepmind.com/blog/article/generally-capable-agents-emerge-from-open-ended-play). In this work we turn our attention to how to create embodied agents in simulation that can generalise to unseen test…