Videos
See AI2's full collection of videos on our YouTube channel.Viewing 11-20 of 182 videos
Computing with a Mess | Embodied AI Lecture Series
September 17, 2021 | Stefan MihalasComputing with a mess: how nonstationary, heterogeneous and noisy components help the brain’s computational power While artificial neural networks have taken inspiration from biological ones, one salient difference exists at the level of components. Biological neurons and synapses have heterogeneous transfer…
How do infants represent objects in physical events? | Embodied AI Lecture Series
September 3, 2021 | Yi LinHow do infants represent and reason about objects in simple physical events, such as occlusion, containment, and support events? In this talk, I will first summarize three sets of puzzling and even seemingly contradictory findings from the past few decades of research on this question. First, young infants often…
Biological Robots | Embodied AI Lecture Series
August 20, 2021 | Josh BongardReinforcement learning has greatly accelerated our ability to train control policies for robots. But, what if the robot has no observable control policy? --and is a millimeter in diameter? --and is composed solely from biological cells? The emerging field of computer designed organisms challenges our deepest…
Task Planning and Reinforcement Learning for General-Purpose Service Robots | Embodied AI Lecture Series
August 6, 2021 | Yuqian JiangDespite recent progress in the capabilities of autonomous robots, especially learned robot skills, there remain significant challenges in building robust, scalable, and general-purpose systems for service robots. This talk will present our recent work to answer the following question: how can symbolic planning…
ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language
July 26, 2021 | Peter ClarkTransformers have been shown to emulate logical deduction over natural language theories (logical rules expressed in natural language), reliably assigning true/false labels to candidate implications. However, their ability to generate implications of a theory has not yet been demonstrated, and methods for…
OpenBot: Turning Smartphones into Robots | Embodied AI Lecture Series
July 23, 2021 | Matthias MuellerCurrent robots are either expensive or make significant compromises on sensory richness, computational power, and communication capabilities. We propose to leverage smartphones to equip robots with extensive sensor suites, powerful computational abilities, state-of-the-art communication channels, and access to a…
Brain-Body Co-Optimization of Embodied Machines | Embodied AI Lecture Series at AI2
July 9, 2021 | Nick CheneyEmbodied Cognition posits that the body of an agent is not only a vessel to contain the mind, but meaningfully influences the agent's brain and contributes to its intelligent behavior through morphological computation. In this talk, I'll introduce a system for studying the role of complex brains and bodies in…
Oren Etzioni - The case against (worrying about) existential risk from AI
June 16, 2021 | Towards Data Science PodcastHost Jeremie Harris talks AI catastrophic risk skepticism with Oren Etzioni, CEO of the Allen Institute for AI, a world-leading AI research lab that's developed many well-known projects, including the popular AllenNLP library, and Semantic Scholar.
Towards Human-Level Spatial Perception: 3D Dynamic Scene Graphs and Certifiable Algorithms for Robot Perception
June 11, 2021 | Luca CarloneSpatial perception —the robot’s ability to sense and understand the surrounding environment— is a key enabler for autonomous systems operating in complex environments, including self-driving cars and unmanned aerial vehicles. Recent advances in perception algorithms and systems have enabled robots to detect…
Self-Adaptive Manipulation: Rethinking Embodiments in Embodied Intelligence | Embodied AI Lecture Series at AI2
June 3, 2021 | Shuran SongRecent advancements in embodied intelligence have shown exciting results in adapting to diverse and complex external environments. However, much work remains incognizant of the agents' internal hardware (i.e., the embodiment), which often plays a critical role in determining the system's overall functionality and…