Hello everyone,
I’m currently developing an open-source autonomous mobile robot that combines navigation, computer vision, voice interaction, and AI assistance into a single platform.
The robot is designed to operate autonomously while providing natural human-robot interaction through voice, vision, and sensor-based awareness.
Hardware
- Raspberry Pi
- RP LiDAR C1
- Camera
- Android Tablet Interface
- Robotics Sensors
- Motor Control System
Software Stack
- ROS2
- MediaPipe
- RTAB-Map
- FastAPI
- Docker
- Whisper
- NVIDIA Isaac Sim
AI Infrastructure
The robot utilizes cloud-based AI services running on NVIDIA H200 GPUs for advanced perception and AI workloads, while real-time robot control remains on-board.
Planned Features
- Autonomous Navigation
- LiDAR-based Mapping and SLAM
- Obstacle Avoidance
- Human Detection and Tracking
- Face and Gesture Recognition
- Voice Assistant Integration
- Natural Language Interaction
- Real-Time Robot Telemetry
- Cloud-Assisted AI Processing
- Digital Twin Simulation using Isaac Sim
Current Status
Development is currently focused on ROS2 integration, navigation, perception pipelines, and human-robot interaction capabilities.
I would appreciate feedback from the community regarding architecture, navigation stack design, and ROS2 best practices.
GitHub: GitHub - ancomevortex/Autonomous-Intractive-Bot · GitHub