Glossary
This glossary defines key terms used throughout the RoboBook Physical AI & Humanoid Robotics Curriculum.
A
Action
In ROS 2, a persistent communication pattern for long-running tasks with feedback and goal management.
API (Application Programming Interface)
A set of rules and protocols for building and interacting with software applications.
Artificial Intelligence (AI)
The simulation of human intelligence processes by machines, especially computer systems.
B
Behavior Tree
A hierarchical structure used in robotics for organizing and executing complex behaviors.
Bridge
A component that connects two different communication systems, such as ROS 2 and Unity.
C
Cognitive Architecture
A framework for organizing and implementing intelligent behavior in AI systems.
Control Theory
A field of engineering and mathematics that deals with the behavior of dynamical systems with inputs.
D
Deep Learning
A subset of machine learning based on artificial neural networks with representation learning.
Depth Camera
A camera that captures distance information for each pixel in addition to color information.
Docker
A containerization platform that enables applications to run in isolated environments.
Domain Randomization
A technique for training AI models on varied simulated environments to improve real-world performance.
E
Embodied AI
Artificial intelligence that interacts with the physical world through robotic agents.
End Effector
The device at the end of a robotic arm designed to interact with the environment.
F
Forward Kinematics
The process of determining the position of the end effector based on joint angles.
Framework
A reusable, semi-complete application that can be specialized to produce custom applications.
G
Gazebo
A robotics simulation environment that provides physics simulation and 3D rendering.
GPU (Graphics Processing Unit)
A specialized electronic circuit designed to rapidly manipulate and alter memory to accelerate graphics rendering.
H
Hardware-in-the-Loop (HIL)
A testing technique that involves physical hardware components in a simulation loop.
Humanoid Robot
A robot with a human-like body structure, typically including a head, torso, two arms, and two legs.
I
Isaac Sim
NVIDIA's robotics simulation application based on NVIDIA Omniverse.
Isaac ROS
A collection of perception and navigation packages for NVIDIA hardware acceleration.
Inverse Kinematics
The process of determining joint angles required to achieve a desired end effector position.
IoT (Internet of Things)
A system of interrelated computing devices that transfer data over a network without human intervention.
J
Joint
A connection between two or more links in a robotic mechanism.
K
Kinematics
The study of motion without considering the forces that cause the motion.
Knowledge Graph
A structured representation of knowledge as entities and their relationships.
L
LIDAR (Light Detection and Ranging)
A remote sensing method that uses light in the form of a pulsed laser to measure distances.
LLM (Large Language Model)
A type of artificial intelligence model that understands and generates human language.
Localization
The process of determining the position and orientation of a robot in a known map.
Log File
A file that records events occurring in an operating system or software.
M
Mapping
The process of creating a representation of the environment for robot navigation.
Machine Learning
A type of artificial intelligence that enables computers to learn and make decisions from data.
Middleware
Software that provides common services and capabilities to applications beyond what's offered by the operating system.
Module
A self-contained unit of a larger system, such as a software module or hardware module.
N
Nav2
The navigation stack for ROS 2 that provides path planning and obstacle avoidance.
Neural Network
A computing system inspired by biological neural networks that constitute animal brains.
Node
A process that performs computation in a ROS system.
NVIDIA Omniverse
A simulation and collaboration platform for 3D design workflows.
O
Occupancy Grid
A probabilistic representation of space that indicates whether areas are occupied or free.
Omni-directional
A robot that can move in any direction regardless of its orientation.
Operating System
Software that manages computer hardware and software resources.
P
Perception
The ability of a robot to interpret sensory information from its environment.
PID Controller
A control loop mechanism employing feedback in industrial control systems.
Planning
The process of determining a sequence of actions to achieve a goal.
Plugin
A software component that adds specific capabilities to a larger application.
Point Cloud
A set of data points in space, typically representing the external surface of an object.
Pose
The position and orientation of a robot or object in space.
Python
A high-level programming language used extensively in robotics and AI.
Q
Q-Learning
A model-free reinforcement learning algorithm to learn quality of actions.
Quaternion
A mathematical concept used to represent rotations and orientations in 3D space.
R
ROS (Robot Operating System)
A flexible framework for writing robot software that provides hardware abstraction and device drivers.
ROS 2
The second generation of the Robot Operating System with improved features for real-world applications.
RealSense
Intel's stereo camera technology for depth perception and computer vision.
Robot
A machine capable of carrying out complex actions automatically, especially one programmable by a computer.
Robot Kinematics
The study of motion in robotic systems, including forward and inverse kinematics.
Robot Operating System (ROS)
A flexible framework for writing robot software that provides hardware abstraction and device drivers.
Runtime
The time during which a program is executing.
S
Sensor Fusion
The combining of sensory data from multiple sources to improve accuracy and reliability.
SLAM (Simultaneous Localization and Mapping)
The computational problem of constructing or updating a map of an unknown environment while simultaneously keeping track of an agent's location.
Simulation
The imitation of the operation of a real-world process or system over time.
SDF (Simulation Description Format)
An XML-based format for describing objects and environments in simulation.
State Machine
A computational model used to design computer programs and logic circuits.
Supervised Learning
A type of machine learning where the model is trained on labeled data.
System Integration
The process of bringing together component subsystems into one system.
T
TensorFlow
An open-source library for machine learning and artificial intelligence.
Topic
A named bus over which nodes exchange messages in ROS.
Trajectory
The path that a moving object follows through space as a function of time.
Trust Region
An optimization technique that defines a region around the current best solution.
Type Checking
The process of verifying and enforcing the constraints of types in programming languages.
U
Ubuntu
A Linux distribution based on Debian, commonly used in robotics development.
URDF (Unified Robot Description Format)
An XML format for representing a robot model in ROS.
Unity
A cross-platform game engine used for creating 3D and 2D simulations.
Unsupervised Learning
A type of machine learning that learns patterns from unlabeled data.
USB (Universal Serial Bus)
A standard for connecting computers to peripheral devices.
V
VLA (Vision-Language-Action)
A model that connects visual perception, language understanding, and action execution.
Vision System
A system that uses cameras and image processing to perceive the environment.
Virtual Reality (VR)
A simulated experience that can be similar to or completely different from the real world.
Voice-to-Action
A system that converts spoken commands into robotic actions.
W
Webots
A robot simulation software package developed by Cyberbotics.
Workspace
The space within which a robot can operate.
X
Xacro
An XML macro language for generating URDF files in ROS.
Y
YAML (YAML Ain't Markup Language)
A human-readable data serialization language used in configuration files.
Z
Zero-Shot Learning
A machine learning approach where a model learns to recognize new classes without training examples.
Z-Buffer
A method used in 3D graphics to manage image depth coordinates.