Pieter Abbeel


RI Seminar : Pieter Abbeel : Machine Learning and Optimization for Robotics

Streamed live on Oct 18, 2013

Pieter Abbeel
Assistant Professor, Department of Electrical Engineering and Computer Science, UC Berkeley

October 18, 2013

Abstract
Robots are typically far less capable in autonomous mode than in tele-operated mode. I believe advances in machine learning and optimization have the potential to significantly narrow the gap between what's possible in tele-operation and what's possible autonomously. First, I will describe in depth "Apprenticeship learning," a new approach to equip robots with new skills through learning from ensembles of expert human demonstrations. Our initial work in apprenticeship learning enabled the most advanced helicopter aerobatics to-date, including maneuvers such as chaos, tic-tocs, and auto-rotation landings which only exceptional expert human pilots can fly. Our most recent work in apprenticeship learning is inspired by challenges in surgical robotics. We are studying how a robot could learn to perform challenging robotic manipulation tasks, such as knot-tying. Next, I will describe our recent advances in optimization based planning --- both in state space and in belief space. Finally, I will briefly discuss our recent work on enabling robots to learn on their own through non-parametric model-based reinforcement learning.

Speaker Biography
Pieter Abbeel received a BS/MS in Electrical Engineering from KU Leuven (Belgium) and received his Ph.D. degree in Computer Science from Stanford University in 2008. He joined the faculty at UC Berkeley in Fall 2008, with an appointment in the Department of Electrical Engineering and Computer Sciences. He has won various awards, including best paper awards at ICML and ICRA, the Sloan Fellowship, the Air Force Office of Scientific Research Young Investigator Program (AFOSR-YIP) award, the Office of Naval Research Young Investigator Program (ONR-YIP) award, the DARPA Young Faculty Award (DARPA-YFA), the Okawa Foundation award, the TR35, the IEEE Robotics and Automation Society (RAS) Early Career Award, and the Dick Volz Best U.S. Ph.D. Thesis in Robotics and Automation Award. He has developed apprenticeship learning algorithms which have enabled advanced helicopter aerobatics, including maneuvers such as tic-tocs, chaos and auto-rotation, which only exceptional human pilots can perform. His group has also enabled the first end-to-end completion of reliably picking up a crumpled laundry article and folding it. His work has been featured in many popular press outlets, including BBC, New York Times, MIT Technology Review, Discovery Channel, SmartPlanet and Wired. His current research focuses on robotics and machine learning with a particular emphasis on challenges in personal robotics, surgical robotics and connectomics.
 

Pieter Abbeel - Towards AI for the physical world

Dec 1, 2019

Towards AI for the Physical World
Pieter Abbeel, Professor, University of California, Berkeley

Pieter Abbeel has been a professor at UC Berkeley since 2008. He is a cofounder of covariant.ai, a cofounder of Gradescope, a research scientist at OpenAI (2016-2017), a founding faculty partner of AI@TheHouse, and an advisor to many AI/robotics startups. He works in machine learning and robotics; in particular, his research focuses on how to make robots learn from people (apprenticeship learning), how to make robots learn through their own trial and error (reinforcement learning), and how to speed up skill acquisition through learning-to-learn (meta-learning). His robots have learned advanced helicopter aerobatics, knot-tying, basic assembly, laundry organization, locomotion, and vision-based robotic manipulation. He has won numerous awards, including best paper awards at ICML, NIPS, and ICRA, early-career awards from NSF, Darpa, ONR, AFOSR, Sloan, TR35, IEEE, and the Presidential Early Career Award for Scientists and Engineers (PECASE). Professor Abbeel’s work is frequently featured in the popular press, including New York Times, BBC, Bloomberg, Wall Street Journal, Wired, Forbes, Tech Review, and NPR.
 

From cage to stage: commercializing AI and robotics

Jul 21, 2022

What does it take to bring a robot or AI process from the lab to market? Learn from experience with The Engine general partner Milo Werner, academic-commercial crossover specialist Joyce Sidopoulos of MassRobotics, and Pieter Abbeel, who splits his time between UC Berkeley and the well-funded AI outfit he founded Covariant.

This panel is part of TechCrunch Sessions: Robotics 2022.

Article "Robotics and AI are going from cage to stage"

by Devin Coldewey
July 22, 2022
 
Last edited:

Pieter Abbeel: Paving the Path to Generalizable Robotics | TransformX 2022

Oct 25, 2022

Pieter Abbeel wears many hats: Professor at UC Berkeley, Director of the Berkeley Robot Learning Lab, Founder of three companies, podcast host @The Robot Brains Podcast, and investor. The common thread is that Professor Abbeel is passionate about AI and robotics. In this keynote presentation, he will explore the possibility of training a large neural network to enable faster learning in robotics. Professor Abbeel will discuss his lab’s approach to solving this problem and will cover how video prediction is an excellent proxy for generalizable robots, the relevant models and datasets useful for pre-training, how unsupervised learning can help robots learn from themselves; and the usefulness of a human-in-the-loop. He will describe a four-step framework that might be able to lead, ultimately, to generalized robotics. Professor Abbeel is co-director of the Berkeley Artificial Intelligence (BAIR) Lab and founded Gradescope, which provides AI to help instructors with grading homework and exams, and Covariant, which provides AI for robotic automation of warehouses and factories. He is also a founding partner at AIX Ventures, a venture capital firm focused on AI start-ups, and is the host of The Robot Brains podcast, which explores what AI and robotics can do today and where they are headed.
 
Back
Top