Vizuara Books
Vision-Language-Action & World Models for Robotics
Build a self-driving VLA stack, from pixels to a real car.
A hands-on path through Vision-Language-Action models, world models, and reinforcement learning for autonomy: the Action Chunking Transformer, Isaac Lab, and code-as-policy. Every idea is built by hand and deployed onto a physical TurboPi car that drives itself.
Read on your Kindle
We'll send this whole book straight to your Kindle — it opens natively, so you can resize the text, read fully offline, and it remembers where you left off. Nothing to download or manage.
Sending to Kindle is for subscribers — subscribe to read the whole library on your Kindle.
00Foundations: Perception, Language, Action6 capsules
Foundations: Perception, Language, Action — 6 chapters.
01Why Vision Alone Is Not Enoughintuitionfree15 min02The Perception-Reasoning-Control Stackconcept🔒16 min03Transformers and Self-Attention, Refreshedconcept🔒16 min04Vision Transformers: Images as Tokensconcept🔒15 min05Cross-Attention and the DETR Intuitionconcept🔒16 min06Setting Up Your Environmentcode🔒14 min01Introduction to Vision-Language-Action5 capsules
Introduction to Vision-Language-Action — 5 chapters.
07What Is a Vision-Language-Action Model?concept🔒16 min08RT-2: A Vision-Language-Action Transformerdeep-dive🔒13 min09ACT: The Action Chunking Transformerdeep-dive🔒14 min10The VLA 3D Simulator Platformproject🔒14 min11Reading the RT-2 and ACT Papersdeep-dive🔒14 min02Building the Action Chunking Transformer6 capsules
Building the Action Chunking Transformer — 6 chapters.
12ACT Architecture: A Conditional VAEdeep-dive🔒16 min13Action Chunking and Temporal Ensemblingmath🔒16 min14Collecting Demonstration Datacode🔒15 min15Training ACT in Simulationcode🔒14 min16The Nine ACT Experimentsproject🔒12 min17Evaluating and Debugging a VLA Policycode🔒13 min03From Simulation to the TurboPi Car6 capsules
From Simulation to the TurboPi Car — 6 chapters.
18Self-Paced VLA Deep Divedeep-dive🔒14 min19Meet the TurboPi Platformconcept🔒13 min20TurboPi Commands and Controlcode🔒13 min21The Sim-to-Real Gapintuition🔒14 min22Deploying ACT on TurboPiproject🔒13 min23Closing the Loop: The First Autonomous Driveproject🔒14 min04World Models5 capsules
World Models — 5 chapters.
24What Is a World Model?concept🔒12 min25Latent Dynamics and Imaginationmath🔒14 min26World Models for Drivingdeep-dive🔒12 min27World Model Experimentsproject🔒14 min28World Models vs Model-Free Policiesintuition🔒12 min05Isaac Lab and Scalable Simulation5 capsules
Isaac Lab and Scalable Simulation — 5 chapters.
29Introduction to Isaac Labconcept🔒14 min30TurboPi in Isaac Labproject🔒12 min31Massively Parallel Simulationconcept🔒12 min32ACT Implementation in Isaac Labcode🔒14 min33The Isaac Lab Training Pipelineproject🔒14 min06Reinforcement Learning for Self-Driving4 capsules
Reinforcement Learning for Self-Driving — 4 chapters.
34Why Reinforcement Learning for Driving?intuition🔒14 min35Reward Shaping for Autonomous Controlmath🔒11 min36Training a Driving Policy with RLcode🔒15 min37Combining Imitation and RLdeep-dive🔒13 min07Code as Policy and Capstone5 capsules
Code as Policy and Capstone — 5 chapters.
38Code as Policy: The Ideaconcept🔒13 min39LLMs That Write Robot Programsdeep-dive🔒12 min40Building a Coding-Agent-as-Policyproject🔒12 min41The Full VLA Pipeline, End to Endproject🔒14 min42Capstone: Your Own Self-Driving Carproject🔒12 minRatings & reviews
No ratings yet. Yours would be the first.