Robotics Engineer Course

Lesson 1 • Sensors and Actuators Overview

Surveys the sensing and actuation hardware that enables robot interaction. Prepares students to select appropriate hardware in later design chapters.

Lesson 2 • Safety and Standards in Robotics

Introduces functional safety principles and international robotics standards. Establishes a safety mindset applied in every subsequent practical chapter.

Lesson 3 • Introduction to Robotic Systems

Defines robots, their classifications, and real-world applications. Establishes shared vocabulary used throughout the entire course.

Lesson 4 • Robot Anatomy and Degrees of Freedom

Examines links, joints, and end-effectors as structural building blocks. Connects physical structure to motion capability and workspace limits.

Lesson 1 • Rigid Body Transformations

Covers rotation matrices, homogeneous transforms, and frame composition. Forms the geometric backbone for all kinematic calculations ahead.

Lesson 2 • Workspace Analysis and Visualization

Characterizes reachable and dexterous workspaces using geometric and numerical tools. Guides design decisions for robot placement and task feasibility.

Lesson 3 • Forward Kinematics

Derives end-effector pose from joint parameters using systematic methods. Students apply Denavit-Hartenberg conventions to multi-joint arms.

Lesson 4 • Inverse Kinematics Methods

Solves joint configurations for a desired end-effector pose analytically and numerically. Addresses redundancy and multiple solution handling.

Lesson 1 • Newton-Euler Dynamics

Applies Newton-Euler recursive formulation to compute joint torques from motion. Connects kinematics to the forces required for motion execution.

Lesson 2 • Friction, Compliance, and Backlash

Models non-ideal joint behaviors that degrade positioning accuracy. Prepares students to compensate for real-world mechanical imperfections.

Lesson 3 • Lagrangian Dynamics Formulation

Derives equations of motion using energy-based Lagrangian mechanics. Provides a systematic alternative to Newton-Euler for complex systems.

Lesson 4 • Actuator Sizing and Selection

Translates dynamic torque requirements into motor and gearbox specifications. Students learn to match actuator performance to task demands.

Lesson 1 • PID Control for Robot Joints

Applies proportional-integral-derivative control to individual robot joints. Students tune gains using systematic methods and evaluate performance metrics.

Lesson 2 • Control Theory Fundamentals

Reviews open-loop vs. closed-loop control, transfer functions, and stability criteria. Establishes the theoretical basis for all robot control strategies.

Lesson 3 • Computed-Torque and Feedforward Control

Uses the dynamic model to cancel nonlinearities and achieve linear error dynamics. Improves tracking accuracy beyond what PID alone can achieve.

Lesson 4 • Cartesian and Task-Space Control

Controls end-effector position and orientation directly in Cartesian space. Enables intuitive task specification without manual joint-space conversion.

Lesson 1 • Programming Manipulators with MoveIt

Uses the MoveIt motion planning framework to command robot arms in simulation and hardware. Covers URDF modeling, planning scenes, and execution pipelines.

Lesson 2 • Robot Operating System Architecture

Introduces ROS nodes, topics, services, and the computation graph model. Provides the software infrastructure used in all subsequent programming exercises.

Lesson 3 • Simulation with Gazebo

Builds and tests robot models in the Gazebo physics simulator before hardware use. Reduces development risk by validating software in a safe virtual environment.

Lesson 4 • Version Control and Software Quality

Applies Git workflows, unit testing, and CI pipelines to robot software projects. Instills professional software engineering practices for maintainable codebases.

Lesson 1 • Visual Servoing and Perception-Action Loops

Closes the loop between visual feedback and robot motion for real-time control. Integrates perception with the control strategies from the previous chapter.

Lesson 2 • Image Processing Fundamentals

Applies filtering, edge detection, and morphological operations to robot imagery. Builds preprocessing skills needed before feature extraction and learning.

Lesson 3 • 3D Perception and Depth Sensing

Processes depth images and point clouds to reconstruct 3D scene geometry. Enables grasp planning and obstacle avoidance in unstructured environments.

Lesson 4 • Object Detection and Recognition

Trains and deploys deep learning detectors for identifying objects in robot scenes. Connects perception output to manipulation and navigation decision-making.

Lesson 1 • Optimization-Based Trajectory Planning

Generates smooth, time-optimal trajectories satisfying kinematic and dynamic constraints. Produces executable motion profiles for real robot hardware.

Lesson 2 • Simultaneous Localization and Mapping

Builds consistent maps while estimating robot pose using SLAM algorithms. Enables autonomous operation in previously unknown environments.

Lesson 3 • Configuration Space and Obstacles

Transforms workspace obstacles into configuration-space representations for planning. Provides the conceptual model underlying all sampling and graph-based planners.

Lesson 4 • Mobile Robot Navigation Stack

Configures localization, mapping, and path planning for autonomous ground robots. Integrates sensor data with the ROS navigation stack for real deployments.

Lesson 1 • System Architecture and Design Patterns

Applies behavior trees, state machines, and modular architectures to complex robots. Ensures scalable, maintainable software for multi-subsystem integration.

Lesson 2 • System Testing and Commissioning

Executes structured integration tests, acceptance criteria, and commissioning procedures. Ensures the deployed system meets performance and safety specifications.

Lesson 3 • Grasping and Manipulation Planning

Plans stable grasps and dexterous manipulation sequences for industrial tasks. Combines perception, kinematics, and planning into end-to-end pick-and-place pipelines.

Lesson 4 • Human-Robot Collaboration

Designs safe and efficient workflows where humans and robots share workspace. Applies collaborative robot standards and intent-recognition techniques.