Learn the fundamentals of integrated task and motion planning (TAMP), and explore examples using PDDLStream, which combines symbolic task planning and sampling-based motion planning.
Category Archives: Artificial Intelligence
Task Planning in Robotics
Learn the fundamentals of task planning for robotics applications, with a focus on Planning Domain Definition Language (PDDL).
2021 in Review, Part 1: Research Projects at MIT CSAIL
Sebastian discusses 3 of his major collaborative projects at MIT CSAIL, which focus on learning and planning under uncertainty.
Introduction to Behavior Trees
This post introduces behavior trees for designing and managing the execution of complex behaviors in autonomous systems. This includes robotics examples, software library recommendations, and comparisons to finite-state machines.
Object Detection and Instance Segmentation with Detectron2
Learn how to use the Detectron2 library to train object detection and instance segmentation models on your own dataset.
Reinforcement Learning: Looking Ahead and Getting Started
Get a brief overview of topics in reinforcement learning such as multi-agent methods, practical issues, and active areas of research. Also find educational resources to get started with reinforcement learning theory and code.
Introduction to Deep Reinforcement Learning
Learn how deep neural networks have transformed the field of reinforcement learning by exploring some of the popular value-based, policy gradient, and actor-critic methods.
An Intuitive Guide to Reinforcement Learning
Get an overview of traditional reinforcement learning techniques for tabular environments consisting of finite sets of discrete states and actions.
Introduction to Natural Language Processing
A high-level overview of Natural Language Processing (NLP), with a focus on rule-based and statistical (machine learning) systems for understanding text.
Anatomy of a Robotic System
Learn about all the types of skills that make up a capable robotic system.