NWO Robotics CLI

Command-line interface for the NWO Robotics API - control robots, manage swarms, and orchestrate intelligent automation with natural language.

Features

• 🤖 Robot Control - Natural language commands for any supported robot
• 🌐 Swarm Management - Coordinate multi-robot teams
• 🧠 AI Models - Access VLA (Vision-Language-Action) models
• 📡 IoT Integration - Sensor fusion with robot commands
• 📶 WiFi Sensing - WiROS integration for CSI/RSSI sensing
• 👤 Human Detection - RuView WiFi-based pose and vital signs
• 🎙️ Speech - STT/TTS with Whisper, Piper, and voice cloning
• 🔒 Safety Systems - Built-in collision avoidance and ethics engine
• 📊 Online Learning - Continuous RL from telemetry

Installation

pip install nwo-robotics

Quick Start

# Authenticate
nwo auth login

# Control a robot with natural language
nwo robot "pick up the box and place it on the table"

# List available AI models
nwo models list

# Create a robot swarm
nwo swarm create "Warehouse Team"

# Enable WiFi sensing
nwo sensor wiros enable --interface wlan0

# Speech-to-text
nwo speech stt transcribe recording.wav

# Text-to-speech
nwo speech tts synthesize "Task completed" --voice en_US-amy-medium -o done.wav

# Clone a voice
nwo speech clone create --sample my_voice.wav --name my_clone

Commands

WiFi Sensing

The NWO CLI integrates with WiROS for WiFi-based sensing:

# Enable WiROS CSI sensing
nwo sensor wiros enable --interface wlan0 --mode csi

# View available topics
nwo sensor wiros topics

# Stream CSI data
nwo sensor wiros stream /nwo/wiros/csi --to-topic /nwo/sensors/wifi_csi

# Extract bearing information
nwo sensor wiros bearing --algorithm music

# Multi-sensor fusion
nwo sensor fusion --sensors wiros --sensors ruview

See WIROS-INTEGRATION.md for detailed documentation.

Speech Integration

The NWO CLI supports speech recognition and synthesis:

# Speech-to-text with Whisper
nwo speech stt transcribe recording.wav --language en

# Text-to-speech with Piper
nwo speech tts synthesize "Hello world" --voice en_US-amy-medium -o hello.wav

# Clone a voice (6+ seconds of audio)
nwo speech clone create --sample my_voice.wav --name my_clone

# Use cloned voice with XTTS
nwo speech tts synthesize "Hello" --voice my_clone --engine xtts

# Direct robot speech
nwo speech speak "Moving to kitchen" --robot unitree_g1_001

Features:

• STT: Whisper (cloud or local whisper.cpp)
• TTS: Piper TTS (fast, local, MIT licensed)
• Voice Cloning: Coqui XTTS v2 (6-second samples)
• 14 languages supported

API Documentation

• API Base: https://nwo.capital/webapp
• Documentation: https://nwo.capital/docs
• Dashboard: https://nwo.capital/webapp/api-key.php

Requirements

• Python 3.8+
• API key from NWO Capital

License

Apache 2.0 - See LICENSE for details.

Support

• Website: https://nwo.capital
• Email: ciprian.pater@publicae.org
• Issues: https://github.com/RedCiprianPater/nwo-robotics-cli/issues