COURSE 27Advanced10 IN-DEPTH LESSONS

Robotics and Embodied AI (Intro)

Embodied intelligence: spatial perception, robot kinematics, ROS2 middleware, simulation-to-real transfer, and Vision-Language-Action (VLA) models.

Start Lesson 1: Embodied AI overview →← All 29 Courses

Course Syllabus & Units

Unit 1

Overview

1 lessons
1.1L2

Embodied AI overview

**Embodied AI** connects intelligence to sensors and actuators in the physical world—robot arms, mobile bases, humanoids—not only chat on a screen. Google DeepMind’s Gemini Robotics post (Mar 12, 2025) frames the jump from multimodal dig...

Read lesson →
Unit 2

Loops

1 lessons
2.1L2

Sense, plan, act

The classic robotics loop: **sense** the world, **plan** a next move, **act** with actuators, then sense again—under safety constraints. MIT Manipulation’s course description organizes topics as perception, planning (kinematics, collisio...

Read lesson →
Unit 3

Sim

2 lessons
3.1L2

Simulation and sim-to-real

Training and testing robots in **simulation**, then transferring to reality—where gaps in physics and sensing bite. Modern Robotics courses use CoppeliaSim (formerly V-REP) for kinematics/dynamics animation. MIT Manipulation uses cloud-p...

Read lesson →
3.2L2

Sim-to-real and Isaac Lab

**Isaac Lab** is NVIDIA’s official robot-learning framework for **Isaac Sim**, providing APIs/examples for reinforcement learning, imitation learning, and related workflows. The Isaac Sim docs index lists tutorials for robot setup (URDF/...

Read lesson →
Unit 4

Humans

1 lessons
4.1L2

Human supervisory control

Humans supervising semi-autonomous machines: intervene, take over, and set constraints—teleoperation and shared control included. DeepMind’s Gemini Robotics materials stress **steerability** and collaboration with people; Gemini Robotics...

Read lesson →
Unit 5

Safety

1 lessons
5.1L2

Safety cases for robots (literacy)

A plain-language intro to **safety cases**: structured arguments that a system is acceptably safe for a defined context—not a certification course and not a weapons guide. DeepMind’s Gemini Robotics blog describes a layered approach (low...

Read lesson →
Unit 6

Foundations

1 lessons
6.1L2

Robotics mechanics, planning, and control (literacy)

The **Modern Robotics** spine (Lynch & Park, Cambridge 2017; free preprint on the Northwestern wiki): configuration space, rigid-body motions, forward/inverse kinematics, velocity kinematics & statics, dynamics, trajectory generation, mo...

Read lesson →
Unit 7

Manipulation

1 lessons
7.1L2

Learning-based manipulation themes

**Robotic manipulation** in unstructured scenes (homes, restaurants, kitchens): perceive objects, plan motions and grasps, and control contact. MIT **6.4210/6.4212 Robotic Manipulation** (Fall 2025 site; OCW Fall 2022) teaches algorithmi...

Read lesson →
Unit 8

Vla

1 lessons
8.1L2

Vision-language-action models (high level)

**Vision-language-action (VLA)** models extend vision-language models so they can output **actions** for robots—not only captions or answers. DeepMind’s **RT-2** (Jul 28, 2023) co-fine-tunes VLMs on web and robotics data and represents a...

Read lesson →
Unit 9

Software

1 lessons
9.1L2

ROS and robot software stacks

**ROS (Robot Operating System)** is a widely used open robotics software ecosystem (middleware + tools + conventions)—despite the name, it is not a traditional PC operating system. MASTER’s research guide points learners to official docs...

Read lesson →