Key Concepts
Workspaces
A workspace is your team’s container for all environments, workflows, and resources. It provides centralized authentication, team collaboration, permissions, resource sharing across environments, and billing and usage tracking.Environments
An environment is a 3D space where your digital twins exist and interact. It can represent physical facilities (warehouse, factory floor, outdoor space), testing scenarios, or simulation environments. Environments support both Edit Mode (for designing and configuring) and Live Mode (for real-time operation and monitoring).Digital Twins
A digital twin is a virtual replica of a physical robot that mirrors its behavior, capabilities, and state in real time. It includes an accurate 3D model, physics simulation, virtual sensors matching the physical setup, and bidirectional real-time sync with the physical robot.Edge Node
An edge node is a physical compute unit deployed at the periphery of the Cyberwave platform (e.g., industrial PC, embedded computer, Raspberry Pi), typically co-located with one or more robots. Edge nodes operate under strict latency, bandwidth, and reliability constraints and are designed to function even under degraded connectivity.Asset Catalog
The Asset Catalog is Cyberwave’s library of pre-configured robot assets. Each asset includes a unique registry ID (e.g.,the-robot-studio/so101), a URDF file describing joints and links, a 3D model for visualization, and metadata about capabilities. Asset types include robot arms, mobile robots, quadrupeds, and drones.
ML Models
ML Models are AI models registered in your workspace that can process various inputs (video, images, audio, text, actions) and integrate with robotics workflows. Cyberwave provides an end-to-end pipeline: collect data through teleoperation, create datasets, train models, deploy as controller policies, and execute autonomously.Datasets
A dataset is a collection of recorded robot operations used for training ML models, containing multiple episodes with joint positions, camera feeds, and timing data.Episodes
An episode is a single recording of the robot completing a task from start to finish. Record 10–15 demonstrations of the same task with slight variations for better model generalisation.Workflows
Workflows let you create automated sequences of robot operations through visual orchestration. Connect nodes to build complex behaviors without writing procedural code. Workflows can be triggered manually, on a schedule, by events, or via the API, and run on Cyberwave’s cloud infrastructure.Controller Policies
A controller policy determines how a robot should act. Cyberwave supports manual control (direct input through the dashboard or SDK), teleoperation (a physical leader arm controlling a follower arm in real time), remote operation (controlling the robot from the Cyberwave dashboard without a leader arm), and AI models (trained models that execute tasks from natural language prompts).Teleoperation
Teleoperation uses a physical leader arm to control a follower arm in real time. It requires both a leader and follower arm and is ideal for data collection and creating training datasets.Remote Operation
Remote operation controls the follower arm directly from the Cyberwave dashboard, only requires the follower arm. Useful for testing, calibration, and manual joint control without needing a physical leader arm.Authentication
Cyberwave uses API keys or tokens to authenticate requests for the Python SDK, REST API calls, and MQTT connections.Next Steps
Quick Start
Connect your robot to a digital twin
SO101 Quickstart
Get started with the SO101 robot arm
UGV Beast Quickstart
Get started with the UGV Beast