YoVDO

RoboCat: A Self-Improving Agent for Robotic Manipulation - 2023 Fall Robotics Colloquium

Offered By: Paul G. Allen School via YouTube

Tags

Robotics Courses Artificial Intelligence Courses Machine Learning Courses Computer Vision Courses Reinforcement Learning Courses Neural Networks Courses Transfer Learning Courses Autonomous Systems Courses Multi-Task Learning Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a cutting-edge robotics colloquium featuring Coline Devin from Google DeepMind as she presents "RoboCat: A Self-Improving Agent for Robotic Manipulation." Delve into the potential of leveraging diverse robotic experiences to master new skills and embodiments quickly. Learn about RoboCat, a multi-embodiment, multi-task generalist agent for robotic manipulation, designed as a visual goal-conditioned decision transformer. Discover how this innovative agent can generalize to new tasks and robots, both zero-shot and through rapid adaptation. Gain insights into the agent's capabilities through large-scale evaluations in simulation and on real robot embodiments. Understand how RoboCat's training data diversity contributes to cross-task transfer and improved efficiency in adapting to new tasks. This 51-minute talk, part of the Paul G. Allen School's 2023 Fall Robotics Colloquium, offers a glimpse into the future of robot learning and autonomous improvement loops in robotic manipulation.

Syllabus

2023 Fall Robotics Colloquium: Coline Devin (Google Deepmind)


Taught by

Paul G. Allen School

Related Courses

Underactuated Robotics
Massachusetts Institute of Technology via edX
Computer Systems Design for Energy Efficiency
Chalmers University of Technology via edX
Differential Equations: 2x2 Systems
Massachusetts Institute of Technology via edX
Decision-Making for Autonomous Systems
Chalmers University of Technology via edX
Drones and Autonomous Systems I: Fundamentals
University System of Maryland via edX