Abel Mendoza

Robotics & Embedded Systems Engineer

Abel Mendoza with computers

Based in Southern California ยท Open to UAV, aerospace, and defense roles.

I like writing code for the web, electronics and embedded systems, and tinkering with robotics.

When I'm not coding I like aggressively cuddling others on the jiu jitsu mat, reading, and educating myself.

Featured Work


Project Showcase

In this video, I'm showcasing my ฮฉ1 robot. Check out my YouTube channel for more robotics videos.

Projects

Selected work in robotics, autonomy, and systems engineering.

Omega-1 Autonomous Robotics Platform

Omega-1 โ€” Autonomous Robotics Platform

A real four-wheeled robot built on Raspberry Pi 4B, controlled through a full-stack web interface. Hardware, firmware, and software built from scratch โ€” designed to scale from manual RC control to GPU-accelerated ML autonomy on NVIDIA Jetson Orin.

๐Ÿค– PID Motor Control ๐Ÿ‘๏ธ 8-Mode Vision Pipeline โš™๏ธ OmegaOS Orchestrator ๐Ÿ“ก ROS2 Multi-Device Network
  • Movement engine: PCA9685 PWM over IยฒC, PID control, odometry tracking, thermal safety watchdog, Xbox controller teleoperation
  • Vision pipeline: ArUco detection, KCF tracking, face detection, motion detection, YOLOv8 on Jetson Orin โ€” 8 modes total
  • OmegaOS: custom service orchestrator with auto-start, crash recovery, and REST API โ€” modeled after systemd
  • ROS2 DDS network across RPi, dev machine, and Jetson with automatic hardware profile switching
  • Web UI: TypeScript, React, Redux, Next.js, TailwindCSS โ€” joystick control, live camera feed, sensor dashboard, vision mode switching
  • Stack: Python ยท Go ยท ROS2 ยท FastAPI ยท OpenCV ยท React ยท Next.js ยท TailwindCSS ยท WebSockets ยท Docker
PX4 Autonomous Missions โ€” Gazebo Harmonic + MAVROS2

PX4 Autonomous Missions โ€” Gazebo Harmonic + MAVROS2

Autonomous UAV mission stack using PX4 v1.15+, Gazebo Harmonic, MAVROS2 (ROS 2 Humble), and MAVSDK-Python. Includes a custom obstacle world with 5 static obstacles for avoidance simulation, a lawnmower scan mission, and full QGroundControl integration.

๐Ÿšง 5-Obstacle Avoidance World ๐Ÿ“ก MAVROS2 + ROS 2 ๐Ÿ—บ๏ธ QGroundControl ๐ŸŒ Full SITL Simulation
  • Custom Gazebo Harmonic world (obstacle_world.sdf) with 5 static obstacles; obstacle_avoidance.py routes 8 pre-planned waypoints around all obstacles at 20 m altitude with โ‰ฅ5 m lateral clearance
  • Lawnmower scan mission (3ร—3 grid, 9 waypoints, ~20 m step) and fly.py basic test script; post-flight telemetry logged to timestamped CSV and visualized with plot_flight.py
  • Stack: PX4 v1.15+, Gazebo Harmonic (gz-sim 8.x), ROS 2 Humble, MAVROS2, MAVSDK-Python 2.0+, QGroundControl, Ubuntu 22.04
Jetson RealSense Perception System project preview

Jetson RealSense Perception

Embedded RGB-D perception toolkit for NVIDIA Jetson Orin Nano and Intel RealSense D455. Supports standalone pyrealsense2 workflows and ROS2 Humble integration, validated on Ubuntu 22.04 / JetPack L4T 36.4.7.

๐ŸŸฆ NVIDIA Jetson Orin Nano ๐Ÿ“ท Intel RealSense D455 ๐Ÿ› ๏ธ librealsense 2.0 (RSUSB) ๐Ÿข ROS2 Humble
  • Standalone scripts: capture, camera info probe, obstacle detection, point clouds, IMU, occupancy mapping
  • ROS2 wrapper validation: realsense2_camera launch, topic sanity, camera_info intrinsics, topic publishers
  • Documentation + onboarding: hardware setup, software setup, ROS2 setup, troubleshooting, validation checklist
  • Full validation: rs-enumerate-devices and check_realsense.py; depth/color streaming capture; ROS2 topic and intrinsics checks
Titan Rover Autonomous Navigation project

Titan Rover โ€” Autonomous Navigation

Group project with the Titan Rover university club โ€” a team of Cal State Fullerton engineering students. Built and contributed to an autonomous rover using ROS, OpenCV, and sensor fusion for real-world terrain navigation and obstacle avoidance.

๐Ÿค– ROS ๐Ÿ‘๏ธ OpenCV ๐Ÿ“ก Sensor Fusion ๐Ÿ—บ๏ธ Autonomous Navigation
  • Autonomous terrain navigation with real-time obstacle detection using OpenCV
  • Sensor fusion pipeline integrating camera, IMU, and encoder data
  • ROS-based architecture with custom nodes for perception and motion planning
LoreBook โ€” AI Life Engine

LoreBook โ€” AI Life Engine

A full-stack AI-powered journaling platform that treats your life as a continuous narrative. Write journal entries โ€” LoreBook automatically writes your biography, builds your timeline, tracks relationships, detects contradictions and identity drift, and predicts your trajectory. Built by Omega Technologies.

๐Ÿง  Continuity Intelligence Engine ๐Ÿ“– Auto-Biography Generation ๐Ÿ”Ž Hybrid RAG Retrieval โš™๏ธ 30+ Analytical Engines
  • Continuity Engine โ€” automatically detects contradictions, identity drift, abandoned goals, emotional arcs, and behavior loops after every journal entry
  • Custom engine orchestration layer with 30+ named engines, dependency-aware DAG scheduling, and parallel execution via constrained concurrency
  • Hybrid RAG pipeline: OpenAI embeddings + pgvector + BM25 keyword search + entity boosting + temporal decay weighting + MMR reranking
  • LoreKeeper Narrative Compiler (LNC) โ€” compiler-inspired epistemic integrity system with Entry IR, dependency graph, entity symbol table with scope resolution, and incremental recompilation
  • 9-layer timeline hierarchy (Mythos โ†’ Eras โ†’ Sagas โ†’ Arcs โ†’ Chapters โ†’ Scenes โ†’ Actions โ†’ MicroActions) auto-built from journal entries
  • Multi-persona AI chat: Gossip Buddy, Therapist, Historian, Strategist, Memory Bank
  • Performance: multi-level caching (TinyLFU + Supabase), 10-100x speed improvements, eliminated N+1 queries
  • Stack: TypeScript ยท React ยท Node.js ยท Supabase/PostgreSQL ยท pgvector ยท OpenAI ยท Stripe ยท GitHub Actions
Screenshot of MacGuardian Watchdog

MacGuardian Watchdog

A comprehensive macOS security suite featuring system hardening, threat detection, AI/ML analysis, and automated remediation. Enterprise-grade security tools for personal and small business use.

๐Ÿ”’ Security Suite ๐Ÿ›ก๏ธ Threat Detection ๐Ÿค– AI/ML Analysis โšก Auto-Fix
  • System hardening: SIP monitoring, Gatekeeper verification, FileVault encryption
  • Real-time threat detection: Process monitoring, network analysis, malware scanning
  • AI/ML-powered security analysis with behavioral pattern recognition
  • File integrity monitoring with automated incident response
  • Tech Stack: Shell, Python, Swift (macOS native app)

Contact


Open to robotics, UAV, embedded systems, and aerospace roles in Southern California.

abelxmendoza@gmail.com