Skip to main content

9 docs tagged with "vla"

View all tags

Capstone Project - The Autonomous Humanoid

Complete VLA pipeline demonstration showing how a simulated humanoid robot receives voice commands, plans paths, navigates obstacles, identifies objects, and manipulates them.

Cognitive Planning with LLMs

Understanding how LLMs perform cognitive planning by translating natural language commands into ROS 2 action sequences.

Glossary - Key Terminology

Key terminology definitions for Module 4: Vision-Language-Action (VLA), including VLA, voice-to-action, cognitive planning, and related concepts.

LLM-Robotics Convergence

Understanding how Large Language Models (LLMs) converge with robotics to enable natural language interaction with humanoid robots.

Module 4 - Vision-Language-Action (VLA)

Introduction to Vision-Language-Action (VLA) systems, covering LLM-robotics convergence, voice-to-action, cognitive planning, and complete VLA pipeline integration.

Voice-to-Action Using OpenAI Whisper

Understanding how OpenAI Whisper enables voice-to-action capabilities for humanoid robots, including the complete pipeline from audio capture to action generation.