Skip to main content

Who This Book Is For

This textbook is designed for multiple audiences with varying goals and backgrounds.

Primary Audience​

University Students (Undergraduate/Graduate)​

Ideal for students in:

  • Computer Science (AI/Robotics specialization)
  • Electrical Engineering (Robotics/Controls)
  • Mechanical Engineering (Mechatronics)
  • Cognitive Science (Embodied AI)

Prerequisites:

  • Programming experience in Python (intermediate level)
  • Basic understanding of linear algebra and calculus
  • Familiarity with command-line interfaces (Linux/Unix)
  • Understanding of basic physics concepts

What you'll gain:

  • Hands-on experience with industry-standard tools
  • Portfolio projects for job applications
  • Foundation for robotics research or careers
  • Skills in ROS 2, simulation, and AI integration

Instructors and Educators​

Use this textbook to:

  • Design a semester-long robotics course (13-15 weeks)
  • Create lab-based learning experiences
  • Demonstrate real-world AI applications
  • Teach modern robotics development workflows

Resources provided:

  • Complete chapter structure with learning objectives
  • Lab exercises with validation criteria
  • Code examples for demonstrations
  • Instructor guides and rubrics (Appendix E)

Secondary Audience​

AI Engineers Transitioning to Robotics​

If you have:

  • Strong machine learning background
  • Experience with PyTorch, TensorFlow, or similar
  • Interest in embodied AI and physical systems

This textbook provides:

  • Bridge from digital AI to Physical AI
  • ROS 2 integration patterns for ML models
  • Simulation tools for robot training
  • VLA system design and implementation

Robotics Professionals Upskilling​

If you have:

  • Experience with ROS 1 (want to learn ROS 2)
  • Background in traditional robotics (want to add AI)
  • Industrial automation experience

This textbook covers:

  • Modern ROS 2 architecture and Python development
  • NVIDIA Isaac Sim for advanced simulation
  • Integration of LLMs and voice control
  • Cloud and edge deployment strategies

Self-Learners and Hobbyists​

If you are:

  • Passionate about robotics and AI
  • Building personal projects
  • Preparing for a career change

Requirements:

  • Strong self-motivation
  • Access to development hardware (see Requirements)
  • Willingness to troubleshoot independently

Prerequisite Knowledge​

Essential Prerequisites​

Programming:

  • Python 3: classes, decorators, async/await
  • Basic C++ (for understanding some ROS 2 examples)
  • Git and version control concepts

Mathematics:

  • Linear algebra: vectors, matrices, transformations
  • Calculus: derivatives, optimization basics
  • Probability: distributions, Bayes' theorem

Computer Science:

  • Data structures: lists, dictionaries, trees
  • Algorithms: search, sorting, graphs
  • Operating systems: processes, threads, file systems

Helpful But Not Required​

Robotics Background:

  • ROS 1 experience (helps but not required, ROS 2 taught from scratch)
  • Control theory (PID, state-space)
  • Computer vision basics

AI/ML Background:

  • Neural networks and deep learning
  • Large Language Models (LLMs)
  • Speech recognition systems

Hardware Experience:

  • Linux system administration (Ubuntu/Debian)
  • Embedded systems (Raspberry Pi, Jetson)
  • Sensor integration

Not Suited For​

To set proper expectations, this textbook is NOT ideal for:

Absolute Beginners​

If you have:

  • No programming experience → Start with Python fundamentals first
  • No Linux familiarity → Learn basic command-line skills first
  • No math background → Study linear algebra and calculus first

Recommended preparation:

  • Complete a Python course (Coursera, Udacity, etc.)
  • Set up Ubuntu and practice basic terminal commands
  • Review Khan Academy linear algebra and calculus

Industry Practitioners Seeking Quick Reference​

This is a learning textbook, not a reference manual. If you need:

  • Quick API documentation → Use official ROS 2/Isaac Sim docs
  • Production deployment guides → See vendor documentation
  • Troubleshooting for specific hardware → Consult product manuals

Better resources:

Learning Commitment​

Time Investment​

Per Chapter (average):

  • Reading: 1-2 hours
  • Implementation tutorials: 2-3 hours
  • Lab exercises: 2-4 hours
  • Total: 5-9 hours per chapter

Full Course (27 chapters):

  • Total time: 135-245 hours
  • Typical semester: 3-4 hours/week for 13-15 weeks
  • Intensive bootcamp: 4-6 weeks full-time

Hardware Investment​

See Requirements Overview for detailed costs.

Minimum (simulation only): $1,500-2,500

  • Development workstation with RTX GPU
  • No physical robot required

Recommended (sim + edge): $2,500-4,000

  • Development workstation
  • Jetson Orin Nano/NX for edge deployment
  • Sensors (RealSense camera, IMU)

Complete Lab (sim + edge + robot): $5,000-15,000

  • Workstation + Jetson + sensors
  • Robot platform (Unitree Go2, mini-humanoid, etc.)

Success Profiles​

Profile 1: Aspiring Robotics Engineer​

Background:

  • CS undergraduate, junior year
  • Completed data structures, algorithms, AI fundamentals
  • No prior robotics experience

Goals:

  • Gain hands-on robotics skills
  • Build portfolio for job applications
  • Understand industry tools (ROS 2, Isaac Sim)

Approach:

  • Follow all chapters sequentially
  • Complete all lab exercises
  • Extend capstone project with unique features

Outcome:

  • Job-ready robotics engineer
  • Strong foundation for grad school
  • Portfolio projects demonstrating practical skills

Profile 2: AI Researcher Adding Embodiment​

Background:

  • PhD student or postdoc in ML/AI
  • Strong PyTorch, research experience
  • Wants to explore embodied AI

Goals:

  • Understand Physical AI constraints
  • Learn simulation tools for robot learning
  • Integrate own models with ROS 2

Approach:

  • Skim Part I-II (foundations)
  • Deep dive Part IV (Isaac Sim, perception)
  • Focus on Part V (VLA systems)
  • Adapt capstone to research goals

Outcome:

  • Publishable embodied AI research
  • Simulation infrastructure for experiments
  • Understanding of sim-to-real transfer

Profile 3: Instructor Building a Course​

Background:

  • University professor or industry trainer
  • Domain expertise in robotics or AI
  • Needs structured curriculum

Goals:

  • Design semester course
  • Create lab infrastructure
  • Assess student learning

Approach:

  • Review all chapters for course scope
  • Select subset based on semester length
  • Adapt lab exercises to available hardware
  • Use instructor guides (Appendix E)

Outcome:

  • Complete course with syllabus
  • Repeatable lab experiences
  • Assessment rubrics and grading criteria

Getting Started​

Ready to begin? Next steps:

  1. Review Requirements - Ensure you have necessary resources
  2. Read How to Use This Book - Optimize your learning strategy
  3. Start Chapter 1 - Dive into Physical AI

If you're unsure whether this textbook matches your background, start with Chapter 1 and assess. The early chapters provide diagnostic opportunities to identify knowledge gaps.