Carter — Autonomous Object Tracking & Navigation
Built a complete autonomous object tracking and navigation system from scratch — a 4-service microservice Docker architecture for robot navigation using NVIDIA Isaac.
The Challenge
Build a robot that can autonomously detect, track, and navigate toward objects in real-time using stereo depth perception and zero-shot object detection, deployed across both x86 and ARM64/Jetson platforms.
The Solution
Designed a 4-service microservice architecture: Depth Generation (NVIDIA Isaac ROS ESS stereo depth), Object Detection (NanoOWL — text-prompted, zero-shot), Goal Pose Generation (combines detections + depth → 3D navigation goals), and Perception & Path Planning (NVSLAM + NVBLOX + Nav2 → robot movement).
Tech Stack
Key Features
- 4-service microservice Docker architecture
- Zero-shot object detection with text prompts
- Stereo depth to 3D navigation goals
- NVSLAM + NVBLOX for 3D reconstruction
- Cross-platform (x86 + ARM64/Jetson)
Impact
Full autonomous navigation from perception to path planning
Related Projects
ShyldAI — Operating Room Activity Monitor
Built a production medical AI system deployed on NVIDIA Jetson Orin Nano in hospitals — a 6-node distributed ROS2 system for real-time OR activity monitoring.
Accident Detector
Real-time accident detection from video using InternVideo2 + BERT.
Badminton Analysis (MatchFlow)
Rally detection, highlights generation, and Streamlit dashboard for badminton match analysis.